<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (JordanFurlong)</title>
    <link>https://pinboard.in/u:JordanFurlong/public/</link>
    <description>recent bookmarks from JordanFurlong</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://www.legaltechnologyhub.com/contents/the-innovators-dilemma-why-existing-legal-ai-platforms-structurally-cannot-solve-the-activation-gap-from-inside/?_hsenc=p2ANqtz-9xnKZg8hC22YKXtI4SFKSZvxgyCkIiZkaSscN0RrVNsGrQW6F6DBSqqnfu6bdPZEkJXpHFUgqtX0XqtdJTSTcaEcQtfQ&amp;_hsmi=424979656"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/05/13/how-in-house-legal-teams-are-using-ai-to-cut-costs-and-win-budget-approval/"/>
	<rdf:li rdf:resource="https://www.legalwritingjournal.org/article/68099-_law-student-professional-development-and-formation-bridging-law-school-student-and-employer-goals_-neil-w-hamilton-and-louis-d-bilionis-cambri"/>
	<rdf:li rdf:resource="https://www.law360.com/pulse/modern-lawyer/articles/2478166"/>
	<rdf:li rdf:resource="https://www.ft.com/content/2205e2d0-50dc-4e80-9bf7-78d0272276c0?shareType=nongift&amp;syn-25a6b1a6=1"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/06/01/law-firms-are-using-ai-as-strategy-tool-not-for-reliable-forecasts-of-litigation-outcomes/"/>
	<rdf:li rdf:resource="https://www.law360.com/pulse/modern-lawyer/articles/2484325?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0"/>
	<rdf:li rdf:resource="https://www.legalfutures.co.uk/latest-news/the-clock-is-ticking-pe-investment-in-law-down-but-deal-volume-up"/>
	<rdf:li rdf:resource="https://nationalmagazine.ca/en-ca/articles/opinion/2026/ai-tools-for-case-law-research-keep-getting-better"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/06/08/why-3-attorneys-left-goodwin-to-start-an-ai-native-ip-firm/"/>
	<rdf:li rdf:resource="https://www.law360.com/pulse/modern-lawyer/articles/2488217?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/06/09/better-than-tar-nearly-expert-what-a-major-study-shows-about-gen-ai-and-tar-in-a-complex-document-review/"/>
	<rdf:li rdf:resource="https://abovethelaw.com/2026/06/trouble-for-midsize-law-firms-is-the-titanic-sinking/"/>
	<rdf:li rdf:resource="https://www.ft.com/content/47f4d549-4560-4830-bf55-47774a9057bc?shareType=nongift"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/06/15/what-can-big-law-learn-from-the-rise-of-ai-native-law-firms/"/>
	<rdf:li rdf:resource="https://www.ft.com/content/d368d0b8-9264-408b-b0af-0f0b660e1c8f?accessToken=zwAAAZ7Q4FyBkdPTaNC4kmRAi9Owrw8LZg4cjw.MEYCIQDFpZRufBPFDFFX8hlAIrI_zVkql94tKVaNKYHoHHof2wIhAPOafuOADKHmrBASca07SyukQaT7FUiOPa52tR3KRhvk&amp;sharetype=gift&amp;token=6eb7065d-19d1-423f-94c5-c66bd2282de5&amp;syn-25a6b1a6=1"/>
	<rdf:li rdf:resource="https://www.legalfutures.co.uk/blog/firms-need-to-move-faster-on-ai-pricing"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/05/13/how-in-house-legal-teams-are-using-ai-to-cut-costs-and-win-budget-approval/?kw=How%25252BIn-House%25252BLegal%25252BTeams%25252BAre%25252BUsing%25252BAI%25252Bto%25252BCut%25252BCosts%25252Band%25252BWin%25252BBudget%25252BApproval&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803"/>
	<rdf:li rdf:resource="https://a2aj.ca/about/"/>
	<rdf:li rdf:resource="https://www.legalfutures.co.uk/latest-news/meet-mike-the-open-source-ai-challenger-built-by-a-city-solicitor"/>
	<rdf:li rdf:resource="https://www.law360.com/pulse/modern-lawyer/articles/2475936?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0"/>
	<rdf:li rdf:resource="https://legaled.ai/claude-for-legal-is-huge/"/>
	<rdf:li rdf:resource="https://www.legaltechnologyhub.com/contents/anthropic-unveils-claude-for-legal-with-12-new-plugins-20-mcp-connectors-and-more/"/>
	<rdf:li rdf:resource="https://free.law/2026/05/12/courtlistener-is-now-available-inside-claude/"/>
	<rdf:li rdf:resource="https://www.theatlantic.com/international/2026/05/iran-war-trump-losing/687094/"/>
	<rdf:li rdf:resource="https://www.law360.com/pulse/modern-lawyer/articles/2473585"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/05/06/wolters-kluwer-launches-invoice-review-ai-agent-for-in-house-teams/"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/05/06/perkins-coie-turns-to-ai-avatars-to-train-lawyers-on-soft-skills/?kw=Perkins%25252BCoie%25252BTurns%25252Bto%25252BAI%25252BAvatars%25252Bto%25252BTrain%25252BLawyers%25252Bon%25252BSoft%25252BSkills&amp;utm_position=2&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803"/>
	<rdf:li rdf:resource="https://alameda.institute/after-order/"/>
	<rdf:li rdf:resource="https://www.ft.com/content/35d63fa0-7175-4204-9ba8-5a0c1f10ba5a?shareType=nongift&amp;syn-25a6b1a6=1"/>
	<rdf:li rdf:resource="https://www.law360.com/pulse/modern-lawyer/articles/2470293?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0"/>
	<rdf:li rdf:resource="https://abovethelaw.com/2026/04/clearyx-bets-that-biglaw-disruption-is-inevitable/"/>
	<rdf:li rdf:resource="https://www.law.com/international-edition/2026/04/29/why-ai-is-making-the-top-lawyers-more-expensive/print/"/>
	<rdf:li rdf:resource="https://www.attorneyatwork.com/data-driven-law-firm-valuation/?mc_cid=8b76962049&amp;mc_eid=93b1286af1"/>
	<rdf:li rdf:resource="https://www.legalfutures.co.uk/latest-news/sra-puts-size-of-suspected-pm-law-fraud-at-40m"/>
	<rdf:li rdf:resource="https://www.law360.com/pulse/modern-lawyer/articles/2461235?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/04/23/inside-freshfields-partnership-with-anthropic-and-what-it-means-for-the-legal-industry-/?kw=Inside%25252BFreshfields%25252527%25252BPartnership%25252BWith%25252BAnthropic%25252Band%25252BWhat%25252BIt%25252BMeans%25252Bfor%25252Bthe%25252BLegal%25252BIndustry&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803"/>
	<rdf:li rdf:resource="https://www.legalfutures.co.uk/latest-news/eight-out-of-10-candidates-say-sqe-is-not-fit-for-purpose"/>
	<rdf:li rdf:resource="https://www.legalfutures.co.uk/latest-news/us-personal-injury-firm-attracts-125m-private-equity-investment"/>
	<rdf:li rdf:resource="https://www.thomsonreuters.com/en-us/posts/legal/honing-legal-judgment-training-lawyers/"/>
	<rdf:li rdf:resource="https://www.thomsonreuters.com/en-us/posts/wp-content/uploads/sites/20/2025/09/2025-NCSC-Judges-White-Paper.pdf"/>
	<rdf:li rdf:resource="https://www.thomsonreuters.com/en-us/posts/innovation/thomson-reuters-and-hotshot-partner-to-close-the-gap-between-law-school-and-legal-practice/"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/04/01/better-service-and-higher-rates-inside-goodwins-ambitious-ai-training-program-/"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/04/01/google-xs-discovery-litigation-strategy-leader-gen-ai-is-fundamentally-reshaping-the-legal-department-outside-counsel-relationship-/?kw=Google%25252BX%25252527s%25252BDiscovery%25252C%25252BLitigation%25252BStrategy%25252BLeader%25253A%25252BGen%25252BAI%25252Bis%25252B%25252526lsquo%25253BFundamentally%25252BReshaping%25252527%25252Bthe%25252BLegal%25252BDepartment%25252C%25252BOutside%25252BCounsel%25252BRelationship&amp;utm_position=3&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803"/>
	<rdf:li rdf:resource="https://michaelplaxton.substack.com/p/to-our-next-law-dean"/>
	<rdf:li rdf:resource="https://www.legalfutures.co.uk/latest-news/entry-of-pe-puts-focus-on-capital-growth-not-annual-cash-distribution"/>
	<rdf:li rdf:resource="https://www.law360.com/pulse/modern-lawyer/articles/2449518"/>
	<rdf:li rdf:resource="https://www.legaltechnologyhub.com/contents/law-firms-want-to-change;-they-just-cant/?_hsenc=p2ANqtz-9ieqmsoDQ0tp7slmhquQtAo2i_5e2WkDcF-neDNyEWkJFLEIauNQOdRZ8Lc9JIrKasfsjj-PWNqf21oE4t4IHmPVFu6g&amp;_hsmi=417739967"/>
	<rdf:li rdf:resource="https://www.legaltechnologyhub.com/contents/the-shift-beyond-prompting-why-legal-ai-is-moving-to-systems-that-act/?_hsenc=p2ANqtz-9gt9QUprf7Bwj2h0JF_-mHDoo0oSqAtwpKz_ZApfd6jFbpVCYZqn4dJyL5jjopbh1CoJ0za1rvLWXWcm2OjIF1hywibw&amp;_hsmi=417091366"/>
	<rdf:li rdf:resource="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6461619&amp;dgcid=ejournal_html"/>
	<rdf:li rdf:resource="https://www.law360.com/pulse/modern-lawyer/articles/2468330"/>
	<rdf:li rdf:resource="https://acoup.blog/2026/03/25/miscellanea-the-war-in-iran/"/>
	<rdf:li rdf:resource="https://thewildcat.co.uk/project-items/noslegal/"/>
	<rdf:li rdf:resource="https://www.lek.com/insights/business-services/how-legal-msos-are-restructuring-law-firm-operations"/>
	<rdf:li rdf:resource="https://www.canadianlawyermag.com/resources/professional-regulation/law-that-replaces-law-society-of-bc-diminishes-bars-self-regulation-is-constitutional-bc-court/394038"/>
	<rdf:li rdf:resource="https://www.argmin.net/p/cosma-shalizi-is-aware-of-all-internet"/>
	<rdf:li rdf:resource="https://www.victorialawfoundation.org.au/research-projects/measure-for-measure"/>
	<rdf:li rdf:resource="https://www.legalfuel.com/as-ai-allows-lawyers-to-better-serve-clients-firms-must-prepare-for-the-post-ai-world/"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/04/21/norm-laws-hires-from-ropes--gray-sidley-discuss-their-tech-driven-transition/?kw=Norm%25252BLaw%25252527s%25252BHires%25252BFrom%25252BRopes%25252B%25252526%25252BGray%25252C%25252BSidley%25252BDiscuss%25252BTheir%25252BTech-Driven%25252BTransition&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803"/>
	<rdf:li rdf:resource="https://www.law360.com/pulse/modern-lawyer/articles/2468243"/>
	<rdf:li rdf:resource="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6461619"/>
	<rdf:li rdf:resource="https://www.law360.com/pulse/modern-lawyer/articles/2469238"/>
	<rdf:li rdf:resource="https://www.law.com/legaltechnews/2026/04/15/inside-an-ai-native-law-firm-started-by-cooley-fenwick-and-thomson-reuters-veterans-/?kw=Inside%25252Ban%25252B%25252527AI-Native%25252BLaw%25252BFirm%25252527%25252BStarted%25252Bby%25252BCooley%25252C%25252BFenwick%25252Band%25252BThomson%25252BReuters%25252BVeterans&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803"/>
	<rdf:li rdf:resource="https://www.legalfutures.co.uk/latest-news/vos-legal-education-needs-complete-rethink-in-age-of-machine-justice"/>
	<rdf:li rdf:resource="https://www.law.com/international-edition/2026/04/16/inside-private-equitys-law-firm-fishing-expedition/"/>
	<rdf:li rdf:resource="https://davidoks.blog/p/why-the-atm-didnt-kill-bank-teller"/>
	<rdf:li rdf:resource="https://www.legaltechnologyhub.com/contents/aba-techshow-2026-superpowers-in-theory-and-in-practice/"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=N5JDzS9MQYI&amp;t=1214s"/>
	<rdf:li rdf:resource="https://www.legaltechnologyhub.com/contents/ai-vocabulary-agentic-systems-architecture-and-governance/?_hsenc=p2ANqtz--G56uLmXbQDvLb31Sy7J7FlvlHocQM7jDHmo78PCh7CzHZ2p8jBcWRj0QjRqSvD5GcI0UopG4VqPbRif5MoabdLFMVBQ&amp;_hsmi=412008385"/>
	<rdf:li rdf:resource="https://lawyerforward.substack.com/p/yes-they-are-trying-to-replace-you"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://www.legaltechnologyhub.com/contents/the-innovators-dilemma-why-existing-legal-ai-platforms-structurally-cannot-solve-the-activation-gap-from-inside/?_hsenc=p2ANqtz-9xnKZg8hC22YKXtI4SFKSZvxgyCkIiZkaSscN0RrVNsGrQW6F6DBSqqnfu6bdPZEkJXpHFUgqtX0XqtdJTSTcaEcQtfQ&amp;_hsmi=424979656">
    <title>The Innovator’s Dilemma: Why Existing Legal AI Platforms Structurally Cannot Solve the Activation Gap from Inside | Legaltech Hub</title>
    <dc:date>2026-06-22T21:27:23+00:00</dc:date>
    <link>https://www.legaltechnologyhub.com/contents/the-innovators-dilemma-why-existing-legal-ai-platforms-structurally-cannot-solve-the-activation-gap-from-inside/?_hsenc=p2ANqtz-9xnKZg8hC22YKXtI4SFKSZvxgyCkIiZkaSscN0RrVNsGrQW6F6DBSqqnfu6bdPZEkJXpHFUgqtX0XqtdJTSTcaEcQtfQ&amp;_hsmi=424979656</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[When Clayton Christensen published The Innovator’s Dilemma in 1997, he was describing a pattern that had already played out in disk drives, mini-computers, and steel. A successful incumbent, calibrated to a particular customer and a particular margin structure, meets a new technology that is worse on the dimensions its customers currently care about but better on a different set. The incumbent dismisses it, reasonably, because in its customers’ terms it is worse. By the time the new technology is good enough to compete on the old dimensions, it has taken the market from underneath.

Something close to that pattern is now visible in legal AI. What is striking is how clearly the people involved can see it, and how little the constraints bend even so. 

The Pressure from Below and Above 
The incumbents here are the existing legal AI platforms: the CLM vendors, contract intelligence tools, e-billing systems, and document automation built over the last decade around the in-house function and the firms working with it. Most are well funded, well built, and led by capable people. None is in obvious trouble. Several are still growing quickly. 

The pressure from below is the autopilot-native services category: firms pricing for the outcome rather than the seat and taking the lawyer out of the loop for a narrow band of work. By the platforms’ standards, they look small, and their output is occasionally rough. The pressure from above is the foundation model providers. Anthropic launched Claude for Legal in May 2026 with practice-area plugins and a set of connectors into legal software, and OpenAI and Google are pushing in parallel. By the platforms’ standards, those legal offerings are early and partial. 

The classic incumbent response to both is that they are not really doing what we do. That is, for now, true. It is also more or less what Christensen says incumbents say shortly before the ground moves. 

Why Neither Side Can Be Defended from Inside 
The reason the platforms cannot defend either side is not that they are slow, or under-resourced, or blind to the threat. It is that the moves which would count as defending themselves are the same moves that would destroy the business paying the bills today. Defending against the autopilot-natives means selling outcomes, which means selling work the platforms’ own customers currently do. The channel walks. The comp plans, the partner networks, and the success functions are all calibrated to the customer doing the existing work. To go that way, a platform has to be willing to compete with the people it sells to. 

Defending against the foundation model providers means owning more of the operating layer beneath the model, which is exactly the activation work most platforms have left to others. The product was always a workflow on top of someone else’s intelligence; now the intelligence is starting to do the workflow too. Moving down into the operating layer is the defensive move. It is not where most platforms are built to sit today. The model providers will reach for some of that work as well; what they cannot easily reach is its deployment inside a specific enterprise, against a specific team’s playbooks, which is a services problem rather than a model problem. 

Each move is rational on its own. Together they ask a platform to do the thing almost no incumbent in Christensen’s casebook has done well: cannibalise the high-margin seat business that funds the company now, in order to stand up a lower-margin services business that might fund it in five years. Boards rarely approve that. Sales orgs rarely execute it. The investors who backed the current trajectory rarely reward it. 

The Honest Caveat 
I want to be careful not to overstate this. The Christensen framework is descriptive, not deterministic; patterns are patterns, not prophecies. There is a version of the next few years in which the autopilot-natives plateau, the model providers are pulled into larger markets, and the platforms ride the cycle out with their core intact. 

But the question every platform CEO is now being asked by their board, in one form or another, is the same. What is our answer on the autopilot-natives? On Claude for Legal? On why NRR is not expanding and renewals are getting harder? The improvements most platforms can reach for, a sharper roadmap, a bigger success team, a tuned sales motion, are real, but they are not answers to a disruption pattern. The pattern asks for a different operating model, not a better version of the current one. 

That is the trap. The companies that built the current legal AI market are, by construction, the least free to operate the next one, because operating it would mean becoming a different kind of company, and no company is naturally good at becoming a different kind of company. 

The One Move that Remains 
There is one move that does not require that. A platform can bring in a partner to operate the layer it cannot afford to build inside, on a commercial structure that aligns the partner’s economics with the platform’s rather than competing with them. That partner takes the work budget the autopilot-natives are reaching for, and the activation work the model providers will try to reach for, and runs both under the platform’s brand, in a single contract with the customer. 

The platform CEOs thinking clearly about this are landing in the same place. The dilemma is not soluble from inside the platform alone. The answer has to come from outside, in a shape no current consultancy, ALSP, or services firm offers by default. Telon is built to be that partner. 

The next essay is about what that partner has to look like, and why none of the categories already in the market produces it. 

For now, the observation is simple enough. The platforms are facing the textbook innovator’s dilemma in real time. The ones that find a way to bring the answer in from outside, before the pressure from below and above closes in, will be the ones that compound. The ones that do not will end up as the case studies everyone later claims were obvious.]]></description>
<dc:subject>ai innovation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:248774d1bd72/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:innovation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/05/13/how-in-house-legal-teams-are-using-ai-to-cut-costs-and-win-budget-approval/">
    <title>How In-House Legal Teams Are Using AI to Cut Costs and Win Budget Approval | Law.com</title>
    <dc:date>2026-06-17T14:34:36+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/05/13/how-in-house-legal-teams-are-using-ai-to-cut-costs-and-win-budget-approval/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[One area drawing significant attention was outside counsel billing review. Wilkinson said WSP used AI tools to identify law firm charges that violated outside counsel guidelines, including internal law firm communication costs hidden in invoice descriptions.

The company ultimately rejected roughly $300,000 in internal communication charges tied to three months of invoices from a U.K. law firm, she said.

“So the CFO right away was all for that,” Wilkinson said.

WSP has since expanded its AI oversight of outside counsel by requiring firms to disclose which AI tools they are using on company matters.

“Our new outside counsel guidelines just released in April, not only have two pages of AI guidelines, but they require a schedule to be submitted with all of the AI tools they’re using on our matters,” Wilkinson said.]]></description>
<dc:subject>ai clients pricing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:cb8a954aca0d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:clients"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:pricing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legalwritingjournal.org/article/68099-_law-student-professional-development-and-formation-bridging-law-school-student-and-employer-goals_-neil-w-hamilton-and-louis-d-bilionis-cambri">
    <title>Law Student Professional Development and Formation: Bridging Law School, Student, and Employer Goals, Neil W. Hamilton and Louis D. Bilionis (Cambridge University Press 2022), 167 Pages | Published in Legal Writing</title>
    <dc:date>2026-06-16T20:45:22+00:00</dc:date>
    <link>https://www.legalwritingjournal.org/article/68099-_law-student-professional-development-and-formation-bridging-law-school-student-and-employer-goals_-neil-w-hamilton-and-louis-d-bilionis-cambri</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Faculty teaching first-year lawyering skills classes, including legal research and writing,[1] have long been part of the conversation surrounding law students’ professional development and professional identity formation. This is not to conflate the professionalism skills that are often learning objectives in our classrooms with the deeper, long-term process of professional identity formation that every successful young lawyer must engage in thoughtfully.[2] However, our curricula have long offered deep and formative opportunities for socialization into the legal profession, from the simulations we devise reflective of law practice, to the direct feedback we provide on student performance, to the one-on-one mentoring relationships and space for reflection that are hallmarks of our courses. In addition, with ABA accreditors’ focus on assessment of institutional learning outcomes, many lawyering skills faculty have emerged as leaders at our institutions in efforts to define and assess school-wide learning goals, including those centering on professional skills and professional identity.

]]></description>
<dc:subject>identity formation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:d2810d9daaee/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:identity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:formation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law360.com/pulse/modern-lawyer/articles/2478166">
    <title>How Mentors Can Be Pivotal For Midcareer Attorneys - Law360 Pulse</title>
    <dc:date>2026-06-16T20:42:00+00:00</dc:date>
    <link>https://www.law360.com/pulse/modern-lawyer/articles/2478166</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[After associates kick off their training wheels and become established attorneys, some may be tempted to allow their mentor relationships to languish. But the need for trusted feedback doesn't lessen, executive coaches and recruiters tell Law360 Pulse.

In midcareer, concerns often evolve from worries such as how to deal with a demanding boss to more seasoned quandaries such as navigating the politics of a partnership or the responsibilities of managing other lawyers. Rather than having just one mentor, more experienced attorneys might best be served by consulting with several colleagues who may be particularly knowledgeable in different facets of a legal career, said Chelsea Thaxter, who works as an executive coach, professional development consultant and workshop facilitator.

Sometimes referred to as a personal board of directors, this diverse group can provide an attorney with varying perspectives, based on individual areas of strength. For example, there may be a mentor who has a great handle on dealing with office politics, but may not have as many illuminating insights on how to balance the needs of a job with raising a family, Thaxter said.

One mentor might always seem to be ahead of the curve when it comes to incorporating artificial intelligence into their workflow, or in anticipating where their practice is heading. Meanwhile, another seasoned attorney could serve the mentor role of providing career advice on whether to continue at a firm or seek a lateral move, she said.

"You need to look at the mentor and think about where you need help and what that person's skill set is," Thaxter said.

Christy Kuklinski, a partner at Balch & Bingham LLP whose practice focuses on securities and corporate work, says she gives and receives career advice through an informal network of lawyers at the firm.

She and her fellow attorneys — some more seasoned, some still associates — talk regularly about matters such as how to develop relationships with clients, how to maintain a healthy work-life balance, and how to prioritize work that they find meaningful.

Kuklinski also maintains a more formal mentor-mentee relationship with Debra Lewis, a partner at Balch & Bingham who began her legal career in the early 1980s. Lewis told Law360 Pulse earlier this year that after not having female mentors in her career, it's important for her to serve in that role for the next generation of female legal leaders.

Kuklinski says she cherishes having Lewis in her corner, in part because she can count on Lewis to provide guidance on matters she may not have even considered.

"Sometimes ... we need to have someone that will just tell you what you need to know," Kuklinski said.

If an attorney does not already have a relationship with a potential mentor, they can reach out to the person and invite them for a cup of coffee, said Nicole Kennedy, a principal with Principle Recruiting. Once they have followed through on any advice from that meeting, they should look to circle back and update the person on how things turned out, along with showing gratitude for their time and insights, she said.

"If they consistently do things like that, they're more likely to build that relationship so it can last and grow over time," Kennedy said.

And for those who may not have such a network available, or who might prefer to keep their professional development concerns private, another option is to hire a coach, said Gary Miles, founder of recruiting firm Miles Partner Placement.

While many midcareer attorneys lean on their fellow partners for advice on how to handle various legal matters, some may look to a coach to address a particular professional need, he said.

"Some people just need to feel that they have someone behind them, who's on their side, so they hire a coach," Miles said. "I've known very successful partners who really didn't need any help, but felt that having one made them feel empowered."

Recruiters can also be part of the network of mentors that an attorney cultivates, as they can provide honest advice to an attorney on where they stand in the industry and what they may need to do to achieve a particular career goal, Kennedy said.

Lawyers should be cognizant that as the mentee, they should look to be proactive in the relationship and share their questions and concerns, as opposed to waiting for the mentor to guess what they may need, Kennedy said.

"They really have to be self-motivated about their own professional development," Kennedy said. "It's so important for a mentee to be consistent, because consistency is what strengthens that relationship long term."

Depending on the relationship an attorney has with a mentor, that more senior individual can also serve as the lawyer's personal champion or sponsor at the firm, Thaxter said. The mentor may have insights into opportunities that develop at the firm, and look to steer their mentee into roles they would be a good fit for, she said.

"It's really important for them to identify people who can help them on that path internally, because you're not going to make it unless you have strong internal supporters ... who understand very clearly what you need to do in order to get promoted," Thaxter said.]]></description>
<dc:subject>mentoring</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:50e72f530068/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:mentoring"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.ft.com/content/2205e2d0-50dc-4e80-9bf7-78d0272276c0?shareType=nongift&amp;syn-25a6b1a6=1">
    <title>What if remote working, not AI, is to blame for weak junior hiring?</title>
    <dc:date>2026-06-16T20:40:31+00:00</dc:date>
    <link>https://www.ft.com/content/2205e2d0-50dc-4e80-9bf7-78d0272276c0?shareType=nongift&amp;syn-25a6b1a6=1</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Nobody would argue these are shifts we should reverse, but the new data underscores a recurring result from remote work research — that what benefits mid- or late-career workers can harm the youngest.

They also help explain an under-appreciated nuance to the story: contrary to the stereotype of boomers demanding that Gen Z return to the office, it is the youngest generation who is most opposed to fully remote roles and keen for their colleagues to spend more time in the office.


The rise of working from home has been a boon for thirtysomethings (such as myself) who are safely on the career conveyor belt and often juggling work with parenting. But it has hit the youngest workers twice: slowing their climb up the career ladder and now perhaps keeping some out of the labour market entirely. Demands for a return to five days in the office are a step too far — the evidence consistently shows hybrid arrangements get the best results — but next time you hear calls for an extra day in person, bear in mind the biggest beneficiaries won’t be the bosses, they’ll be the juniors.]]></description>
<dc:subject>remote ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:6fb89d7e9919/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:remote"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/06/01/law-firms-are-using-ai-as-strategy-tool-not-for-reliable-forecasts-of-litigation-outcomes/">
    <title>Law Firms Are Using AI as Strategy Tool, Not for Reliable Forecasts of Litigation Outcomes | Law.com</title>
    <dc:date>2026-06-16T20:36:19+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/06/01/law-firms-are-using-ai-as-strategy-tool-not-for-reliable-forecasts-of-litigation-outcomes/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[The majority of law firm leaders with an eye on AI tools view them as at least somewhat reliable in predicting how cases might turn out, but they're generally not treating large language models as a crystal ball that can calculate the likelihood of winning or losing a case outright.

Instead, attorneys are more often using the predictive functions of AI to corroborate or identify potential holes in their thinking about litigation strategy.

As part of a recent report from Law.com Compass' Pacesetter Research, AI and innovation leaders from 300 U.S.-based law firms were surveyed in the first quarter of 2026. When asked whether they felt AI could accurately predict the results of legal cases, 62% of those surveys said yes, but with some limitations. Another 17% said AI tools are not accurate enough to make those types of predictions accurately, and the remaining 21% said they were unsure.

None of those surveyed said they thought AI could predict the outcome of cases with high accuracy. The survey found AI is perceived as useful for spotting risk and providing support for specific scenarios, but most of the respondents—40% of whom said they were worried about bias in algorithms—didn't see its as reliable enough to make high stakes predictions without human judgment and guardrails.

What makes AI useful for predicting litigation outcomes, said Quinn Emanuel Urquhart & Sullivan partner Patrick Curran, is when it's being used by experienced litigators. For instance, while large language models might not be particularly accurate if asked flat out what a judge will ask during argument, he said, a litigator who's able to input several elements of a case they expect the court to address will have more success.

"We start to get some pretty accurate examples—sometimes eerily accurate examples—of what the judges will ask," Curran said. "When we combine the experience and the judgment and the intuition of experienced litigators with these tools, then I think that marriage can generate some really exciting results. Just on their own, you don't get the same results."

Loren Brown, global vice chair and head of disputes at DLA Piper, said his firm is using AI to make predictions in several ways. One strategy is using data, mostly in proprietary tools, to predict risk to give clients a chance to fix issues, like those involving compliance or product liability, before litigation arises.

"We're using these tools to dive into data sets and do risk assessments that we've been doing for a very long time, but we're able to penetrate data sets in much more cost effective ways, because otherwise it would be millions of dollars, like what discovery costs," Brown said. "Those are predictive in the sense that we're identifying risks before they become problems."

Another practice involves using commercially available tools to analyze data sets on settlements, trial outcomes or motions rulings. Brown said DLA Piper uses those types of benchmarking tools to figure out where a case might fit in by comparison, but the commercial value of predictive tools that assign scores based on the chance of winning or losing a case isn't clear so far, and those may currently be of less use to law firms than to those in the litigation financing world who are making decisions about which cases to invest in.

At Quinn Emanuel, attorneys are using large language models to "gut check" their instincts about litigation strategy against outcomes in cases that involved comparable issues or the same judges, Curran said. But the firm—which primarily uses Anthropic's Claude, both on its own and as a way of developing proprietary AI solutions and agents—has AI usage policies aimed at ensuring everything from legal citations to strategy decisions remains rooted in human judgment.

"I don't think we've yet seen any indication that, given the high stakes of litigation, any of our clients want to be handing over the decision making reins to a large language model, but I do think more and more clients will want to know that their experienced litigators are using those sorts of tools to sharpen and pressure test their thinking," Curran said.

Currently, Brown said, the value of the commercially available tools that can be used for predicting litigation outcomes is in the data sets behind them, and law firms have a chance to harness their proprietary data or scrape publicly available date sets to create internal tools of their own that will better serve their clients.

"I use my collective experience to advise clients," Brown said. "Now we can actually harness that internally, and we're working on every day on better harnessing our internal data so that we can eventually have an enterprise solution and really unlock the value of our scale with all the data that we have."]]></description>
<dc:subject>ai litigation prediction firms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:6d4dd3c49a22/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:litigation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:firms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law360.com/pulse/modern-lawyer/articles/2484325?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0">
    <title>BigLaw Could Tap PE Money For Advantage In Talent Wars - Law360 Pulse</title>
    <dc:date>2026-06-16T20:24:34+00:00</dc:date>
    <link>https://www.law360.com/pulse/modern-lawyer/articles/2484325?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[BigLaw firms may soon partner with private equity to gain an edge in the talent wars, potentially reshaping the U.S. legal industry despite fears that the shift could corrode firms' cultures.

As private equity money pours into segments of the U.S. legal industry, such as personal injury, immigration and insurance defense via managed services organization deals, BigLaw firms have thus far sat on the sidelines.

Many market watchers now think the talent wars could soon push BigLaw to take the plunge, as well.

For years, top-tier law firms have been embroiled in a cutthroat competition for market share and top talent that has now resulted in rainmakers being paid like star athletes, with even the most venerable firms susceptible to being raided by their peers.

Restructuring as an MSO would give BigLaw firms the ability to dole out true equity shares as incentives, the same way every other type of business is able to, potentially providing them with a leg up over competitors.

"For AmLaw 200 firms, the investment thesis is access to capital, and the first, second and third top uses of that capital is going to be competing for talent on the lateral market," said Joshua Porte, a Holland & Knight LLP attorney who, along with his colleague Trisha Rich, is one of the leading MSO deal attorneys in the U.S.

Many BigLaw leaders are hesitant, however, fearing that a total overhaul of their firm's structure might do more harm than good.

"I worry about the effect a deal like this could have on our culture," said Scott A. Meyers, chair and CEO of Akerman LLP.

"For any large law firm, all it takes is something that drives a few rainmakers to leave, and the firm can be pushed into the classic death spiral," he added.

Despite the skepticism from some, talk to almost any consultant, transactional attorney or investment banker currently involved in MSO deals, and they'll tell you that every single BigLaw firm is at least taking a close look at the phenomenon. A handful, they say, are already deep into negotiations and could close deals by Q1 2027.

"It's going to happen," Rich said. "It's a matter of when, not if."

A Life-Changing Proposition

Most managed services organization deals entail splitting off a firm's back-office operations into a separate entity — the MSO — which does not practice law and is therefore not subject to Rule 5.4 of the American Bar Association Model Rules of Professional Conduct, which prohibits fee-sharing between lawyers and non-lawyers.

The MSO then charges the law firm a fee for handling functions such as cybersecurity, billing and human resources. Outside investors can purchase equity in the MSO, keeping them on the right side of Rule 5.4 while giving them "exposure to the law firm's economics," to use the careful phrasing of industry practitioners.

Thus far, MSO deals in the U.S. legal industry have primarily involved private equity investors pursuing the classic "buy and build" strategy, which entails partnering with a platform law firm, investing in technology and branding, purchasing other firms and then benefiting from economies of scale.

For the owners of those firms, the MSO deal is mostly a way to cash out the unrealized value of the business they've built over the years through a lump-sum payment.

Flowchart with connected boxes, arrows, and highlighted callout boxes illustrating relationships between investors, equity partners, a service company, and a law firm.



"In consumer-facing practices, the investment thesis and the value proposition are very straightforward," Porte said.

BigLaw firms are different. For starters, leadership needs to convince dozens, if not hundreds, of equity partners that restructuring as an MSO is in the best interest of both them and the firm.

There's also the hesitation and inertia that comes from the fact that no BigLaw firm has successfully pulled it off yet.

To pay for the MSO's services, every equity partner might need to take something like a 5% or 10% haircut on their annual distribution. In exchange, the firm would receive an upfront payment and the ability to hand out shares in the MSO to partners.

Those shares would function like stock in any other type of company, and could be bought, sold and valued at a multiple by outside investors.

"In the partnership model, one dollar is one dollar," said David Morley, the former head of legacy firm Allen & Overy LLP, who now guides outside investment in law firms. "With true equity, one dollar can be multiplied 10, 20, 30 times. That's what most partners don't fully appreciate yet."

By restructuring as an MSO, the thinking goes, firms could use traditional corporate incentive structures to mirror the cultural bonds and defined benefit pension plans that once bound partners to their firms for life.

"Right now, when I retire, I get my capital contribution back with a 0% return, and that's it," Porte said. "That's a very different proposition to being able to sell your shares in an MSO at a multiple. Potentially life-changingly different."

BigLaw firms could use those same tools to reshape their business model and bring on tech and management experts, continuing the trend toward the professionalization of the business of law that's been underway for the past 30 years.

"The reality is that the partnership structure is increasingly outmoded in today's competitive landscape," said Travis Lenkner, chief operating officer at Burford Capital, the world's largest litigation funder.

The same incentives could also help firms get all their partners working toward the common good of the firm, something that's difficult in today's era of top rainmakers pulling down eight-figure annual salaries.

"Today, if you're a partner with a significant practice, yes, you want the firm to succeed, because you want to operate on a leading platform," Lenkner said. "But your primary incentive is to market yourself to the client as the product. The firm is secondary."

"That is not the way to long-term value creation," he added.

Some consultants, meanwhile, think private equity investments could provide BigLaw firms with a massive war chest to invest in AI technology.

However, Meyers and many others are skeptical.

"We're big believers in the power of AI," he said. "But we pay for it like any other investment. Even if we didn't want to dip into our cash reserves for some reason, there's lots of other options that don't involve giving away equity in the firm."

Kirkland & Ellis LLP, for instance, said last week that it plans to spend $500 million over the next few years developing a proprietary artifical intelligence platform and will divert a portion of its annual profit disbursements to pay for it.

Persistent Fears

Robert Conrad, a managing director at recruiter Major Lindsey & Africa, says some BigLaw leaders aren't convinced that the risks of restructuring as an MSO and partnering with outside capital is worth it.

During a recent dinner with the managing partner of a BigLaw firm, "He said there's no way he would take outside capital," Conrad said. "He thought it would be disastrous for the culture of the firm and, in the long run, detrimental to the entire industry."

Several dozen BigLaw firms declined invitations to speak on the record for this article, but many consultants and attorneys said those sorts of fears are commonplace.

"In general, there's a concern that private equity firms are going to be far more interested in profits than the interests of the clients," Conrad said. "The other concern is losing the autonomy lawyers enjoy in the partnership structure; the specter that partners will be relegated to being salaried employees."

Mike McNamara, CEO of legal growth consultancy Baretz & Brunelle and the former CEO of Dentons US, is bullish on BigLaw MSO deals, but concedes that managing partners will have their work cut out in selling the idea to partners.

"Law firm partners love what they do because of the independence," McNamara said. "You can curate client relationships, grow your own businesses and work with like-minded partners. It's really unique among professional services firms."

To convince reluctant partners, some analysts think an MSO might need to be structured as a minority deal in which an outside investor purchases something closer to a 30% stake of the equity in the MSO, rather than the 51% or more that some private equity firms are said to be pitching to BigLaw leaders.

That minority arrangement would keep decision-making power out of the hands of private equity and thus might assuage wary partners.

Burford has been actively courting minority investments in MSO deals with BigLaw firms in the U.S. since late last year.

"The more equity you give up in the MSO, the harder it becomes to get it across the finish line," Porte said. "The deal needs to be structured in such a way that the go forward enterprise is flexible enough to accommodate the hopes and dreams of the young lawyers who are the future of the firm."

Meyers said it doesn't seem like a good fit for Akerman, though.

"When I sat down and crunched the numbers, I couldn't get it to work," Meyers said. "You can use any multiple you want to get whatever answer you want. But the higher you go, the more you're relying on assumptions and guesswork."]]></description>
<dc:subject>privateequity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:0ef4a5d73055/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legalfutures.co.uk/latest-news/the-clock-is-ticking-pe-investment-in-law-down-but-deal-volume-up">
    <title>&quot;The clock is ticking&quot;: PE investment in law down but deal volume up - Legal Futures</title>
    <dc:date>2026-06-16T20:08:22+00:00</dc:date>
    <link>https://www.legalfutures.co.uk/latest-news/the-clock-is-ticking-pe-investment-in-law-down-but-deal-volume-up</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Private equity (PE) invested an estimated £250m into UK law firms last year and around £80m so far this – compared to the record £534m of 2024 – but deal volume is up sharply, according to new research.

]]></description>
<dc:subject>privateequity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:1197b48fd67d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://nationalmagazine.ca/en-ca/articles/opinion/2026/ai-tools-for-case-law-research-keep-getting-better">
    <title>National - AI tools for case law research keep getting better</title>
    <dc:date>2026-06-16T20:08:11+00:00</dc:date>
    <link>https://nationalmagazine.ca/en-ca/articles/opinion/2026/ai-tools-for-case-law-research-keep-getting-better</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Rather than bolting AI onto a search portal, A2AJ brings its database to the AI platform you’re already using. It has no daily use limits. It generates more comprehensive summaries that you can dialogue with. And it’s faster and more reliable than Westlaw’s Edge or LexisNexis’ Protégé, which cost a few hundred dollars a month and are often inaccurate, on top of being slow and clunky to use.

A2AJ’s free connector lets you search their open-source dataset of Canadian court cases, statutes, and regulations. So far, coverage is extensive but not complete. It includes all Supreme Court of Canada decisions from 1877, all Federal Court cases for the past 25 years, and much of British Columbia, Nova Scotia, and the Ontario Court of Appeal. Big gaps remain, but A2AJ is working to fill them.

]]></description>
<dc:subject>access ai research</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:31dd98113492/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:access"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:research"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/06/08/why-3-attorneys-left-goodwin-to-start-an-ai-native-ip-firm/">
    <title>Why 3 Attorneys Left Goodwin to Start an ‘AI-Native’ IP Firm | Law.com</title>
    <dc:date>2026-06-16T19:47:31+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/06/08/why-3-attorneys-left-goodwin-to-start-an-ai-native-ip-firm/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Rapid improvements in generative artificial intelligence tools have prompted the emergence of a new class of AI-native law firm, but the boundaries and possibilities of the category are still coming into view.

While many such firms are focused on commercial contracting, Antheros, a San Francisco-based law firm founded in 2025, aims to use the AI-forward approach to provide a full suite of transactional intellectual property services to startups and emerging companies in life sciences industries.

Antheros was founded by partners Sabrina Poulos, Kristin Havranek and Stephanie Dusaban Gonzales, all three of whom departed from Goodwin Procter’s IP group to start the new firm. Poulos and Havranek were partners at Goodwin and Gonzales was as associate. The three also previously worked at Wilson Sonsini Goodrich & Rosati, where Poulos—now serving as Antheros’s managing partner—held a partnership.

In addition to the three founding partners, Antheros’s staff of roughly a dozen also includes associates, patent agents and other professionals.

Why AI-Native Makes Sense for IP
Poulos and Havranek told Law.com the combination of relatively routine work and higher-level strategic thinking required in IP practice makes the area a strong fit for an AI-native approach. The use of AI allows the firm to get through more routine tasks, such as drafting portions of applications, more efficiently, allowing its attorneys to devote more time to counseling clients on broader portfolio management decisions.

“There's a lot of high-level thinking, but there's also a lot of rote work in drafting up the specs and doing a lot of the prosecution,” Poulos said. “AI lets us compress that, ... and that gives us the space, the freedom and the time to really sit there and think strategically about the client's portfolio.”

This ability to automate some of the more routinized work also impacts how the law firm works as a business, including what it looks for in recruiting and how it brings in revenue.

“At the outset we designed every workflow with AI in mind,” Poulos added. “We said, ‘Here is the workflow. How can we build this with AI as the base, and how can we design our hiring with that in mind, how can we design our fee structure with that in mind?’”

The nature of IP practice and the type of attorney drawn to it made the adoption of an AI-native model easier. Antheros’s founders all have technical backgrounds—Poulos worked in pharmaceutical research prior to becoming an attorney, Havranek was previously an engineer for medical device companies, and Gonzales has a Ph.D. in biomedical sciences.

“Scientists are inherently inquisitive, and especially scientists who become patent attorneys, because they ... want to learn about new technologies, want to get into the weeds about new technologies,” Havranek said.

Building Workflows
To do its work, Antheros draws on enterprise AI software from providers including Harvey, LexisNexis and AnkarAI, which the firm uses to build bespoke workflows for the discrete tasks that make up IP practice including gap analysis, patent prosecution and communication with regulators like the U.S. Patent and Trademark Office.

The firm operates an AI work team that conducts weekly meetings to determine which tools work best for which tasks, and to make sure its workflows are making good use of its tools as their capabilities change over time.

“We know the basic buckets of everything we do within our practice and have mapped what we think are the best tools to use in those instances,” Havranek said. “If something's more scientific, we might use a different tool than something that we are going to try to have some legal conclusions to, or an office action response might be best using a different tool than a drafting or a freedom to operate evaluation.”

While the substantial use of AI can accelerate some tasks, the founders stressed that its attorneys review all work product and noted that substantial elements of IP practice require human expertise, particularly in highly technical areas.

“I don't think that at this stage AI can really substitute for human strategic thinking, and honestly, the depth of knowledge that you have to have when you're doing life sciences IP work, it is really complicated," Poulos said. “I don't think clients would get a particularly good work product if we just fed in or let them feed in their invention disclosure into AI.”

Billing and Business Model
Among the reasons the founders decided to start their own firm was the ability to adopt new pricing models. While the firm offers an hourly rate for clients that would prefer to be billed on time spent on a matter, it also provides subscription-based pricing and flat fee services.

Poulos noted that largely avoiding the billable hour model allows the firm to get around some of the misaligned incentives that can make AI adoption challenging at more traditionally structured firms.

Not having a billable hour requirement “lets us be efficient in our client work, but it also gives everybody space to do business development, to do knowledge management, and to take a look at new and interesting tools,” Poulos said. “We don't have to sacrifice training, we don't have to sacrifice knowledge management, because we are trying to meet an arbitrary hourly requirement.”

Havranek cited gap analysis as an example of a workflow that benefits clients but could have been hard to automate with hourly billing, given the substantial amount of time required to build an AI workflow for the task and the minimal time required to run it.

“We actually can use AI to evaluate unclaimed subject matter across an entire portfolio, every family, every pending claim,” she said. “The client gets portfolio-wide advice that can be instantaneous, practically, ... and they don't have to have a separate engagement or a separate project that’s a billable hour [figure] that they have to pay for.”

"There's a structural tension between the billable hour and the new speed and ability that AI gives us,” she added. "We built it into our law firm from the get-go, and we're not trying to adapt an 80-year-old structure or workflow with new tools.”

]]></description>
<dc:subject>ai-first ip pricing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:bb5fe8befb42/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai-first"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ip"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:pricing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law360.com/pulse/modern-lawyer/articles/2488217?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0">
    <title>Bill Targeting PE In Legal Sector Marks New Ethics Territory - Law360 Pulse</title>
    <dc:date>2026-06-16T19:36:45+00:00</dc:date>
    <link>https://www.law360.com/pulse/modern-lawyer/articles/2488217?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[State lawmakers are stepping up efforts to restrict private equity investment in the legal sector, with a pending bill in Illinois representing the first attempt that goes beyond codifying existing ethics rules. But industry observers say the measure, passed in May and awaiting possible signature, could make firms less attractive to investors and might disrupt relationships with vendors.

Last week, Colorado became the first state to enact a law that directly addresses the use of managed service organizations in the legal industry, an increasingly popular structure that enables firms to take outside investments without running afoul of ethics rules governing nonattorney ownership of firms.

While the Illinois bill would go much further than Colorado's in restricting MSOs and putting up private equity speed bumps, industry observers say it's unlikely to stop the practice entirely.

"I think the gist of it is that this is not going to prohibit MSOs in Illinois," said Lev Breydo, an assistant professor at William & Mary Law School. "It's still a viable model, but there's just a lot more constraints."

The legislation in Colorado and Illinois are among a number of state measures seeking to rein in the role of nonlawyers in the legal profession. Those efforts have included a California law and a South Carolina ethics opinion that both forbid splitting fees with firms that have nonlawyer owners, such as the alternative business structures allowed in Arizona. The Colorado and Illinois bills include similar provisions.

But the Colorado and Illinois measures stand out for the attention paid to MSOs, which opponents of the practice say should be curbed to preserve lawyer independence and protect the public.

Under what MSO proponents describe as a properly structured MSO deal, a law firm spins off its back-office functions, such as financial management, into a separate legal entity, which does not practice law and thus can take investment. The MSO then provides back-office services to the law firm for a fee, which proponents say complies with ethics rules so long as the fee is a fair rate and not a percentage of firm revenue.

In Colorado, Gov. Jared Polis on Thursday signed into law the bipartisan HB26-1421, while the Illinois measure, H.B. 5487, passed that state's legislature on May 31.

The Colorado law says an MSO cannot be paid as a percentage of revenue or fees, which Eli Wald of the University of Denver's Sturm College of Law said is already covered by state ethics rules.

The Illinois bill goes further in targeting MSOs, which it defines as an entity that "provides management and administrative support services in exchange for ownership of a law firm's assets or payments." Parts of the language mirror Illinois' version of ethics rule 5.4, which focuses on the professional independence of attorneys and prevents fee-sharing with nonlawyers.

However, the law also goes beyond the ethics rules by explicitly forbidding MSOs from accessing client records or hiring or firing "allied legal staff" such as paralegals. Violations may result in an attorney being referred to the state bar for discipline and fines of up to $10,000 per violation or treble any client damages, whichever is greater.

Bruce Pfaff, a member of the Illinois Trial Lawyers Association who helped draft the legislation, said the goal of the bill was to protect the independence of attorneys and prevent a pattern seen in industries like healthcare, where research has found private equity involvement correlates with increased prices, higher turnover and, in some contexts, worse patient outcomes.

"The [Illinois personal injury] marketplace is very healthy," Pfaff said. "We have a lot of competition among lawyers for clients and cases and a lot of very healthy, brilliant small law firms. The aggregation that always comes with private equity is not good for competition and not good for clients."

Jay Hoffman, a state representative who signed on as a co-sponsor after the bill's introduction, likewise said that he worried these types of relationships would threaten attorney independence.

After its introduction, the bill was amended in the state Senate to carve out firms with more than $300 million in annual revenue. Hoffman, who is in the House, said he was not aware of why the Senate added the provision.

One of the largest law firms to publicly express interest in an MSO deal — McDermott Will & Schulte, which has more than $2 billion in revenue — is headquartered in Chicago.

Trisha Rich, a legal ethics attorney with Holland & Knight LLP who has worked on MSO deals, said that if it becomes law, the Illinois bill will not stop "properly compliant" MSOs but may interfere with relationships with other vendors, especially those that provide document review services, which may run afoul of the bill's language on handling client records.

"I understand what they're trying to do, but the bill doesn't accomplish that," she said. "I'm setting up two or three [MSOs in Illinois] right now. This is not going to stop investments in Illinois law firms ... but it will target a lot of vendor relationships."

When asked, Pfaff said he sees the key distinction between a private equity-owned MSO and a more normal vendor relationship as the fact that it is much harder for a firm to cut ties with an MSO, as opposed to its ability to shop around for services from other vendors. He acknowledged the bill does not make an effort to regulate exclusive vendor relationships.

Breydo of William & Mary Law School, who has written about the "governance gap" surrounding law firm MSOs, also said this bill would not prevent MSOs outright. However, he added, there are some things in the bill that may interfere with the usual private equity playbook, in particular the restrictions around hiring allied legal staff.

"Fee restrictions can be engineered around, and most deals already do," he said. "The bite is in control: staffing, productivity parameters, info access. ... Those are the levers to accelerate a firm's growth and to course-correct when a deal drifts."

If a private equity firm doesn't have control over staffing, he said, that makes it harder to hit the returns that investors expect. While the bill is unlikely to make it impossible to stand up an MSO in Illinois, he said, it could make it less attractive from a business perspective, pushing investors to other states.

Breydo said he sees the Illinois bill as part of a bigger pushback against outside capital in the legal industry, pointing to the Colorado bill and the response to alternative business structures in California and other states. The details of the attempts to regulate, though, will be key, he said.]]></description>
<dc:subject>privateequity ethics regulation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:66637412e74a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ethics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:regulation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/06/09/better-than-tar-nearly-expert-what-a-major-study-shows-about-gen-ai-and-tar-in-a-complex-document-review/">
    <title>Better Than TAR. Nearly Expert: What a Major Study Shows About Gen AI and TAR in a Complex Document Review | Law.com</title>
    <dc:date>2026-06-16T19:36:08+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/06/09/better-than-tar-nearly-expert-what-a-major-study-shows-about-gen-ai-and-tar-in-a-complex-document-review/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[We recently conducted an empirical study examining this question on an intentionally complex document review. We conducted a managed TAR review using relativity active learning (RAL), a continuous active learning tool that uses reviewer coding decisions to help prioritize likely responsive documents, supported by a 24-person review team provided by Cimplifi, a managed review vendor. In all, this workflow required 1,123 hours of human effort. Separately, we developed and ran a gen AI workflow using Relativity aiR for Review, a gen AI tool powered by a large language model (LLM) that uses a natural-language prompt to classify documents and explain its reasoning. In all, this workflow required just 18 hours of human effort. After both reviews were complete, an independent subject-matter expert (SME) performed a blinded random sample review to support an impartial comparison of results.

The results were striking. aiR for Review found substantially more responsive documents and missed fewer than the active learning workflow. The tradeoff was modest: aiR for Review identified more documents as potentially responsive, but a lower proportion of those documents ultimately proved to be responsive compared to RAL. Separately, when the SME later reviewed aiR for Review’s reasoning for certain documents he had initially coded not responsive, he changed 7% of those calls to responsive. Those overturns came after the blinded comparison and were not counted toward the reported metrics, but they suggest aiR for Review’s finer-grained judgment can help even an expert reviewer find more responsive documents.]]></description>
<dc:subject>e-discovery ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:8d8cba1d1f73/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:e-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://abovethelaw.com/2026/06/trouble-for-midsize-law-firms-is-the-titanic-sinking/">
    <title>Trouble For Midsize Law Firms: Is The Titanic Sinking? - Above the Law</title>
    <dc:date>2026-06-16T19:31:37+00:00</dc:date>
    <link>https://abovethelaw.com/2026/06/trouble-for-midsize-law-firms-is-the-titanic-sinking/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Turbulent Times For Middies

The report, published May 26, 2026, has three main findings:

Midsize rate growth in the first quarter and in 2025 was significantly less than the rate growth at Am Law 100 and 200 firms.
Midsize firms had the least growth in technology and knowledge management investment than not just Am Law 100 and 200 firms but of any segment.
Midsize firms have a low investment in recruiting expenses and are virtually absent from the lateral market.
According to the report, not only is the midsize rate growth modest, their expense growth rate was also the highest of any segment.

]]></description>
<dc:subject>midsize firms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:641f092e21b9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:midsize"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:firms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.ft.com/content/47f4d549-4560-4830-bf55-47774a9057bc?shareType=nongift">
    <title>‘Can a machine do this job?’ is the wrong question</title>
    <dc:date>2026-06-16T19:18:22+00:00</dc:date>
    <link>https://www.ft.com/content/47f4d549-4560-4830-bf55-47774a9057bc?shareType=nongift</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[
Please use the sharing tools found via the share button at the top or side of articles. Copying articles to share with others is a breach of FT.com T&Cs and Copyright Policy. Email licensing@ft.com to buy additional rights. Subscribers may share up to 10 or 20 articles per month using the gift article service. More information can be found at https://help.ft.com/faq/gifting-and-sharing-an-article/what-is-a-gift-article/.
https://www.ft.com/content/47f4d549-4560-4830-bf55-47774a9057bc?shareType=nongift

The writer is author of ‘How Progress Ends: Technology, Innovation, and the Fate of Nations’ and an associate professor at Oxford university 

Whenever AI automation anxiety arises, optimists like to point to the bank teller. US vice-president JD Vance repeated the idea last year: ATMs automated the teller’s core task and yet teller employment rose for three decades. The implicit assumption is that if automation could not kill the teller, surely AI will not kill the accountant.

As economics writer David Oks has noted, this reassurance is premature. Once customers could deposit a cheque by photographing it and send money without visiting a branch, the teller was replaced — not by a better machine in the bank but by the customer outside it.

The distinction matters, and it turns on a mechanism economists have understood since the 19th century. When a technology automates tasks inside an existing service, it can trigger a Jevons paradox: the service becomes cheaper, demand expands, and employment grows. That is what ATMs did and it is the reason automation has so often failed to produce mass unemployment.

But the paradox has a condition: it works only when the technology makes the existing service model more efficient. When a technology lets people do the work themselves, demand for the service collapses.

The sociologist Jonathan Gershuny identified this pattern in 1978. Modern economies, he argued, were not heading towards a service utopia but a self-service economy in which households would absorb the work themselves. The washing machine illustrates this: it did not automate the laundress’s job — it gave customers the means to do without her.

The pattern has been repeating ever since. Self-checkout handed scanning and bagging to the shopper. The internet gave travellers direct access to flight schedules and hotel reviews that agents once controlled. Online brokerages put a trading terminal in every pocket.

AI extends this mechanism even to the manual trades, the supposed safe haven of the AI age. If a homeowner can ask a chatbot why their boiler is losing pressure, heating engineers may lose call-outs. Nor are professions immune: doctors may find patients have decoded test results before they arrive.

This solves a problem for companies in the process. As Christian Catalini, founder of the MIT Cryptoeconomics Lab, and collaborators have argued, when AI pushes the cost of execution towards zero, the binding constraint becomes human verification — our limited capacity to validate outcomes and take responsibility. Self-service offloads that burden on to the customer.

This shift has broader macroeconomic implications. When work shifts to the consumer, it vanishes from the economy that statisticians measure. A company that replaces a billing department with a chatbot interface records lower costs and higher output per worker. The national accounts register a productivity gain. But the hours that patients spend decoding their own tests appear nowhere — not in labour statistics, not in GDP. As AI self-service expands into professional domains, this blind spot will grow.

Policymakers who rely on those indicators to judge whether AI is delivering benefits may be missing a deeper shift. The great achievement of modern capitalism was to move activity from the household into the market — converting domestic production into paid specialisation, creating jobs and making output visible to the national accounts. AI-enabled self-service is quietly reversing that centuries-long trend.


The automation question — can a machine do this job? — would never have predicted the laundress’s decline. No robot could walk to the well and handwash linens. But the washing machine did not need to. The self-service question — can the customer do without this job? — would have predicted it. If we keep asking the first question about AI, we will keep looking in the wrong place.

]]></description>
<dc:subject>ai future</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:988c9c803d41/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:future"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/06/15/what-can-big-law-learn-from-the-rise-of-ai-native-law-firms/">
    <title>What Can Big Law Learn From the Rise of AI-Native Law Firms? | Law.com</title>
    <dc:date>2026-06-16T19:15:49+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/06/15/what-can-big-law-learn-from-the-rise-of-ai-native-law-firms/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[For Javed Qardud-Din, co-founder of AI-native firm General Legal and a former associate at Fenwick & West, the financial success enjoyed by large firm partnerships may hold them back from adopting large elements of the AI-native model, which generally involves alternative billing arrangements.“It's very difficult for them to lower their prices in the short term so that hopefully they get more clients in the long term. It's very difficult for them to get off the billable hour,” he said. “The reason it's difficult is that the partners are taking the profits off the table every year, ... so if you ask them to take a huge pay cut in one year or a few years, that's a very difficult proposition.”

Another major impediment to large firms emulating AI-native firms is the very scope of service Big Law often seeks to provide. AI-native firms to date tend to concentrate in a single practice area, often contracting, and they focus on legal work particularly well suitedto AI-powered automation. Large law firms, conversely, tend to handle a broader array of matter types that involve harder-to-automate areas such as litigation.

Client comfort is also likely to limit the degree to which large firms would want to resemble their new counterparts. AI-native firms often explicitly target small, growth-stage companies, in part because their legal needs can be simpler. New founders, particularly in tech and adjacent industries, are also often more willing to experiment with novel technology and the new business models it enables.

Conversely, Big Law often serves large and complicated enterprises that take widely varying approaches to AI in outside counsel guidelines. While some clients actively push outside counsel to speed up their adoption of AI, others continue to limit its use, making it challenging for firms to impose an across-the-board approach to how AI is used on any given task.

Logan Brown, a former Cooley associate who founded AI-native firm Soxton, said her firm’s clients are sometimes small and new enough that they are more likely to go without representation than to work with a larger firm.

“I view my competition as the [large language] models rather than existing law firms,” she said. "We're pricing ourselves and we're really thinking about being a solution that allows folks to get a qualified attorney's advice rather than just relying on Claude.”

Where Big Law Can Catch Up

But not everything about large firms' structures is ill suited for widespread AI deployment along the lines of AI-native firms. In some ways, their structure can actually provide an advantage. Large law firms have a vastly greater array of internal workflows that can be remade with AI, with the potential to achieve major efficiency gains or take on new types of work.
Goodwin Procter chief technology officer Eric Tan previously told Law.com that one of his aims is “moving Goodwin from a technology-enabled law firm into an AI-native firm.” He said this process is not limited to front office service delivery roles and noted that the firm’s legal operations teams can also rebuild workflows around AI or use new tools to take on work they had not previously done.

Tan cited the example of Goodwin’s security team, which built an AI agent to assess the firm’s access logs for vulnerabilities, as an example of a team taking an AI-native approach to enable work it could not have done previously.

For larger firms, the question may be less one of becoming an AI-native firm than introducing AI-native workflows when and where it makes sense.

Helen Fan, founder of legal AI consultancy Helen’s Legal AI Lab and chief AI officer at MagStone Law, said the ability of larger firms to emulate AI-native firms is less a matter of “yes” or “no” than a case-by-case decision within firms. Practices that have already embraced some of the hallmarks of AI-native firms, such as value-based pricing, will likely have stronger incentives to adopt tools that can speed up their work.

“For many law firms, which have the clients [from] private equity or private funds, they already have the value-based billing system, ... so that's why they would like to do this,” she said.

“For many other big law firms, ... it's really hard to change, become value-based, because [they might work on] a very complicated legal issue, especially for financial regulatory problems. If the big law firms do some litigation or patent issues, ... maybe they don't have the reason to change it.”

This points to a broader reality that, so long as they are not losing business to AI-native firms, large firms may focus on procuring and developing AI tools to speed up or improve existing processes instead of reshaping them entirely.

“I don't know if the big law firms are set up [to become AI-native], but I'm sure that there's going to be things that they're able to do internally to keep up with their current clients' demands,” Brown said.

]]></description>
<dc:subject>ai-first pricing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:5000d5f5b55b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai-first"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:pricing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.ft.com/content/d368d0b8-9264-408b-b0af-0f0b660e1c8f?accessToken=zwAAAZ7Q4FyBkdPTaNC4kmRAi9Owrw8LZg4cjw.MEYCIQDFpZRufBPFDFFX8hlAIrI_zVkql94tKVaNKYHoHHof2wIhAPOafuOADKHmrBASca07SyukQaT7FUiOPa52tR3KRhvk&amp;sharetype=gift&amp;token=6eb7065d-19d1-423f-94c5-c66bd2282de5&amp;syn-25a6b1a6=1">
    <title>Private equity bosses warn of AI threat to bets on law and accountancy</title>
    <dc:date>2026-06-16T19:10:49+00:00</dc:date>
    <link>https://www.ft.com/content/d368d0b8-9264-408b-b0af-0f0b660e1c8f?accessToken=zwAAAZ7Q4FyBkdPTaNC4kmRAi9Owrw8LZg4cjw.MEYCIQDFpZRufBPFDFFX8hlAIrI_zVkql94tKVaNKYHoHHof2wIhAPOafuOADKHmrBASca07SyukQaT7FUiOPa52tR3KRhvk&amp;sharetype=gift&amp;token=6eb7065d-19d1-423f-94c5-c66bd2282de5&amp;syn-25a6b1a6=1</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Law and accountancy are among the businesses most vulnerable to AI disruption, top private capital executives have warned, adding to the worries of buyout groups that have invested heavily in professional services.


The rapid development of generative AI has already hit the valuations of software businesses but private equity and credit investors told the FT that asset-light advisory businesses that bill by the hour were also at serious risk.

“Software has dominated the headlines but AI goes so much further,” said Kevin Marchetti, chief investment officer and head of US direct lending at Man Group. “Claims auditing, billing automation, proxy voting management or legal services . . . you could really foresee how AI could impact them.”

Executives at the sector’s annual SuperReturn conference in Berlin said the technology could disrupt businesses across a swath of sectors backed by private equity groups, after software buyout deals collapsed this year over fears that new AI tools would undermine those companies’ business models. 

“Apologies to the lawyers, accountants, consultants in the room,” Apollo Global Management executive Scott Kleinman told SuperReturn delegates. “You’re going to see a lot of pressure.” 

Shares in Accenture, the world’s largest listed consultancy, have fallen by almost half in the past year, indicating the scale of investors’ fears that AI will damage professional services groups.

Executives said that private capital groups were starting to shun new investments in some professional services firms because of uncertainty over their long-term revenues and valuations.

“Few . . . are looking to invest in certain white-collar services companies undergoing a revolution in their business model and which are more exposed to AI displacement risk,” said Joana Rocha Scaff, head of European private equity at Neuberger Berman.

Scaff said groups performing writing, translation and legal services were particularly vulnerable. While AI offered efficiency and margin improvement, “there are also risks of revenue disruptions, especially if they charge by man hours”, she added.

Professional services groups that are not operating in regulated sectors are seen by some investors as particularly exposed to disruption by AI.

“We looked at bookkeeping businesses charging by the hour, which we felt were particularly exposed [as they did not do regulated audit work],” said Andrew Sillitoe, co-chief executive of Apax Partners. “On the other hand, the value of having your accounts signed off by an auditor is so much more than the sum of the person-hours taken to do it. Here, AI automation should be a tailwind.”

AI disruption of professional services groups threatens to dent returns for private equity firms that have poured billions of dollars into the sector in recent years, attracted by their low capital expenditure and the opportunity to roll up smaller groups.

Recommended

News in-depthManagement consulting
Will the IT consulting share price rout ever end?

Last year, a Blackstone-led group bought a majority stake in Citrin Cooperman from smaller buyout rival New Mountain Capital for more than $2bn. New Mountain and Cinven have also bought stakes in Grant Thornton’s US, UK and Germany arms.

Legal services groups have also been targets, with Inflexion taking UK law firm DWF private in 2023. In the US, buyout groups have also been developing corporate structures to allow them to back legal firms, which have traditionally operated as partnerships with little or no external investment.

Executives said they were increasingly focused on sectors such as industrials, where companies hold significant assets and have a low risk of being rendered obsolete by technology — dubbed the halo trade.

“It’s weird that the market only cares about software,” said a top credit executive at one of the biggest private capital groups. “AI could be valuable to accounting firms, but will small accounting roll-ups be able to compete with KPMG [in deploying AI]?”

Other buyout executives with investments in accounting groups said, however, that those that deployed AI well and adapted to new revenue models could benefit from the changes sweeping the sector.]]></description>
<dc:subject>privateequity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:e5e7034aef7f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legalfutures.co.uk/blog/firms-need-to-move-faster-on-ai-pricing">
    <title>Firms need to move faster on AI pricing - Legal Futures</title>
    <dc:date>2026-05-26T21:02:41+00:00</dc:date>
    <link>https://www.legalfutures.co.uk/blog/firms-need-to-move-faster-on-ai-pricing</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Value-based pricing sounds great in theory, but firms need a clear way to articulate and measure value if they want clients to buy into it. And hybrid models, which I suspect many firms will naturally move towards, are operationally much harder to manage than many people realise.

This is why I keep coming back to the same point with firms: AI pricing is no longer just a pricing conversation. It is an operational one.

You cannot manage this well through spreadsheets, disconnected systems and instinct alone. Firms need better matter data. Better visibility into profitability. Better budgeting discipline. Better ways to model pricing scenarios and track assumptions as matters evolve.

Most importantly, firms need to stop treating this as a future-state discussion.]]></description>
<dc:subject>ai pricing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:462bd36fbc8d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:pricing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/05/13/how-in-house-legal-teams-are-using-ai-to-cut-costs-and-win-budget-approval/?kw=How%25252BIn-House%25252BLegal%25252BTeams%25252BAre%25252BUsing%25252BAI%25252Bto%25252BCut%25252BCosts%25252Band%25252BWin%25252BBudget%25252BApproval&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803">
    <title>How In-House Legal Teams Are Using AI to Cut Costs and Win Budget Approval | Law.com</title>
    <dc:date>2026-05-26T20:50:12+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/05/13/how-in-house-legal-teams-are-using-ai-to-cut-costs-and-win-budget-approval/?kw=How%25252BIn-House%25252BLegal%25252BTeams%25252BAre%25252BUsing%25252BAI%25252Bto%25252BCut%25252BCosts%25252Band%25252BWin%25252BBudget%25252BApproval&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Legal operations leaders at CLOC’s Global Institute said legal departments are winning over skeptical finance executives by using artificial intelligence to cut outside counsel costs, automate routine work and produce measurable savings instead of broad promises about innovation.

During a Tuesday panel in Chicago titled “Beyond the Hype: 3 Ways to Prove ROI with Legal AI,” speakers said legal teams are under pressure to show exactly how AI investments improve efficiency and reduce spending, especially as CFOs demand hard numbers before approving new technology budgets.

“Your return on investment is numbers. You’re the CFO. You don’t care how many hours we save doing legal work. You care what the bottom line is,” said Alyse Wilkinson, senior director of global legal operations at WSP Global.

The discussion centered less on futuristic AI use cases and more on practical ways legal departments are using tools now, including invoice review, legal research, 50-state surveys and internal workflow management.

Jake London, a legal administrative assistant at Huntington National Bank, said his team started small when trying to justify AI spending internally.

“We knew that if we just signed up for the first step, eventually it was going to be like, ‘OK, what are you using it for?’” London said.

The Huntington legal operations team focused first on outside counsel work tied to 50-state surveys. By analyzing historical legal spend data in Thomson Reuters’ Legal Tracker platform, the department identified exactly how much it had been paying law firms for that work before testing whether generative AI tool CoCounsel could replicate it internally.

“We looked at how much we spent over the last quarter, over the last year,” London said. “And we were able to say, ‘OK, here’s an exact number that programs can save us.’”

Wilkinson described a similar effort at WSP, where legal operations leaders used AI prompts to help the company’s CFO quickly pull legal spend data.

“Oftentimes it’s not the system, it’s people, and the people don’t like the system if they don’t know how to use it,” she said.

The panel repeatedly returned to the importance of targeting narrow, measurable use cases first instead of attempting broad AI rollouts all at once.

“There are so many things to do with AI,” moderator Kelsey Nicol, director of product specialists for corporate legal solutions at Thomson Reuters, told attendees. “But how do I really focus in on those pieces that move the needle?”

One area drawing significant attention was outside counsel billing review. Wilkinson said WSP used AI tools to identify law firm charges that violated outside counsel guidelines, including internal law firm communication costs hidden in invoice descriptions.

The company ultimately rejected roughly $300,000 in internal communication charges tied to three months of invoices from a U.K. law firm, she said.

“So the CFO right away was all for that,” Wilkinson said.

WSP has since expanded its AI oversight of outside counsel by requiring firms to disclose which AI tools they are using on company matters.

“Our new outside counsel guidelines just released in April, not only have two pages of AI guidelines, but they require a schedule to be submitted with all of the AI tools they’re using on our matters,” Wilkinson said.

The panel also highlighted a growing tension inside legal departments: Firms are buying AI licenses, but many lawyers still are not using the tools regularly.

One attendee said their company revoked Microsoft Copilot licenses from employees who failed to use them. Others described lower-stakes efforts focused on training, gamification and peer examples.

London said Huntington surveys lawyers monthly about AI usage, asking both how they are using tools and what prevents adoption.

“What’s worked really well for us is identifying the people who are using it—our super users—and incorporating that into our newsletter or having them do a short demo,” he said. “Having it come from another lawyer can help.”

Wilkinson said WSP built prompt libraries, training videos and short tutorials to make adoption feel less intimidating.

“The prompt is only as good as the recipe,” she said. “Make sure you order the pizza that is half pepperoni and half pineapple and not just a pizza, because the Lord knows what will end up at your door.”

Some attendees said the hardest part is that many employees still do not understand what AI can realistically help with.

“One of the issues with our surveys is a lot of people don’t know what they don’t know,” one attendee said.

Others said legal departments need to stop presenting AI as something abstract or threatening.

“We’re trying to emphasize that this is a tool that’s here to help you,” London said. “It’s not scary. It’s not going to hurt you.”

Wilkinson echoed that point, telling attendees: “You’re not going to break it, and if you break it, we’ll fix it.”]]></description>
<dc:subject>clients ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:a3bfa769d84d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:clients"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://a2aj.ca/about/">
    <title>About — A2AJ</title>
    <dc:date>2026-05-26T20:49:16+00:00</dc:date>
    <link>https://a2aj.ca/about/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[he A2AJ is a research project based in Toronto, Canada, and is co-hosted by York University’s Osgoode Hall Law School and Toronto Metropolitan University’s Lincoln Alexander School of Law, with support from the Law Foundation of Ontario.

We research and advocate for a fairer, more accessible justice system as technology reshapes the law. Our work includes developing legal datasets, legal AI benchmarks, and open-source legal tech tools—all focused on improving access to justice, especially for marginalized and low-income communities in Canada. We support law reform to ensure that legal tech empowers the public, not just well-resourced individuals and institutions. We also create interdisciplinary learning opportunities for law students and for students in tech-related disciplines.

Ultimately, we aim to help foster a non-profit, open-source, and rights-enhancing legal tech ecosystem in Canada.]]></description>
<dc:subject>ai access</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:00847ccad087/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:access"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legalfutures.co.uk/latest-news/meet-mike-the-open-source-ai-challenger-built-by-a-city-solicitor">
    <title>Meet Mike, the open-source AI challenger built by a City solicitor - Legal Futures</title>
    <dc:date>2026-05-26T20:27:36+00:00</dc:date>
    <link>https://www.legalfutures.co.uk/latest-news/meet-mike-the-open-source-ai-challenger-built-by-a-city-solicitor</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[A growing number of lawyers and law firms are contacting the solicitor who created Mike, a free alternative to the AI giants Harvey and Legora.

Launched just two weeks ago, the interest in Mike from lawyers around the world has made this the fastest-growing legal tech project in history.

Law firms can now choose between the major brands Harvey and Legora, which can cost hundreds of pounds per lawyer per month, or open-source Mike, which costs nothing.

Speaking to Legal Futures, Mike’s creator Will Chen, a former associate in the Singapore and London offices of US firm Latham & Watkins, said the sector was showing huge interest in his AI.

Mr Chen said: “The response has been much bigger than I expected. A lot of lawyers, innovation teams and technical people inside firms have reached out. There is clearly strong interest in self-hosted legal AI and alternatives to closed enterprise systems.”

And despite Legora’s and Harvey’s multi-billion dollar valuations and expensive global advertising campaigns, Mike is making history.

Mr Chen said: “Mike quickly reached thousands of [collaboration platform] GitHub stars and hundreds of forks in a few days. It is now the fastest growing legal tech [repository] in history.

“A viral trend is that new versions of Mike for different countries are popping up every few hours on LinkedIn. These include Korean, Dutch, French, Turkish and countless other variants. The collaboration has become very international very quickly.”

Mike sits on Microsoft’s platform and is powered by Claude and Gemini. Lawyers can use Mike in the same way they use Harvey and Legora, such as to read documents, research, and draft and edit contracts.

The name comes from the character Mike Ross from the TV series Suits. Harvey was named the same way, inspired by the character Harvey Specter. The ‘oss’ from Ross appears in Mike’s url, MikeOSS, which stands for open-source software.

Mr Chen built Mike in just two weeks, with small and medium-sized firms in mind.

His last legal tech project was Lawprof, which has grown into the UK’s largest online legal learning platform.

Mr Chen said: “I set out to prove that the core functionality of Harvey and Legora could be replicated in two weeks. And I put it in open source so anyone could see for themselves, so that people can build upon it and make it better. That is the whole point of open source.”

“I wanted to show that there might be a different future for legal AI: one that’s open, affordable and gives lawyers control over the application layer and their proprietary data. One that stands in contrast to the expensive, closed systems designed for vendor lock-in that are spreading across the industry.

“The ‘BigLaw’ firms that can afford these tools partly do so to signal prestige to clients. Every other AmLaw 100 firm bought it, so it must be good, right? But small and mid-sized firms are being priced out.”

Legora is valued at $5.5bn and is used by more than 1,000 firms, including Bird & Bird, Linklaters, and Dentons.

Harvey, which is valued at $11bn, is used by global firms too, including A&O Shearman.

In recent weeks Legora unveiled a global advertising campaign featuring Jude Law as part of its worldwide expansion. On billboards in London and New York, the Hollywood actor is seen wearing a dark suit inside a wood-panelled offices. The slogan says: “Law has never looked so attractive.”

Harvey has signed up Gabriel Macht, the actor who played Harvey Spector, and has moved into sports sponsorship, including on Premier League football electronic advertising boards.

Mr Chen said Mike’s marketing message was based on functionality and cost – “the open-source alternative to Harvey and Legora. All the features without an enterprise contract”.

Comments on LinkedIn from lawyers and AI developers around the world confirm the growing support for Mike and open-source lawtech.

Saad Ansari, founder of Stealth, an AI start-up, wrote: “Making law more accessible by making it cheaper is a great public service.”

Lindsay Healy, chief executive of Aria Grace Law, said: “What you have done is simply awesome.”

Inspired by the success so far, Mr Chen said the next step was building capability and trust in Mike.

“Right now the focus is improving stability, security and self-hosting. I intend for Mike to remain open source and I want for there to be a path where Mike becomes an enterprise grade solution.”

“Companies like Harvey and Legora are very strong, given their head start. But open source has advantages too – speed, flexibility, and transparency. Based on the response so far, I think there is clearly demand for an open alternative.”]]></description>
<dc:subject>ai access</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:86c411fc76bd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:access"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law360.com/pulse/modern-lawyer/articles/2475936?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0">
    <title>Trading Scheme Is A 'Wake-Up Call' For BigLaw Compliance - Law360 Pulse</title>
    <dc:date>2026-05-15T19:48:19+00:00</dc:date>
    <link>https://www.law360.com/pulse/modern-lawyer/articles/2475936?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Melinda Roth, a former Wall Street investment banker and current visiting professor at Washington and Lee School of Law, likes to show her classes a slide about the U.S. Supreme Court's 1997 decision in United States v. O'Hagan.

The title is: O'Hagan, Oh Had 'Em.

The case involved a Dorsey & Whitney LLP partner who the high court held could be liable for securities fraud because he used nonpublic information in a "deceptive" manner. Roth uses the landmark decision to teach law students about the perils of abusing their access to information meant to be kept under wraps.

A future law school lesson may have surfaced last week, when Boston federal prosecutors alleged that a former associate who worked at Sidley Austin LLP, Latham & Watkins LLP, and Goodwin Procter LLP helped lead a decade-long scheme that involved leaking nonpublic information about deals his firms worked on in exchange for kickbacks. Those firms and others whose information was allegedly stolen are described in a pair of indictments as victims.

The breadth of the alleged scheme should jolt firms to reexamine their practices to close gaps in internal security, experts told Law360, even if totally eliminating bad actors is nearly impossible.

"I don't think this threat was on law firms' radar," said David Axelrod, a former federal prosecutor and attorney with the U.S. Securities and Exchange Commission who now leads the securities enforcement and corporate governance litigation group at Ballard Spahr LLP.

"I don't think law firms ever contemplated the idea that someone is going to go into their mergers and acquisitions department and be looking to extract material nonpublic information for a decade," Axelrod said. "I think this is going to be a wake-up call."

A "Black Eye" for Firms

According to a pair of indictments, Nicolo Nourafchan bounced from Goodwin to Latham to Sidley Austin and recruited others to join the scheme along the way, leaking info related to some of the biggest deals of the past decade.

A former attorney at Wachtell Lipton Rosen & Katz and Weil Gotshal & Manges LLP, another firm that was allegedly victimized, is among the unindicted co-conspirators tied to the sweeping scheme.

The deals the defendants allegedly traded on include Occidental Petroleum's $55 billion acquisition of Anadarko Petroleum Corp. in 2019; Johnson & Johnson's $31 billion acquisition of Swiss rare drug manufacturer Actelion Ltd. in 2017; a 2023 deal in which private equity firms Blackstone and Permira acquired eBay-backed Norwegian online marketplace Adevinta ASA in a deal worth about $13.2 billion; and Sixth Street's $5.1 billion purchase of insurance group Enstar in 2024.

The U.S. Securities and Exchange Commission filed a parallel civil suit over the alleged scheme. Four defendants reached settlements with the SEC, according to court filings.

Evan Gotlob, a former Boston federal prosecutor who leads the white collar practice at DarrowEverett LLP in Rhode Island, said the case casts a bad light on all the firms involved, especially because the indictment alleges that Nourafchan was able to gain access to information on deals he was not working on.

"I don't have access to every single file at DarrowEverett because, why would I need access to everything?" Gotlob said, adding that information was similarly siloed at Saul Ewing LLP, where he worked previously.

"To allow somebody who is relatively junior, and very junior at most of these firms because he moved around so much, to have access to those files is really a black eye for them," Gotlob said. "No one is saying [the firms] were involved, but it looks bad for them."

The firms identified as victims have said they are cooperating with law enforcement. They did not respond to questions about whether they have, or will, be changing any internal procedures in light of the case. An attorney for Nourafchan declined to comment.

Karen Woody, another professor at Washington and Lee who worked in private practice for four different firms, said that she has seen few comprehensive measures in place to ensure that attorneys, especially junior associates, were not trading on confidential information.

"Maybe it was because it seemed like it should go without saying," said Woody, who teaches securities and white collar law. "We are members of the bar, we have ethical requirements, it would have been so brazen."

The need for firms to calm worried clients and save face publicly will likely cause some to change their practices quickly, Woody said.

"I imagine there will be some very quick ramp-up by firms," she said, "because this is not a good look for anybody."

How to Catch an Inside Trader

The news of the insider trading case broke publicly in the midst of a white collar bar conference in Boston. Gotlob, who attended the conference, said a number of lawyers he spoke to expressed the need to take a second look at internal procedures and compliance practices.

"There are a lot of meetings that have taken place over the last week over this," he said.

Ballard Spahr's Axelrod said that all firms, including his, are going to go through new security processes, including using code names for projects, requiring password access for certain files, and, in extreme situations, making lawyers who work on deals sign nondisclosure agreements.

"I think you're going to see all of that become much more prevalent," he said.

The ability for people to make money with insider information in ways they could not in the past, such as prediction markets, is something law firms will have to deal with, said Todd Haugh, a professor of business law and ethics at Indiana University's Kelley School of Business.

"Firms are going to have to get more sophisticated, and that probably means using a lot more data-centric AI tools and things like that to identify when people who really don't necessarily need access to information are accessing it and either blocking them at the gate, or identifying it very quickly and then investigating it," Haugh said.

Michael Maschke, the president and CEO of cybersecurity firm Sensei Enterprises Inc., said another challenge law firms face is that the bad actor they are trying to stop may be someone who has a legitimate need to access the information in question.

He said firms may want to have tools in place that flag files that are accessed at abnormal times or by someone who isn't directly involved in a particular deal. Being aware of whether systems are accessed after hours and being on top of the forwarding of emails and other communications over corporate networks is also important, Maschke said.

"You're dealing with insiders, and you want to focus on behavioral analysis and activity that is unusual," he said.

One of the biggest problems he sees is firms that do not follow the practice of limiting privileged access to as small a circle as possible.

"A lot of times, partners want access to everything because they are a partner," Maschke said. "From a security standpoint, that is not the best position to take."

Marci Rozen, senior legal director at ZwillGen PLLC, which specializes in technology and privacy law, agreed that limiting access to confidential information is the "gold standard" practice, but it can pose practical challenges for firms.

"I've experienced it in my own practice," Rozen said. "[If] I have a client with an urgent issue and I need to pull someone in right away, it can cause burdensome delays if you have to wait for IT to lift restrictions."

But Rozen said there is software that can detect behavior patterns that could be indicative of an insider threat. A document management system can establish a baseline for activity and flag certain "deviations," Rozen said, such as someone accessing information for a matter they are not working on or while on leave from the firm, as Nourafchan is alleged to have done.

Law firms can also beef up training of associates, and even partners, on insider trading issues, Rozen said, adding that companies in the financial services industry set a good example for the legal profession to follow.

"Financial institutions are really good at this because they are so tightly regulated and subject to regular audits, whereas law firms don't have that primary regulator and they don't think about incorporating this as much into day-to-day training," she said. "I think law firms could learn a thing or two from financial institutions."

The Best Security Still Has Its Limits

Even with top-notch security measures in place, firms may still struggle to ferret out the type of activity at the center of the explosive new case, experts said. Axelrod noted that individuals using law firm information to further insider trading is a practice as old as insider trading itself.

"Criminals are going to commit criminal acts if they have the opportunity," he said.

There were several prominent cases in 2023 alone. That year, the ex-boyfriend of a then-Covington & Burling LLP associate pled guilty to securities fraud after stealing a glance at documents concerning a biotech merger.

An ex-Cozen O'Connor lawyer was suspended from practicing law and hit with a fine for buying shares of Liberty Property Trust after he was put in charge of a conflict check on a potential merger between Liberty, a client of the firm, and Prologis Inc., a real estate investment trust.

And a young Brazilian lawyer who had worked a one-year stint at Gibson Dunn & Crutcher LLP as a visiting attorney pled guilty to insider trading and received a two-month prison sentence after admitting to using the firm's private database to profit from a merger between two companies.

In 2017, a former Foley & Lardner LLP partner copped to charges over claims that he used confidential information about the law firm's clients to make $327,000 in illicit trading profits.

Roth said that the issue is less about whether rules or procedures need to be changed, but rather, "How do firms better detect when someone is breaking those rules and not following those procedures?"

According to federal prosecutors, the defendants and other unnamed co-conspirators tried to keep law enforcement — and the law firms — in the dark by using burner phones, encrypted applications, coded language and clandestine meetings without any electronics.

Massachusetts U.S. Attorney Leah Foley said when the case was unveiled that the charges stemmed from a multiyear investigation and said that the trading "not only violated the securities laws, but it also took advantage of the special access and ethical duties that come with a law license."

"You can put whatever you want on the books, you can have a rule that says you can't make a single trade without clearing it with our conflict department," Roth said. "But these rogue lawyers can be pretty deceptive."

IU's Haugh said that firms would be "silly" not to look at their own internal practices in light of this case, but added that the legal industry is not always known for being forward-looking technologically.

"It's a traditional business based on trust and an ethical foundation, so I am a little bit skeptical that there is going to be an incredible amount of innovation," he said. "Law firms are more likely to be the followers than the leaders here."]]></description>
<dc:subject>fraud</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:dc59593783a9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:fraud"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://legaled.ai/claude-for-legal-is-huge/">
    <title>Claude for Legal Is Huge!</title>
    <dc:date>2026-05-15T19:47:04+00:00</dc:date>
    <link>https://legaled.ai/claude-for-legal-is-huge/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Anthropic just rolled out Claude for Legal, and even if you're buried taking, grading or just having recurrent nightmares about exams, this post deserves ten minutes. At least three things matter for the academy: a law-student plugin with a summa cum laude portfolio of skills; a free CourtListener connector that does traditional legal research and more while quietly routing around the Westlaw/Lexis duopoly; and a legal-clinic plugin that turns supervisory pedagogy into configuration and could bend the cost curve of clinical and legal-aid work. There is much more and none of it is finished — but the trajectory is unmistakable. Access-to-justice, clinical economics, and how and to whom we teach law itself are all about to look different faster than we can imagine. This is only the beginning.

It was inevitable. Claude has entered the legal tech market big time. It's a huge development. In this blog post I am just going to alert readers to what has happened and show a few examples. But probing all the capabilities of Claude for Legal is going to span a number of posts that I'll try to get out over the next week or two. (Gotta grade those exams 😦)

The Law Student Plugin
Claude has added a "law student plugin" that contains a portfolio of skills that law students should find incredibly useful. Maybe professors too! Here's a listing.


To install the skills, you have to religiously follow the instructions in the video contained at this website. https://github.com/anthropics/claude-for-legal/blob/main/QUICKSTART.md Watch it carefully! (I messed up the first few times due to impatience and incorrect assumptions about how the UI works).

I'll let the new skill create a Socratic discussion of separation of powers.


Let's see how its legal-writing skill performs. I had Grok draft a deliberately cruddy answer to a hypothetical exam question involving separation of powers. Here's a screen capture of the beginning of Claude's response.


Let's see if it can forecast an exam question I might ask? I gave it my most recent constitutional law exam and wrote:


/exam-forecast Forecast a multiple choice question this fiendish professor might write.

After having conducted this accurate analysis of the fiendish professor's questioning style, it comes up with a future question.

Forecast question
A Chandler-style MCQ he very plausibly writes for next year — weaponizing Trump v. Anderson (2024), which is conspicuously absent from this year's bank despite being the Court's marquee structural decision of that term:

Question (forecast)
Following allegations of election-related misconduct, the Secretary of State of Franklin, after a contested administrative hearing, determines that former Senator Marcus Holloway "engaged in insurrection or rebellion against the United States" within the meaning of Section 3 of the Fourteenth Amendment. Franklin law provides that the Secretary "shall exclude from the ballot any candidate she determines to be constitutionally ineligible to hold the office sought." Acting under that authority, the Secretary removes Holloway from Franklin's presidential primary ballot. No federal statute purports to authorize state enforcement of Section 3 against federal candidates, though 18 U.S.C. § 2383 makes it a federal crime to engage in insurrection or rebellion. Holloway sues in federal court, arguing Franklin lacks constitutional authority to disqualify him. How should the court rule?

(a) For Franklin. Article II's Electors Clause grants States plenary authority to determine the "manner" of appointing presidential electors, which necessarily includes the authority to determine which candidates may appear on the State's ballot. Section 3 imposes a textual qualification, and the State's authority to enforce a textual qualification follows from its authority to administer the election. See Chiafalo v. Washington.

(b) For Holloway. Section 3 of the Fourteenth Amendment may not be enforced against candidates for federal office absent legislation enacted by Congress under Section 5. The Constitution channels enforcement of Section 3 against federal candidates through Congress rather than the States in order to avoid a patchwork of inconsistent state-by-state disqualifications that would fracture the uniform national character of federal elections. Trump v. Anderson, 601 U.S. 100 (2024).

(c) For Holloway. Whether a particular individual "engaged in insurrection" within the meaning of Section 3 is a nonjusticiable political question committed to Congress by Article I, § 5, which makes each House the Judge of "the Elections, Returns and Qualifications of its own Members" — and the matter is therefore outside the competence of any State or court.

(d) For Franklin, but only because 18 U.S.C. § 2383 supplies the congressional authorization required to enforce Section 3 against federal candidates; absent that statute, Franklin would lack power to disqualify Holloway, but the statute cures the defect.

Correct answer: (b).

There's tons more to explore here in the law student plugin. Claude for Legal is a giant release. But let's move to another capability released today.

The CourtListener Connector
One huge feature for legal educators, especially those without large budgets, is the ability to connect to CourtListener for free. Other products have claimed before to offer this kind of connection to this vast legal database, but my experience with earlier versions was not stellar. Here, you can see me using the new connector to search for Texas cases on the duty to settle decided after 2020. I am not using my paid Midpage subscription. I am using the free CourtListener MCP connector.

That matters. Students may no longer need to spend $25 a month for decent access to grounded AI. The free CourtListener version may not be quite as powerful, but it can still reduce hallucination risk substantially and produce grounded answers within the familiar framework of a consumer large language model that already offers dozens of other capabilities.


The CourtListener skill can retrieve cases that it has found and discuss them.


So it can apparently find cases, retrieve them, and comment upon them. But can it check if the cases it discovers are still good law? Yes! Here is my deliberately cruddy prompt:

There is a Texas insurance case called something like Farmers v. Soriano from the 1990s. Can you find the case and see if it has any negative treatment.
I located the case and checked for negative treatment. There are actually two opinions in this litigation:

The Texas Supreme Court decision — Texas Farmers Insurance Co. v. Soriano, 881 S.W.2d 312 (Tex. 1994) — is the one you're almost certainly thinking of. It reversed the San Antonio Court of Appeals (844 S.W.2d 808) and established what is now usually called the "Soriano rule": in a multiple-claimant situation, an insurer that in good faith settles with one or more claimants in a way that exhausts (or substantially exhausts) policy proceeds is not liable in Stowers to the insured even if remaining claimants are left without recovery. CourtListener shows 106 citing opinions.

Negative treatment in CourtListener's data: None of the standard markers turn up. The case has not been overruled, abrogated, or disapproved. I ran searches for "Soriano" paired with "overruled," "abrogated," "declined to follow," "distinguishable," "rejected," "criticized," and "disagree." The hits that came back are overwhelmingly (a) cases involving unrelated parties named Soriano (immigration, criminal, workers'-comp), or (b) opinions citing Soriano favorably. A spot-check confirms this: American Guarantee & Liability v. ACE American Insurance, 990 F.3d 842, 848–49 & n.16 (5th Cir. 2021), recites the Soriano three-prong test as canonical Texas Stowers law; Westport Insurance v. Pennsylvania National Mutual, 117 F.4th 653 (5th Cir. 2024), and OneBeacon v. T. Wade Welch & Associates likewise apply it as good law.

The only "negative" voice inside the Soriano file itself is the original concurrence by Justice Hightower (joined by Doggett, Gammage, and Spector in part) stating "I disagree with the court's analysis of an insurer's duty to settle (including the requirement of a formal settlement demand within policy limits)," cross-referencing his dissent in American Physicians Insurance Exchange v. Garcia, 876 S.W.2d 842 (Tex. 1994). That is intra-court disagreement at the time of decision, not subsequent negative treatment, and it never commanded a majority.

Two caveats. First, CourtListener does not maintain a Shepard's- or KeyCite-style negative-treatment flag system — the absence of negative-treatment hits in my keyword searches means I found nothing, not that nothing exists. Second, my searches showed several later cases that distinguish Soriano on its facts (e.g., refusing to extend its safe harbor where the insurer's settlement did not actually exhaust limits, or where the offer was not a proper Stowers demand). Distinguishing is not negative treatment in the Shepard's sense, but it is worth being aware of when relying on the case. For a definitive answer in a brief, I'd still run KeyCite or Shepard's.

Sources:

Texas Farmers Ins. Co. v. Soriano, 881 S.W.2d 312 (Tex. 1994)
Texas Farmers Ins. Co. v. Soriano, 844 S.W.2d 808 (Tex. App.—San Antonio 1992) (reversed)
American Guarantee v. ACE, 990 F.3d 842 (5th Cir. 2021)
Students and other legal professionals can use the CourtListener connector to summarize a body of law. Here's my prompt. Again, I used absolutely minimal effort.

Retrieve all the post 2020 cases that you found and create a 300 word essay on how they change or clarify the duty to settle in Texas. I will permit you to use the web to research how the baseline Stowers doctrine works in texas. Put your answer in an html div with a light blue background.
A few minutes later, I get this:

Let me pull the Westport opinion and do a quick web check on baseline Stowers before drafting.
The Stowers Doctrine After 2020: Clarification, Not Revolution
The Stowers doctrine, rooted in G.A. Stowers Furniture Co. v. American Indemnity Co., 15 S.W.2d 544 (Tex. Comm'n App. 1929), requires a liability insurer to exercise ordinary care in responding to a third-party settlement demand or face liability for any excess judgment. American Physicians Insurance Exchange v. Garcia and Texas Farmers Insurance Co. v. Soriano (both 1994) fix three triggering prerequisites: the claim is within coverage; the demand is within policy limits; and an ordinarily prudent insurer would accept it given exposure. The demand must be unconditional, for a sum certain, and propose a full release.

The post-2020 cases sharpen these edges without rewriting the framework. American Guarantee & Liability v. ACE American Insurance, 990 F.3d 842 (5th Cir. 2021), reaffirms that ambiguity defeats Stowers — there, an offer of "$1.9MM to $2.0MM with costs" failed because the demand did not clearly state a sum certain. The same opinion Erie-guesses that a lump-sum offer made by a parent as next friend for minor children is not inherently conditional merely because post-acceptance judicial approval will be required, modestly expanding the universe of triggering offers. And it holds that arguments about appellate-reversal prospects must be preserved in the trial court or are waived.

Westport Insurance v. Pennsylvania National Mutual, 117 F.4th 653 (5th Cir. 2024), clarifies the primary-versus-excess interaction: an excess insurer's later contractual breach does not excuse the primary's earlier Stowers breach, and Stowers is not a freestanding defense to an excess carrier's duty to indemnify. In re State Farm Mutual Automobile Insurance Co. (Tex. App.—Fort Worth Nov. 19, 2020) is largely dicta but reminds readers that Murray abandoned Arnold's Stowers analogy as the doctrinal bridge between first-party UM/UIM and third-party bad faith. The post-2020 picture is incremental tightening, not doctrinal upheaval.

It can also create precedent graphs (although I am not sure I would vouch for this one).

Use the CourtListener MCP to Make a network visualization that connects the citations between Myers v. United States and Trump v. Slaughter in the case law database."

But CourtListener goes beyond judicial opinions. It also permits access to docket entries. Here's an example of a query and a screen capture of part of the response.

use courtlistener to find docket entries from 2026 in the Nathan v. Alamo Heights case in the 5th Circuit. Put the answer in a markdown file.

I had often wondered if Claude or one of the other frontier AI labs would use part of their billions to crash through the eroding Westlaw/Lexis duopoly and simply buy a legal database for their users. I had thought (and continue to think) it would be a great idea. By now connecting to a pre-existing database, however, and developing an intelligent connector, Claude may have gotten at least halfway there for free. It's the first frontier AI lab out of the gate in this effort but I suspect not the last.

Legal Clinics
Another important part of today's release is the legal-clinic plugin. This one isn't aimed at the solo or the BigLaw associate — it's aimed squarely at the law school clinic supervisor and her students, and (I think) at the legal aid lawyer trying to do five times as much work as her funding allows. Sixteen skills in all. Rather than march through every one, let me pull out the three I think do the most work, and just list the rest.

cold-start-interview. The professor's one-time clinic setup, and the foundation everything else rests on. Captures practice areas, jurisdiction, supervision style (formal review queue / configurable flags / lighter-touch), and ingests the handbook, filing guides, local court rules, intake forms, and a scrubbed example file. Writes a CLAUDE.md every other skill reads. This is what lets the professor encode her pedagogy once and have it scale across every student-facing skill without her having to repeat it. Quietly the most important skill in the bundle.

draft. First drafts of common clinic documents — asylum applications, eviction answers, protective-order petitions, demand letters — with jurisdiction-aware formatting and [FACT NEEDED] / [VERIFY] / [UNCERTAIN] flags planted inline where the work isn't done yet. Loud AI-assisted label at the top, automatic supervision routing, no pretense that this is anything but a starting point. This is the workhorse. It will be the skill students use most and the one that compresses the lowest-value hours of clinic work into minutes.

semester-handoff. The mirror of /ramp. At the end of the term it reads deadlines.yaml and the per-case comms logs and generates a transition memo for every active case plus a cohort summary. The institutional knowledge that used to walk out the door with the graduating 2L — what was promised the client last March, where the research dead-ended, which deadline is sitting on July 14 — just stays put. The most distinctive structural contribution in the plugin and the one I'd build a clinic around.

The rest, briefly: build-guide (lets the supervisor configure pedagogy per practice area), client-comms-log (append-only per-case comms record), client-intake (structured intake with conflict and issue-spotting), client-letter (routine correspondence from templates), customize (change one thing without re-running cold-start), deadlines (the cross-case deadline tracker), memo (IRAC scaffold with blank Application and Conclusion — pedagogically smart), ramp (student onboarding from the handbook the professor uploaded), research-start ("leads not authorities" research roadmap), status (case status reshaped for client / internal / court audiences), supervisor-review-queue (the professor's review inbox when she's chosen formal-queue supervision). Two more — form-generation and plain-language-letters — are deprecated, folded into /draft and /client-letter+/status respectively.

Why this could matter a lot
Now let me put my professor hat on and tell you why I think this release is more important than the law student plugin everybody is going to focus on.

Law school clinics — and the legal aid organizations that share their economics — are caught in an unforgiving bind. Every case needs a credentialed attorney to supervise an inexperienced student. That supervision is the largest cost driver in clinical legal education and the binding constraint on how much pro bono work a legal aid office can actually deliver. Students often churn in semester cycles. Knowledge walks out the door every December and every May. Intake produces administrative drag. Routine correspondence absorbs hours that should be going to advocacy. The result is a chronic gap between the volume of unmet legal need and the throughput of the institutions trying to meet it. This plugin attacks every link in that chain.

The first thing it does is turn the supervising attorney's pedagogy into configuration. cold-start-interview and build-guide let her encode her practice areas, jurisdiction, supervision posture, and teaching philosophy once. Every downstream skill — draft, memo, client-intake, status — then reads from that same CLAUDE.md. supervisor-review-queue enforces the review gates she chose. Her judgment scales without her having to repeat it.

The second thing it does is compress the structurally similar, lowest-leverage hours of clinic work. client-intake produces a formatted summary in minutes instead of half an afternoon. draft generates a jurisdiction-aware first draft of an eviction answer or a protective-order petition with the missing facts visibly flagged. research-start hands the 2L a roadmap instead of letting her flail at the Westlaw bar for two hours. client-letter and status automate the dozens of routine touches that used to be evening work. None of these outputs is a final product — every one is loudly labeled AI-assisted and routes back through supervision — but the time formerly consumed by the lowest-value tasks now belongs to the irreducibly human ones: client counseling, strategy, advocacy.

The third thing — and the one I find most quietly impressive — is what deadlines, client-comms-log, and semester-handoff do together. They build a persistent operational substrate that is itself the answer to the semester-churn problem. The 2L who arrives in August inherits per-case handoff memos and a cohort summary built automatically from the deadline file and the comms logs. ramp then teaches her the clinic she is actually entering, from the very handbook her professor configured at cold-start. The institutional memory that used to evaporate with each graduating cohort just doesn't anymore.

Here's an example of what the deadline skill generates.

/legal-clinic:deadlines Use the skill to alert me to the series of deadlines my client is likely to face in a Houston eviction case. She got served with a notice to vacate yesterday but she believes she has proof (a) that she is current in her rent and (b) that the landlord threatened to report her to ICE if she did not pay in full. That might be extortion.

This is a useful answer but it looks as if the skill could be improved. Fortunately skill files can generally be forked so that a Texas clinic could likely adapt it for its own use by using the Illinois or California material as a template.

By the way, to test out whether the skill files are as portable as advertised, I ran it in OpenAI's Codex rather than Claude. It worked a little differently, but it did function. This fact leads me to believe that many of the skills now available for Claude for Legal may also work at least partly inside other large language models.

Here's a skill file. Use it to alert me to the series of deadlines my client is likely to face in a Houston eviction case. She got served with a notice to vacate yesterday but she believes she has proof (a) that she is current in her rent and (b) that the landlord threatened to report her to ICE if she did not pay in full. That might be extortion.I used the deadline-tracking approach from your skill file and set a single thread alert to run daily from May 14, 2026 through May 26, 2026. It will prompt you to watch for a filing, citation, service date, and trial date so the later deadlines can be calendared from real trigger dates rather than guesses.
I used the deadline-tracking approach from your skill file and set a single thread alert to run daily from May 14, 2026 through May 26, 2026. It will prompt you to watch for a filing, citation, service date, and trial date so the later deadlines can be calendared from real trigger dates rather than guesses.

For this Houston eviction matter, the immediate timeline is:

May 11, 2026: notice to vacate served.
May 14, 2026: likely first day the landlord could file, assuming this is the default three-day Texas notice period and the lease does not require a longer period. Texas now counts the notice period from the day of delivery. This is an inference from the statute, not a court-confirmed case date. ([jp.hctx.net](https://www.jp.hctx.net/evictions/faq.htm))
If the landlord files:
The trial date stated in the citation must generally be set 10 to 21 days after filing.
A written answer is optional in justice court, but attendance at trial matters.
A jury demand is due no later than 3 days before trial. ([jp.hctx.net](https://www.jp.hctx.net/evictions/filing.htm))
If the landlord seeks summary disposition under the 2026 rules and a response deadline applies from the papers served, that response can be very short, including a 4-day response period in the rule text quoted by the Texas Supreme Court materials. The exact applicability should be checked against the filed motion and case type.
If judgment is entered against the tenant:
Appeal is due within 5 days after judgment is signed.
A writ of possession generally cannot issue before the 6th day after judgment or before the appeal deadline passes, whichever is later.
Two merits points are worth flagging now:

Because the Texas statute changed effective January 1, 2026, if the eviction is based solely on nonpayment and she was not late or delinquent before the month of the notice, the notice must be in the form of a notice to pay rent or vacate, not merely a bare notice to vacate.
Her proof that rent is current is central. The ICE threat should also be preserved exactly as received, but I have not classified it as extortion here without a separate legal analysis.
The next useful trigger is any filed petition, citation, service date, or hearing notice. Once one of those exists, I can turn the rest into exact dates instead of conditional ones.

Stack these various skills and the cost curve of running a clinic bends. A clinic that supervised eight students on twenty cases could plausibly supervise eight students on thirty-five — or twelve students on the same twenty, with deeper case work per student. Legal aid offices outside law schools, operating under the same supervision constraint with even less slack, benefit in a smilar way. Housing, immigration, bankruptcy, family law — the document-heavy practice areas where the unmet-need gap is widest — are exactly where this plugin might hit hardest. But it might also enable new clinics in diverse fields: imagine the ERISA clinic, the maritime clinic, and other areas in which practical experience might benefit students and communities alike.

And more ...
There is more in the Claude for Legal announcement that is of great relevance to legal educators and the legal profession generally. One notable item is a partnership with Courtroom5, a platform that describes its mission as helping self-represented litigants. I have not yet been able to get its Claude connector to work, so any assessment has to remain provisional. But certainly the idea is important. If Claude can connect effectively with software designed for self-represented litigants, that could become a major access-to-justice development. AI may enable an averagely educated person to function much more like a competent legal advocate, at least in smaller matters where the alternative is often paying $400 or more per hour for a licensed attorney—or going without help altogether. We will explore the implications in future posts. For now, the central point is simple: a substantial increase in AI-assisted pro se litigation has already begun, and it is likely to matter a great deal for both the judiciary and legal education.

Future Posts
As I said at the beginning, Claude for Legal is a huge development. I want to write more. Unfortunately, I've got a stack of exams that do not seem to be grading themselves. And although it is super tempting just to throw them into AI and see what results, I am still old school enough this year to feel some obligation to grade them myself. But we're going to come back to many of the new features of Claude for Legal and a related development that I'm hoping I can access and test for myself, Claude for Microsoft 365, which lets you use Claude inside the apps with which most legal academics and legal professionals are most comfortable.

We often say, somewhat casually, that AI is advancing exponentially. But those can remain abstract words until you see what that means in practice: tools like Claude for Legal, projects like Suzie Law, Irys, or Legora aOS, and the seemingly endless stream of new legaltech products arriving almost daily. Then the pace of change stops feeling theoretical and starts hitting you in the face.

Claude for Legal is one of the clearest examples yet. I have only scratched the surface here, and I expect to return to it soon. But even this early look suggests that it is not merely another useful legal AI product. In my world of legal education and beyond, it is a deeply disruptive one.]]></description>
<dc:subject>schools AI competence access</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:9af69590fd4e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:schools"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:AI"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:competence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:access"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legaltechnologyhub.com/contents/anthropic-unveils-claude-for-legal-with-12-new-plugins-20-mcp-connectors-and-more/">
    <title>Anthropic Unveils 'Claude for Legal' With 12 New Plugins, 20+ MCP Connectors &amp; More | Legaltech Hub</title>
    <dc:date>2026-05-15T18:57:21+00:00</dc:date>
    <link>https://www.legaltechnologyhub.com/contents/anthropic-unveils-claude-for-legal-with-12-new-plugins-20-mcp-connectors-and-more/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Few companies have caused more buzz in the legal tech space this year than Anthropic—a generalist AI provider with no origins in the legal industry. Anthropic's foray into the legal market has come in waves of increasingly more significant announcements, from the launch of a Claude legal plugin to legal-specific webinars to a Word integration focused on contracting. 

The building momentum has led many in the industry to ask if, or even when, Anthropic might make an official move into the legal vertical. 

Today, Anthropic answered that question with the launch of Claude for Legal. Akin to vertical programs previously announced for sectors like financial services, Claude for Legal represents a significant expansion and formalization of the growing momentum Anthropic has been building in the legal industry in recent months. 

Comprising 12 new legal practice-area plugins, over 20 MCP Connectors with legal tech providers, an expansion of Claude across Microsoft 365, strategic access to justice partnerships, and more, Claude for Legal is positioned as the "next step" in Anthropic's legal offerings. "Claude is now built for the workflows at the heart of every legal organization—helping firms and in-house teams across tasks like drafting, research, contract lifecycle, e-discovery, and matter management to improve how they serve clients and manage risk," the company said in a fact sheet provided to media. 

According to Anthropic, "Legal is now the #1 power-user job function in Claude Cowork." Claude has seen a surge in interest from legal users in the months since Claude introduced its first legal plugin on January 30, 2026, Mark Pike, Associate General Counsel at Anthropic, told Legaltech Hub (LTH). "We want to meet lawyers where they work, and we know that there's an incredible ecosystem of technology that lawyers are using each day, and that a lot of these partners are powered by Claude Opus 4.7, which has been at the frontier of being capable of doing agent legal work," Pike said. "Everything we're doing in developing these tools and technologies in furtherance of this open ecosystem, whether that's powered by the models, the MCPs and Skills that can also be embedded inside of these third-party tools, or the enthusiastic community that is building on top of this, we think that Claude is helping lead the way in a better-together story." 

Pike made it clear that Anthropic is not looking to unseat legacy legal tech providers but instead work with them to improve the industry. "The underlying capabilities here are real, and they're compounding. And Anthropic is really focused on growing the pie," he told LTH. "We're a platform, and we see that a rising capability in these models is a rising tide that lifts everyone building on it. So, we don't see that as a zero-sum trade. It's an opportunity for everybody to help lawyers get the most out of their tools and better provide client services." 

How We Got Here: A Brief History of Anthropic & Legal  
Anthropic’s path to today’s launch of Claude for Legal has unfolded over the course of the last three years, as traced in the graphic below. 

The company has been touching legal since Claude's March 2023 debut, which name-checked the now-defunct Robin AI—though the launch was overshadowed by OpenAI's GPT-4 release the same day and Casetext's CoCounsel running on it. Anthropic gradually gained ground through the industry's pivot to multi-model strategies and its open-sourcing of MCP in November 2024. 

Direct entry came in early 2026, beginning with the Claude Cowork legal plugin on January 30—a release that initially rattled the legal tech market. From there, the pace accelerated: a virtual event in February unveiling new legal connectors and Thomson Reuters's next-generation CoCounsel built on the Claude Agent SDK; the Claude Marketplace launch in March with Harvey as the sole legal partner; the Claude for Word beta in April; a multi-year Freshfields partnership deploying Claude firmwide; and a Claude for Legal teams webinar that drew more than 20,000 attendees. 

Today's announcement of Claude for Legal is a culmination of this building momentum. 

You can find a more in-depth timeline of Anthropic’s entry into legal in our companion article here. 

 

 

 

A Look Inside 'Claude for Legal' 
Claude for Legal is more than a mere product launch. Anthropic frames it as an expansion of its legal offerings to date, and it operates within the existing Claude interface.  

Pike confirmed to LTH that it is not a standalone product. "This is inside of the Claude you already know and love, inside of our first-party apps," he said.   

That said, Claude for Legal comprises several different legal functionalities and partnerships. To help understand framing, Anthropic supplied a few useful definitions, which are used in the descriptions below: 

 

Connector: Links one outside system (a legal tech platform/tool) to Claude 

Skill: A specific thing Claude knows how to do, such as redline a contract; an individual tool 

Plugin: A bundle of Skills, Connectors, and templates for a specific workflow or role; a toolbox curated for a particular job 

Cookbook: Starter code for building Claude into an outside product 

 

20+ New Legal Tech MCP Connectors 
Claude for Legal introduces over 20 new MCP Connectors across several categories of legal tech tools. All are accessible within the Claude interface, subject to user permissions. Pike explained to LTH that users may need separate subscriptions to the third-party tools in order to take full advantage of the Connectors. 

AI Legal Assistants 

Harvey: Harvey's legal intelligence is accessible in Claude, allowing general legal inquiries, analysis over Vault projects, and research questions in certain knowledge sources 

Solve Intelligence: Assists with claim mapping and patent drafting and connects Claude to patent and non-patent literature, legal texts, SEP technical standards, and the web for prior-art searching 

Fiduciary-Grade Workflows

Thomson Reuters: Connects Claude to TR's AI legal assistant CoCounsel Legal for drafting, research, review, and validation across all major practice areas, grounded in Westlaw primary law, Practical Law guidance, KeyCite, and the user's own documents
Contract Tools 

Definely: Addresses contract structure by resolving definitions, validating cross-references, mapping dependencies, and tracking edits across agreements 

Docusign: Connects Claude to agreement data to surface renewal dates, key obligations, and more, and creates automated contract workflows 

Ironclad: Allows Claude to run plain-language searches in contract repositories and workflows  

Legal Research 

Legal Data Hunter: Offers access to over 23 million open-source legal resource documents from more than 160 jurisdictions 

Midpage: Connects Claude to Midpage's case law database for research with hyperlinks to sources 

Trellis: Claude can access Trellis's state trial court dataset for judge and opposing counsel analytics, including dockets, rulings, verdicts, and filings 

Document Management 

iManage: Gives Claude permission-bound, auditable access to iManage content while keeping documents in iManage 

NetDocuments: Claude can search and retrieve documents from a NetDocuments repository in accordance with organizational permissions and governance policies, and draft new documents based on precedents 

eDiscovery 

Consilio: Claude can access Consilio engagement and document data in line with existing user permissions 

Everlaw: Claude can search, organize, and retrieve documents with direct review links from Everlaw projects using metadata, keywords, and document types 

Relativity: Claude can stand up matters, shape workspace schema, govern access, and analyze usage in RelativityOne 

Deal Rooms and Transaction Documents 

Box: Allows Claude to search and access files in Box, query documents, create or update content, and extract metadata fields in accordance with existing security and access policies 

Datasite: Claude can access Datasite's virtual M&A data rooms and set up folder structures, invite users, search documents, track buyer Q&A, and audit data room readiness  

Expert Networks and Skills 

Lawvable: Users can search a library of agentic legal AI skills written by practicing lawyers, in-house counsel, and legal technologists from within Claude 

The L Suite: Claude connects to a knowledge repository from over 5,000 in-house counsel, including discussion threads, playbooks, shared documents, and outside counsel rankings  

A2J and Public Service 

BoardWise: Access to educational guidance for licensed professionals facing state licensing board matters, including jurisdiction-specific response deadlines and structured outlines for response letters 

Courtroom5: Access to legal guidance for unrepresented civil litigants, including jurisdiction-aware case intake, deadline calculation, and next-step guidance across all 50 states  

Descrybe: Claude can access tools for primary law research, including searching cases by concept or citation, checking treatment status, finding citing authorities, and verifying quoted language 

Free Law Project: Claude can access millions of U.S. court opinions, PACER dockets, judge profiles, oral arguments, and citation data in CourtListener 

 

Pike stressed the importance of the legal research category. "We know how important it is for lawyers to be able to ground their work in authoritative and correct information. And so, with these Connectors, you will be able to pull in information from trusted data sources like Midpage and Trellis," he told LTH. "We also have a partnership with the Free Law Project and Courtroom5 to allow you to pull in and ground Claude in authoritative information and do citation checks so that you can feel confident that your final work product is based on real information."

While Claude for Legal includes an MCP Connector to Thomson Reuters CoCounsel Legal, it’s important to understand that this does not offer direct, full access to Westlaw or Practical Law interfaces. Rather, the Connector allows Claude to access CoCounsel Legal’s Westlaw Deep Research tools, offering “a structured research workflow that synthesizes and analyzes Thomson Reuters content to generate cited outputs, drawing from case law, statutes, regulations, and Practical Law resources,” Thomson Reuters CTO Joel Hron explained to LTH. “As the new CoCounsel Legal product enters GA in the coming months, this Connector will expand to expose the full breadth of legal capability offered by CoCounsel, including research, drafting, document review, etc. Access will still require a CoCounsel Legal subscription,” he added.

Thomson Reuters's involvement in Claude for Legal as an MCP Connector is an extension of the company's existing relationship with Anthropic. The company built the latest generation of the CoCounsel Legal platform on the Claude Agent SDK. Now, it's continuing to work with Anthropic to reduce friction in legal workflows.

"As AI becomes embedded across more tools and environments, work can start almost anywhere. The question is where it resolves, and what system ensures it is right," Hron said in a blog post. "Our expanded partnership with Anthropic... reflects how this is starting to take shape. As CoCounsel Legal capabilities flow to general-purpose AI environments, connecting that work directly into professional systems helps ensure it carries through to completion with the rigor required in professional settings. This is less about embedding a system into every interface and more about ensuring that wherever work begins, it can be completed in systems designed to stand behind the result."

For Harvey, joining Claude for Legal was likewise an obvious move, as it was also an expansion of the company’s existing relationship with Anthropic. "Harvey was one of only six companies who were part of Claude's Marketplace launch, so it makes natural sense that we would join forces with them again as they enter the legal market," Harvey Chief Business Officer John Haddock told LTH. "Anthropic remains a critical partner for Harvey and a key input to our product for customers. Their decision to launch a legal plugin doesn't change that for us."

However, the two arrangements work differently, he noted: "Marketplace is a joint GTM motion where customers can use their existing Anthropic commits with Harvey spend. MCP connector is a product integration where customers can access Harvey intelligence directly in Claude." He confirmed that the company is testing the Harvey Connector in private beta with customers and one or two select, publicly available knowledge sources to start. The company's Lexis integration is not available in Claude for Legal via the Harvey Connector. 

12 New Legal Plugins 
Anthropic has now supplemented its original legal plugin for Claude Cowork with 12 new plugins that are specific to a range of legal practice areas. According to the fact sheet, these plugins "bundle together the Connectors, Skills, and subagents for specific legal roles, several of which also have corresponding cookbooks and can be deployed as Claude Managed Agents." Managed Agents are discussed in more detail below. 

The new practice-area plugins and their functionalities are: 

 



 

All the above plugins can be installed in both Claude Cowork and Claude Code. 

When installing a new plugin, users will be interviewed by Claude regarding their individual practices and tool use and receive a tutorial that coaches them on setting MCPs and Connectors in the right way, Pike explained. "When we launched the plugin back in February, I would tell everybody that it's actually best not right out of the box, that you need to give it the context of the way you practice to really get the most out of it," he said. "And this new experience leans into that and has a built-in tailoring experience. So, instead of buying this off the rack, you can get it tailored to your practice." 

Users can customize the existing Skills by layering on their own precedents or playbooks for a given practice area. Anthropic partners can also submit Connectors and Skills for open-source use by Claude users. 

"Because all of these are built on open protocols, in-house teams and law firms can customize Claude and use it to match the way that they actually practice by building on top of this. And partners can use our model to make their own services better," Pike added. 

Microsoft Expansion  
Building on the Claude for Word announcement from last month, Claude now operates as a single agent across Word, Outlook, Excel, and PowerPoint, with context carrying between them.  

"We know that lawyers spend a lot of time in these Office applications, and we've heard a lot of feedback from lawyers that they want to be able to tap into Claude and have it meet them where they are," Pike told LTH. "So, our plugins will work there as well." 

The Word integration handles drafting, redlining, and clause-by-clause comparisons against playbooks, with full change-tracking and reasoning. It also scrubs internal comments before a draft goes to a counterparty, runs final formatting checks on execution copies, and pulls fallback language from approved playbooks. The Outlook integration triages incoming matter work, flagging contract requests, drafting responses, and scheduling follow-ups. The Excel integration handles closing checklists, working group lists, condition-precedent tracking, and more, populated from matter documents and updated as work progresses. The PowerPoint integration turns matter context into assets like board updates, deal status decks, and pitch presentations grounded in precedents and documents. 

Anthropic provided an example tying it all together: 

"An M&A diligence workflow might start as a data room walk-through in Datasite or Box—Claude indexing the room, surfacing the unusual provisions, and flagging the items that need partner attention. From there it becomes a redline against the firm's playbook in Word, a closing checklist in Excel, a board summary in PowerPoint, and a cover note to the client in Outlook—all handled by the Corporate counsel Plugin, with each step reviewed and approved by the lawyer." 

Claude Platform + Managed Agents 
The Claude Platform is Anthropic's developer environment—the toolkit through which users like law firms and legal tech companies build Claude-powered applications that live inside their own infrastructure rather than inside Cowork.  

Cowork is the Anthropic-hosted workspace a lawyer opens to work with Claude as an assistant. The Claude Platform is the architecture a user turns to when they instead want Claude embedded into a system they own, such as a contract intake portal, an internal matter intelligence dashboard, a CLM workflow, a litigation case management interface, or a custom client deliverable pipeline. 

As part of the Claude for Legal launch, Anthropic introduced Managed Agents in public beta, which runs an agentic harness infrastructure on the user's behalf, "handling long-running tasks, controlling system access, and logging every step," according to the media fact sheet. As Anthropic's literature describes it, "Claude Managed Agents provides the harness and infrastructure for running Claude as an autonomous agent. Instead of building your own agent loop, tool execution, and runtime, you get a fully managed environment where Claude can read files, run commands, browse the web, and execute code securely. The harness supports built-in prompt caching, compaction, and other performance optimizations for high-quality, efficient agent outputs." 

With Managed Agents in the Claude Platform, users don't manage the workflows; they review and approve the outputs. 

Four of the new legal practice-area plugins announced—Commercial counsel, Corporate counsel, Litigation counsel, and Product counsel—are also available as cookbooks that can be deployed in the Claude Platform as Managed Agents. Think of this as the starter code engineers use to build Claude into their own product, but available as an open-source recipe that turns a plugin's logic into deployable Platform code.  

Whereas Claude Cowork is a workspace, Managed Agents is infrastructure. Rather than replacing legal tech providers, Anthropic is allowing them and other legal users to build products on top of Anthropic's models and architecture. 

Anthropic's Deliberate A2J Moves 
Access to justice plays a significant role in Anthropic's Claude for Legal announcement. "It's really important to me that AI legal tooling isn't leaving the Public Service realm behind," Pike told LTH. "I know that legal services are just out of reach for many people and small businesses, and that gap's widening. And so, working with organizations like the Free Law Project, the Justice Technology  Association, and others to help make these types of services more affordable and available will hopefully democratize access, which is in furtherance of Anthropic's mission." 

In addition to the company's partnerships with A2J organizations and MCP Connectors into BoardWise, Courtroom5, Descrybe, and the Free Law Project, Pike emphasized that "qualifying legal aid clinics, public defenders, and nonprofit legal service organizations can gain access to these tools, and we have significantly discounted pricing through our Claude for Nonprofits program." 

We'll dive deeper into Anthropic's A2J commitment and how it plays out in Claude for Legal in a separate article. 

Final Thoughts 
With the launch of Claude for Legal, Anthropic's intentions to serve the legal market are no longer in question.  

The announced Connector list runs through nearly every meaningful category of legal technology—AI legal assistants, contracts, eDiscovery, document management, legal research, deal rooms, expert networks, public service—and includes some of the biggest vendors in each category. The new plugins cover a wide swath of legal practice areas from transactional to litigation and everything in between. The Claude Platform layer with Managed Agents provides a critical infrastructure layer for legal partners to build on. 

What's also clear is that Anthropic is not looking to replace the existing legal tech ecosystem, as many have speculated. Pike's rising-tide and better-together framing, along with the company's willingness to work with—not against—many of the industry's biggest players evidence as much. 

Harvey's experience with Anthropic further confirms it. "Claude for Legal is a great plugin for individual lawyers and non-lawyers to use and brings Claude's consumer-grade capabilities to the market for solo practitioners," Haddock told LTH. "Its arrival on the market doesn't change the daily experience for Harvey users at all."  

Today's announcement is one of product evolution. We've seen Anthropic advance from a layer of prompts and slash commands to a full vertical ecosystem in a matter of months. "If you had told me a few years ago when I started at Anthropic that the best model in the world for coding would also be good for legal work, I would have been shocked," Pike said during the April 24 webinar. "But it turns out, you don't need to fine-tune models to give Claude, the engineer, a legal degree. Instead, you just need to give these tools access to the same tools that the lawyers use every day to get their work done, and that's what helps it become a great teammate within the legal context." 

At least for now, Anthropic's intention to coexist productively with the legal tech ecosystem seems clear. How the market chooses to react to today's announcement, of course, is another question.]]></description>
<dc:subject>ai access</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:7828d4b8cbc8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:access"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://free.law/2026/05/12/courtlistener-is-now-available-inside-claude/">
    <title>AI Tools and Assistants such as Claude Can Now Connect to CourtListener's Full Functionality | Free Law Project | Making the legal ecosystem more equitable and competitive.</title>
    <dc:date>2026-05-15T18:55:21+00:00</dc:date>
    <link>https://free.law/2026/05/12/courtlistener-is-now-available-inside-claude/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Legal information is everywhere. Actually using it has always required either deep expertise or an expensive subscription to a gated research platform. For more than 15 years, Free Law Project has been building the data infrastructure to change that. CourtListener is one of the largest free legal research platforms in the world, built on the belief that the law belongs to everyone.

But access to data is only half the problem. Increasingly, people start their legal questions with AI. That presents a real risk because AI tools often answer legal questions without grounded access to primary sources. This can produce confident responses built on hallucinations rather than real case law.

The same barrier we have spent years dismantling is reappearing in a new form. People can reach the law, but they still cannot trust what they are being told about it. This integration directly addresses that.

What we built
MCP (Model Context Protocol), is an open standard that lets AI models connect to external data sources and tools. Think of it as a direct line between Claude and the systems that hold real-world information — in this case, CourtListener's legal database and utilities

Our MCP server gives Claude and other AI assistants access to:

Case law and opinions — millions of federal and state court decisions going back centuries
PACER/RECAP dockets and filings — the largest open repository of federal court cases, parties, and documents
Citation networks — what cases cite, and what cites them
Oral arguments — a huge trove of searchable audio and transcripts from federal appellate courts
Judge data and financial disclosures — biographical and analytical records on the federal judiciary, including assets and debts that may trigger conflicts of interest
Keyword and semantic search — both keyword and natural language search across our full archive
Alerts — real-time monitoring for new filings, citations, and search queries
Citation verification — grounded citation checks to reduce hallucinations
For our most heavily used functionality, including search, citation verification, and alerts, we built dedicated tools so Claude can use them reliably out of the box. For the rest of the CourtListener API, rather than creating a tool for every endpoint (which would consume too much context), we provide two generic tools: get_endpoint_schema and call_endpoint. These allow Claude to discover available filters and parameters for any endpoint and query it directly.

A dark-background network graph showing citation relationships between Chaplinsky v. New Hampshire (315 U.S. 568, 1942) and Cohen v. California (403 U.S. 15, 1971). Nodes represent cases from 1919 to 1971, color-coded by citation relationship: orange for cases cited only by Chaplinsky, purple for cases cited by both, teal for cases cited only by Cohen, and grey for the two focus cases. Colored arcs connecting the nodes represent direct citations and shared precedents.
A response to the prompt: "Make a network visualization that connects the citations between Chaplinsky v. New Hampshire (the 'fighting words' doctrine) and Cohen v. California in the case law database."
What you can do with it
Because this data now lives inside a conversational AI interface, you can do things that were not possible before, all in a single conversation without a high cost.

Legal researchers can pull citation networks across jurisdictions, analyze how legal language has shifted over time, trace the lineage of a doctrine from its origins to today, and visualize it all.

Lawyers and legal aid organizations can surface relevant dockets and case history without an expensive subscription, search filings, pull opinions, and verify citations inside a single workflow.

Journalists and policy researchers can investigate judicial behavior patterns, track litigation trends across courts, and dig into public court records without specialized tools.

Court watchers can Subscribe to dozens of cases or search queries and manage case or search alerts right within their AI assistant.

Developers and legal tech builders can prototype AI-powered legal applications with direct access to structured, primary-source legal data through a standardized interface.

Self-represented litigants can understand what has been filed in their case, find analogous cases, and get grounded answers to legal questions backed by real primary sources, not generated text.

Here is a sampling of prompts to try:

"Find recent opinions on qualified immunity and identify circuit splits"
"Pull the latest filings on [docket number] and explain what is happening"
"Make me an alert any time Miranda v. Arizona is cited by the Supreme Court"
"Verify every citation in this brief and flag anything that looks off"
"Draft a memo on how circuits have treated [legal issue] and cite the leading cases"
"Find the status of [a given case] and tell me what's next for it"]]></description>
<dc:subject>ai access</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:444e9e39004a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:access"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.theatlantic.com/international/2026/05/iran-war-trump-losing/687094/">
    <title>Checkmate in Iran - The Atlantic</title>
    <dc:date>2026-05-15T18:54:54+00:00</dc:date>
    <link>https://www.theatlantic.com/international/2026/05/iran-war-trump-losing/687094/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[It’s hard to think of a time when the United States suffered a total defeat in a conflict, a setback so decisive that the strategic loss could be neither repaired nor ignored. The calamitous losses suffered at Pearl Harbor, the Philippines, and throughout the Western Pacific in the first months of World War II were eventually reversed. The defeats in Vietnam and Afghanistan were costly but did not do lasting damage to America’s overall position in the world, because they were far from the main theaters of global competition. The initial failure in Iraq was mitigated by a shift in strategy that ultimately left Iraq relatively stable and unthreatening to its neighbors and kept the United States dominant in the region.

]]></description>
<dc:subject>global stratfor</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:4d2e4e820322/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:global"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:stratfor"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law360.com/pulse/modern-lawyer/articles/2473585">
    <title>AI Native Firms Gain Foothold In Changing Legal Industry - Law360 Pulse</title>
    <dc:date>2026-05-15T18:48:54+00:00</dc:date>
    <link>https://www.law360.com/pulse/modern-lawyer/articles/2473585</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA["AI native" law firms are a growing phenomenon sitting at the intersection of artificial intelligence and rising tide of outside investment in the legal industry, aiming to use legal technology to automate work and overhaul the law firm business model — while doing away with the billable hour in the process.

AI native firms are something akin to a law firm version of a startup, raising money from venture capitalists through managed services organizations and drawing the expertise of BigLaw veterans.

Josh Porte and Trisha Rich, partners at Holland & Knight LLP who represent firms looking to take on outside investment, said they're working with about 10 AI native firms that aim to launch as soon as possible.

"The idea is that you can get a team of extremely well-heeled corporate lawyers and get in on the ground floor to construct and train the model, using their knowledge and expertise," said Porte. "[It's] not to replace their judgment, but it could certainly get to the point of being very useful.

"If you're getting midlevel associate work product [from AI], for instance, that's quite powerful and has all sorts of implications for the profession," he added.

But given the limited reach of the large language model technology for certain practice areas, it remains to be seen how broadly applicable the firms' approach will be, while ethics concerns continue to surround the role of outside investments in the legal sector.

"An Enormous Market"

The term "AI native" has recently become a popular way to market a law firm, with even some BigLaw firms trying to position themselves as AI native — to the frustration of some would-be clients. However, in general the term refers to law firms that were founded with generative-text legal tools as an integral part of their workflow and business model.

Examples range from Norm Law LLP — the law firm arm of Norm AI that is now helmed by former Sidley Austin LLP executive committee member Mike Schmidtberger and focuses on institutional clients — to more startup-like firms such as Crosby.ai, which focuses on contract review work, and Lexsy PC, which itself provides legal services for startups.

"In an AI native firm, the objective is that you create AI agents that are sufficiently trained on areas of work such that the first pass of work is done autonomously," said Schmidtberger. For instance, at Norm Law, he said, when the firm receives a term sheet for a transaction, it is automatically routed to an AI tool that will generate a first draft immediately.

AI native firms tend to focus on niche areas with the type of repeatable work that LLMs do well with, such as drafting contract language for standard agreements, which is then reviewed by human attorneys.

One recent AI native firm to announce a successful funding round, California-based Moritz, offers on its website a host of services priced per matter, such as a nondisclosure agreement for as little as $300 or an "intercompany agreement" starting at $1,500. The firm, headed by Norwegian attorney Pamir Ehsas, announced this week it has raised $9 million in funding. The firm did not reply to a request for comment.

Funders of AI native firms include notable names like Blackstone, Y Combinator and Bain Capital.

Christina Melas-Kyriazi, managing director on the ventures team at Bain Capital, which funded Crosby, said that in many ways, the law firm was like any other startup with potential: It was driven by the vision of its founder, Ryan Daniels, who successfully pitched it to Bain. And the advent of LLMs and other legal technology also made this a logical time to invest in legal, she said.

"If you look at the end market of law, at how much is spent on legal services globally, it's an enormous market," said Melas-Kyriazi. "I think we were always excited about companies that were building in the legal domain, but AI was the 'why now.' ... There's this new model that's really exciting."

With their technology, AI native firms say they're able to offer lower-cost legal services to clients.

That's because AI native firms typically are not billing by the hour, finding other structures such as pricing by matter or by document.

At Lexsy, founder Kristina Subbotina said, the firm uses a subscription model, with clients buying annual or monthly subscriptions that come with credits they can then apply to different service offerings.

Thus far, she said, the model has been well-received by Lexsy's clients, who are startups and tend to be displeased with unexpectedly large invoices. "A big thing for them is being able to budget," she said. "They got hit with big bills from BigLaw, and this model eliminates that. They're really happy with that."

While AI native firms prize being more efficient and cost effective than traditional law firms, they remain a relatively niche phenomenon. But proponents say that may change as the technology improves or as firms perfect their strategy.

"My sense is that this will be applicable to the entire legal industry over time," said Melas-Kyriazi, though she added that it will likely take much longer to encroach on some practice areas than others.

Schmidtberger takes a more conservative view, saying that it's unclear to him if firms will ever be able to automate things like litigation work to the degree that AI native firms rely on. At the current level, he added, the technology can't produce high quality work on more sophisticated transactions; however, as the tools Norm Law uses are refined and further trained on the firm's work, he said it will likely continue to improve.

"It is really extraordinary how powerful these AI tools and technologies have become in a short period of time," he said. "It's a very interesting time."

"It Raises a Lot of Questions"

AI native firms are also part of the larger trend of more outside investment coming into the legal sector.

In Arizona and some other jurisdictions where nonlawyers can own law firms, many investors are looking to do so; in other jurisdictions, investors are putting money into law firms through a managed services organization structure, an approach by which a law firm splits its back office into a separate legal entity that does not practice law and thus can sell a stake to nonlawyers.

AI native firms use the same legal structure — both Lexsy and Norm AI confirmed they are using MSOs to take investor dollars — but rather than spinning off part of an existing firm and using the outside capital to invest in the firm or to cash out upon retirement, these firms tend to function like startups, using investor money to stand up operations in the first place.

Under this model, the MSOs own the technology backing the law firm's operations, while the attorneys work for the law firm.

Similar to other MSOs the involvement of outside investors in AI native firms also raises concerns about lawyers' independence.

MSO proponents argue the structure keeps nonlawyers at arm's length from the practice of law, ensuring they cannot interfere with a lawyer's professional judgment. However, if the MSO owns the technology that is integral to the firm's output, that makes it hard to draw a firm line between the two, said Hilary Gerzhoy of Gerzhoy PLLC, a legal ethics practitioner and chair of the D.C. Bar Rules of Professional Conduct Review Committee.

"It raises a lot of questions about ensuring these are discrete functions," she said. "If a lawyer overseeing [the AI] does not own or control it, the firm and the lawyers are susceptible to pressures of the MSO. ... I don't know how that will work in practice."

This is especially true if the LLM tools are training on lawyers' own work in order to be more specialized, she added, saying that would make it potentially fraught for lawyers to risk losing access to those tools in a way not analogous to other legal tech.

When asked, Rich acknowledged that this was "a really serious regulatory and ethics question" that an AI native firm should think through before launching. However, she argued, it was still possible to structure deals in a way that ensured compliance with ethics rules.

"Everything is happening at once," said Porte of Holland & Knight. "There's money flowing in from private financing at the same time technology is changing what it means to practice law. The dominant theme is uncertainty in terms of what these trends mean for the practice of law."
]]></description>
<dc:subject>ai ai-first firms associates</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:1348feaf70c8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai-first"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:firms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:associates"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/05/06/wolters-kluwer-launches-invoice-review-ai-agent-for-in-house-teams/">
    <title>Wolters Kluwer Launches Invoice Review AI Agent for In-House Teams | Law.com</title>
    <dc:date>2026-05-15T18:46:43+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/05/06/wolters-kluwer-launches-invoice-review-ai-agent-for-in-house-teams/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[On Wednesday, information services company Wolters Kluwer announced the launch of its LegalVIEW BillAnalyzer Invoice Review Agent, an agentic artificial intelligence tool for legal spend management.

The announcement comes a little over a month after the company expanded the launch of Libra, its legal AI workspace, to the Czech Republic, Slovakia, Hungary and Romania.

What It Is: The LegalVIEW BillAnalyzer Invoice Review Agent is an AI-powered assistant that supports corporate legal teams in managing billing invoices and maintaining compliance.

The agent can perform tasks including automatically adjusting invoices based on in-house legal billing requirements, providing explanations for adjustments and producing summaries of the adjustments made and cost drivers.

“We [already have] AI-fueled, expert-driven bill review; we have a business that we've had for 10 years where we have lawyers who have come out of practice and who review bills for our clients with some older, machine learning AI in the background,” Dean Sonderegger, senior vice president and general manager of Wolters Kluwer Enterprise Legal Management Solutions business told Law.com. “We looked at that combination of things; we said we should be able to take emerging technology and build agentic AI to automate this to substantially reduce the amount of time it takes people to do bill review.”

Why It’s Needed: Sonderegger said the AI agent came about from the company noticing that in-house legal teams want to more easily track and reduce spending and more quickly figure out what they’re spending money on.

“You see two drivers in the legal market for corporate legal right now. The first driver is that they obviously want to reduce spend, outside spend. ... The second thing is just an issue of time and what you spend your time on,” Sonderegger explained. "When you look at that and then you overlay the hopes of artificial intelligence as it changes our world, that it has the ability to automate things and give us more insight or make better decisions, hopefully, and when we thought about this, we said, ‘What is something that people spend a lot of time doing?’ That is the review of the invoices.”

Under the Hood: Wolters Kluwer’s invoice analyzing AI agent is built on OpenAI’s GPT-5.4 and GPT-5.4 mini large language models and a decade’s worth of invoice review data and experiences that help in navigating the varying complexities of invoice adjustments. The agent orchestrates 10 other agents that can complete more specific tasks depending on the user’s request.

“Certain types of line items will get certain types of agents because there's a lot of nuances. To give you an example, you could have one adjustment where a partner has done a paralegal task and you see this come through at the partner rate and so what you do at that point in time is you say, ‘OK, we're going to adjust that back down to a different rate from that from a rule.’ That's a very different situation than say I have a first-year associate billing, and we've said that's disallowed or there's things where there's approval required,” Sonderegger said.

Competition: While other legal tech companies like enterprise legal management and contract life cycle management company Onit and invoice management platform Oddr leverage generative AI to perform invoice management, the LegalVIEW BillAnalyzer Invoice Review Agent is focused on automating the individual needs and requirements legal teams have when it comes to adjusting their invoices.

“It's not just the review process; it's what are the rules, the exceptions—all those things—and how do I codify those? So that's a differentiation point because these things are quite complex and they tend to change over time,” Sonderegger said. He added that competitors might flag discrepancies but won’t make the adjustments in the way that LegalVIEW BillAnalyzer does.]]></description>
<dc:subject>clients pricing ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:0de0b6497035/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:clients"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:pricing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/05/06/perkins-coie-turns-to-ai-avatars-to-train-lawyers-on-soft-skills/?kw=Perkins%25252BCoie%25252BTurns%25252Bto%25252BAI%25252BAvatars%25252Bto%25252BTrain%25252BLawyers%25252Bon%25252BSoft%25252BSkills&amp;utm_position=2&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803">
    <title>Perkins Coie Turns to AI Avatars to Train Lawyers on Soft Skills | Law.com</title>
    <dc:date>2026-05-15T18:43:26+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/05/06/perkins-coie-turns-to-ai-avatars-to-train-lawyers-on-soft-skills/?kw=Perkins%25252BCoie%25252BTurns%25252Bto%25252BAI%25252BAvatars%25252Bto%25252BTrain%25252BLawyers%25252Bon%25252BSoft%25252BSkills&amp;utm_position=2&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Perkins Coie’s London office is beta testing a new training program using generative artificial intelligence-powered avatars developed in partnership with AI training platform Levra.

The avatars are designed to help lawyers of all experience levels simulate conversations with colleagues to build their soft skills, an area that Perkins Coie managing partner Ian Bagshaw told Law.com can also improve client services.

Founded in 2022, Levra provides professionals across industries with avatars that act out training simulations focused on how to approach scenarios related to emotional and social intelligence to help develop networking, collaboration, conflict resolution and delegation skills.

“We're working with [Levra] in order to create a training pathway across core skills that allows our talent to practice, learn, practice outside of client situations so that when they're in client situations and when they're in difficult internal situations, they are prepared, they've seen it before, they understand how best to communicate,” Bagshaw said.

He added that when lawyers master these interpersonal skills and feel confident, it trickles down to how they will advise and make decisions involving clients.

“Clients want a trusted adviser as a lawyer, clients want value for money from that trusted adviser, and if you hit both of those metrics, you'll get a repeat business relationship,” Bagshaw said. “Repeat business relationships not only build careers, but build law firms.”

The firm began its relationship with Levra in the first quarter of this year. Bagshaw said the gen AI avatar method has worked well so far during its testing, specifically because it is visual and interactive.

“With highly intelligent people, the content has got to be at the right level, the production has to be at the right level that inspires confidence in the content, and you want it to be interactive and the best form of interaction is simulating a real life scenario,” Bagshaw said. “That could be like a message exchange, an email exchange, WhatsApp exchange, or it could be simulating a video call. The most interactive experience, the one that's easiest to use with maximum benefit is a video call. The use of an avatar is accelerating the experience and making it the easiest to use.”

Bagshaw explained that technology like the gen AI avatar provides a safe space for users to comfortably fail, learn from their mistakes and maintain confidence.

“The key thing is making it acceptable for people to fail as part of a learning experience and in a law firm environment, that's often when people crave perfection, any criticism can cause people to lose confidence, not want to attempt something that may risk them failing,” Bagshaw said. “Now, the use of technology creates an absolute safe space for people to experiment in these modules and that safe space. It's very hard to recreate it in any human coaching environment. One of the unexpected outcomes is people enjoy Levra because they feel totally confident that what's between them and the avatar stays between them.”

This year, a growing number of legal tech companies have begun providing simulation training tools for legal professionals performing different tasks.

In February, legal training provider AltaClaro and legal transcription provider Verbit launched their AI-powered deposition simulator DepoSim, which they developed together.

Also in February, legal training provider Hotshot announced its partnership with Stockholm-based legal AI company Legora and said it planned to develop simulated matters that will allow users to practice deploying Legora in workshops before applying it to live client matters.]]></description>
<dc:subject>ai training competence</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:af432f2ad86f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:training"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:competence"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://alameda.institute/after-order/">
    <title>AFTER ORDER | ALAMEDA</title>
    <dc:date>2026-05-15T18:42:31+00:00</dc:date>
    <link>https://alameda.institute/after-order/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[In a time of apparent disorder and instability, questions abound as to where power is located. Who is in control? Who makes decisions on the big issues that affect people’s lives?

And so the concept of sovereignty, widely presumed to have been exhausted by globalisation, is now again central to discussions about our present and future. Analysing how sovereignty is exercised today, amid political, social, and economic fragmentation, can provide valuable insights into the new possibilities these transformations entail.

About Alameda's After Order Project
Questioning the assumption that we are now in an interregnum, a temporary period between stable orders, Alameda’s ‘After Order’ research project considers the possibility that we have entered a time of more frequent crisis – a time after stable orders. 

Through dialogue, and critical engagement, this collaborative research initiative explores the dispersion of claims to sovereignty, the disputes these claims have produced, and the implications for efforts to build new pathways – alamedas – to a better society.]]></description>
<dc:subject>global stratfor</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:59e5f9800785/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:global"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:stratfor"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.ft.com/content/35d63fa0-7175-4204-9ba8-5a0c1f10ba5a?shareType=nongift&amp;syn-25a6b1a6=1">
    <title>How top Wall Street law firms became a pipeline for insider trading</title>
    <dc:date>2026-05-15T18:41:32+00:00</dc:date>
    <link>https://www.ft.com/content/35d63fa0-7175-4204-9ba8-5a0c1f10ba5a?shareType=nongift&amp;syn-25a6b1a6=1</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Lawyers at Goodwin Procter were representing iRobot, maker of the automated Roomba vacuum cleaners, as talks to be acquired by Amazon heated up in the summer of 2022.


Please use the sharing tools found via the share button at the top or side of articles. Copying articles to share with others is a breach of FT.com T&Cs and Copyright Policy. Email licensing@ft.com to buy additional rights. Subscribers may share up to 10 or 20 articles per month using the gift article service. More information can be found at https://help.ft.com/faq/gifting-and-sharing-an-article/what-is-a-gift-article/.
https://www.ft.com/content/35d63fa0-7175-4204-9ba8-5a0c1f10ba5a?shareType=nongift&syn-25a6b1a6=1

In the following months, according to US authorities, a network of more than a dozen people — including three brothers and a hairdresser — began amassing iRobot stock and options. When a deal was announced that August, the group allegedly netted more than $1.7mn in profits; two members of the ring texted each other with champagne emojis.

US prosecutors and securities regulators now say they were working off intelligence that came from inside Goodwin Procter itself.

In criminal charges unsealed on Wednesday, prosecutors said Nicolo Nourafchan, a 43-year-old Yale Law graduate who worked at elite firms Sidley Austin, Latham & Watkins and Goodwin, was at the centre of a decade-long insider trading scheme.

This alleged scheme extended from the halls of Ivy League law schools to Wall Street law offices to pilfer confidential deal information from the firms and feed it to a web of friends and contacts.

Authorities have charged 30 individuals. The Securities and Exchange Commission separately filed civil charges against 21 individuals.

Advising on mergers and acquisitions has become one of the most lucrative areas of business for Wall Street law firms, with even junior associates now earning hundreds of thousands of dollars a year. The work makes firms custodians of confidential information on multibillion-dollar public company transactions, leaving them little choice but to put their faith in their employees.

“What’s outstanding about this is it was a really comprehensive plan over almost a decade to mine law firm information for serial mergers,” said David Axelrod, a litigator at Ballard Spahr and former US prosecutor.

In a statement, Goodwin said: “We are deeply disappointed that a former employee is alleged to have violated the trust placed in him and misused confidential information as part of a broader criminal scheme affecting multiple law firms and their clients.”

Over the course of a decade, Nourafchan allegedly passed information on pending deals to his George Washington University college classmate Robert Yadgarov and others.

Nourafchan and Yadgarov, who has his own personal injury practice, also recruited two other early-career corporate lawyers to share information, according to prosecutors.

In 2014 they allegedly involved Avi Sutton, according to multiple people familiar with the matter as well as matching information from the indictment with public records. Sutton attended Yale Law School with Nourafchan and was working at Wachtell when he allegedly shared his first tip, regarding Burger King’s imminent acquisition of Tim Hortons. He has not been indicted, and appears as an unnamed co-conspirator in one of the indictments.

A few years later, Nourafchan began socialising in New York City with another George Washington classmate, Gabriel Gershowitz, whom he knew was also an M&A lawyer.

Nourafchan and Yadgarov taught him about the scheme and told him they’d earned “several million dollars in illicit profits”, according to the SEC complaint.

Gershowitz, a graduate of Columbia Law School, was working at Weil Gotshal in 2019 when he allegedly began sharing tips.

An attorney for Gershowitz declined to comment. Sutton could not be reached for comment. Attorney information for Nourafchan or Yadgarov could not be found.

According to prosecutors, the friends shared tips on nearly 30 deals involving such companies as Johnson & Johnson, Qualtrics and Occidental Petroleum. Traders allegedly made a collective tens of millions of dollars of illicit profits.

The lawyers were paid kickbacks from the trading proceeds, according to prosecutors. In the first five years of the scheme, Yadgarov allegedly collected more than $6.3mn in kickbacks from a single trader based in Russia, some of which he passed on to the other lawyers.

A former friend and law school classmate of one of the lawyer defendants told the FT that even as dealmaking was a glamorous and high-paying profession, the pressure to keep up a lifestyle with peers in New York City created a crushing demand for cash.

As Nourafchan attempted to convince Gershowitz to join the scheme in 2018, he explained to his friend how he accessed information on deals, according to the SEC complaint. Nourafchan said he viewed documents in the firm’s document management system “in preview or read-only mode” to minimise detection, the complaint says.

Prosecutors alleged he at times accessed documents from deals he was not assigned to work on, including the iRobot deal. Nourafchan, while on a “leave of absence” from Goodwin, accessed a draft merger agreement and other files, according to authorities.

In the iRobot deal, a childhood friend of Nourafchan’s met with a trader at a Florida casino to share the tip, according to authorities. The childhood friend also shared information with the three brothers, authorities allege, who had a WhatsApp chat group called “Brothers in the Market.”

Nourafchan also allegedly tipped off his brother Lorenzo to the pending transaction, who told his hair stylist who told a friend.

Ahead of the public deal announcement, the hair stylist’s friend bought iRobot shares and out-of-the-money call options, according to prosecutors. When Amazon announced it was acquiring iRobot in August, the friend texted the hair stylist: “You were right.” Amazon and iRobot later abandoned the deal.

“You have to wonder how so many smart folks thought that this would work,” said Bill Singer, a former regulatory defence lawyer. “It did work and flourished for a decade, so maybe the smart folks were smart, but not smart enough for the long haul.”

Another instance in the indictments involves the investment bank LionTree, where Sutton began working in 2022. He was the bank’s general counsel and as recently as last week was listed on LionTree’s website as part of its executive leadership.

The following year, Sutton allegedly shared a tip with Yadgarov related to a potential acquisition of Adevinta, as LionTree was advising one of the online classifieds company’s largest shareholders.

LionTree said in a statement, “We are aware of the filing identifying LionTree as one of many victims in this alleged scheme. There are no allegations of wrongdoing against the firm. The individual in question was immediately placed on leave and is no longer active at the firm.”

“No matter how strong a firm’s training, policies and procedures are, it is still unfortunately possible for a bad apple to breach client confidences and break the law,” said Josh Naftalis, a litigator at Pallas Partners and former federal prosecutor.

Wachtell and Latham said in statements that the accused individuals had not been associated with the firms for several years, stressing that both individuals acted in contravention of their policies and the firms were not accused of wrongdoing.

Weil said in a statement that the alleged conduct was “extremely serious” and that the accused individual had not been associated with the firm in over six years. It also noted that the firm was “among the victims of the alleged scheme.”
]]></description>
<dc:subject>fraud ethics regulation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:9267a227e665/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:fraud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ethics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:regulation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law360.com/pulse/modern-lawyer/articles/2470293?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0">
    <title>Law Firm Dissolutions Are Becoming More Common - Law360 Pulse</title>
    <dc:date>2026-05-15T18:40:40+00:00</dc:date>
    <link>https://www.law360.com/pulse/modern-lawyer/articles/2470293?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[McGlinchey Stafford PLLC and Taylor Duma LLP are two midsize law firms that closed their doors this year, but they aren't alone. Ten total firm dissolutions as of the end of the first quarter put the industry on track to reach a six-year high if the pace continues.

In a sector where combinations are a more common strategy than dissolutions when a law firm struggles, and midsize firm dissolutions occur just a handful of times a decade, the closures this year stand out.

The 10 first quarter closures — as tracked by legal intelligence provider SurePoint — represent more than triple the average number of first quarter dissolutions between 2020 and 2022 involving U.S. law firms with five or more lawyers.

"We're getting to the point where firms operating in that mid-market have to come up with something that will allow the firm to grow, or diversify, or be unique and stand out, or the business might just fold," said Phil Flora, vice president of sales at SurePoint.


Kristin Stark, a principal at Fairfax Associates who advises law firms on mergers and acquisitions, said her team is seeing a relatively large influx of interest in combinations this year. U.S. law firms announced 25 combinations during the first quarter of 2026, an increase over the previous year's first quarter, according to the Law360 Pulse Merger Tracker.

"We're definitely seeing more merger interest," Stark said. "Some of that is proactive… Then there are other firms starting to see breakage. They're starting to lose people, they aren't getting as many lateral opportunities and so they're declining in size."

The 10 closures so far in 2026 follow three years in which the full-year number ranged from 29 to 34, according to the data from SurePoint. There was a significant shift in 2023 from earlier years.

In the three years preceding 2023, the number of dissolutions ranged from seven to 16.

It was hard for me to put a finger on a single reason for why the industry saw the significant jump in dissolutions in 2023, a new high that has been sustained since. I spoke to several law firm management and merger consultants, as well as legal recruiters, for this article and two responses came up most: A lack of succession planning for the aging baby boomer owner cohort and the accelerated movement of large law firms into smaller legal markets.

Robert Kamins, a management consultant to law firms at Vertex Advisors, is seeing a theme in the law firms that come to him seeking help looking for ways to figure out generational transfers and succession planning. The youngest baby boomers are 62 this year.

"The baby boomer impact is really significant, especially for founder-run firms," Kamins said. "Those firms can either implement a succession plan or close. But many don't have a plan and they don't have the next generation to step up and lead the firm."

The longevity and style of leadership that was commonly adopted by the boomer generation is one reason for why this transition has been harder for many firms than it has been for other generations, Kamins said. That style includes a top-down structure and less collaboration, which means fewer junior lawyers are prepared to take the reins, he said.

Another major shift in the industry that was put into motion in 2020, but continued to play out in the years that followed, was the shift to remote and hybrid work at law firms, Kamins said.

"Based on anecdotal conversations, law firms aren't the same as they used to be. People aren't going in and they don't have the same vibrancy of culture. It's a demarcation point of sorts," he said.

The loosening of the ties that bind people together in law firms has been one factor in the increased lateral movement in the industry. Additionally, it's simply more common now across industries for workers to have multiple jobs over the course of their careers than it once was.

That makes lateral departures one of the largest risks smaller law firms face, the experts said.

"When firms start to lose people and feel like they're not getting lateral opportunities, they begin to stagnate from a growth perspective," Stark said. "Then you have retirements and firms experience more fragility."


Plus, there's been new pressure on some regional law firms when it comes to that need to retain people and attract others to avoid shrinkage: the entry of BigLaw and national midsize law firms into new markets over the last several years.

"New firms have moved to town and established a strong presence," said Raj Nichani, a legal recruiter in Atlanta at The RMN Agency. "By doing that it ups the level of the game in the community."

Atlanta is one of several markets that has experienced an influx of large law firms, and much of the activity began around 2023, Nichani said. Some other smaller legal markets that have been targeted recently for new office openings include Nashville, Tennessee; Miami; Salt Lake City; Charlotte, North Carolina; Denver; and Austin, Texas.

"With the new firms coming into town, there's only so much supply [of talent]," Nichani said. "The demand right now is outweighing supply. A lot of people are being courted by the larger law firms and other brand names coming to town."

Too many departures can create "radical instability" and law firms, in most cases, will seek a "hail mary pass" merger, according to Stark.

"When a firm is that close to dissolution, you have to move very quickly to find a firm willing to do a combination," she said.

In some cases, according to Kamins, law firm management begins the process of finding a merger partner after they're too far gone to bring the organization back from the brink.

"A lot of times my phone rings when it's too late for firms," he said.]]></description>
<dc:subject>consolidation firms mergers</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:fe19051ad2ba/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:consolidation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:firms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:mergers"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://abovethelaw.com/2026/04/clearyx-bets-that-biglaw-disruption-is-inevitable/">
    <title>ClearyX Bets That Biglaw Disruption Is Inevitable - Above the Law</title>
    <dc:date>2026-05-15T18:39:45+00:00</dc:date>
    <link>https://abovethelaw.com/2026/04/clearyx-bets-that-biglaw-disruption-is-inevitable/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[For all the Biglaw posturing about “leaning into AI,” the tasks that AI is best suited to perform are tasks where clients really don’t need outside counsel pushing the button. Whatever the tool, clients will find a product capable of moving expensive yet automatable work in-house. Trying to cling to that business over the next few years will just end in massive write-downs, frustrated clients, and damaged relationships. With ClearyX, the firm continues to profit from the natural migration of that work while doubling down on the tasks outside counsel have to perform. And even though ClearyX is a separate entity and not necessarily tied to Cleary’s existing client base, it offers a warmer handoff if a client using a product developed by the Cleary brand eventually needs to hire human outside counsel for higher level work.

]]></description>
<dc:subject>firm ai innovation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:b64898d19647/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:firm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:innovation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/international-edition/2026/04/29/why-ai-is-making-the-top-lawyers-more-expensive/print/">
    <title>Why AI Is Making the Top Lawyers More Expensive | Law.com</title>
    <dc:date>2026-05-15T18:28:07+00:00</dc:date>
    <link>https://www.law.com/international-edition/2026/04/29/why-ai-is-making-the-top-lawyers-more-expensive/print/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[AI will widen the inequality between labour and capital inside the legal profession, just as it’s starting to do in every other industry it has touched. Firms with capital can win the talent war today and rebuild the operation around the question every senior partner should be asking: if we were starting this firm today, what would it look like? They are building structurally different platforms — long-term incentives that bind rainmakers to the institution, and proprietary systems that accumulate value year on year.

Firms without capital will get efficiency gains. Drafting, research and review will get cheaper and faster. They will become better versions of the firms they already are. But the value will keep walking out the door with the partner.

As that gap becomes more visible, partners are going to start asking a different question. Not “what is my share of this year’s profits?”, but “what is my stake in the long-term value of this platform?”. Taking your share of this year's profits and walking out empty-handed is a fair deal when the firm itself has no lasting value. When the platform is steadily growing in value, it isn't.

The question is hard but not unanswerable. And the answers are not only available to firms with private capital behind them. The partners who confront the question now will help shape what comes next. The ones who wait will live with what others decide.]]></description>
<dc:subject>ai firms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:b1fad38ecde9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:firms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.attorneyatwork.com/data-driven-law-firm-valuation/?mc_cid=8b76962049&amp;mc_eid=93b1286af1">
    <title>Law Firm Valuation: For MSO Deals, It's All About the Data</title>
    <dc:date>2026-05-15T18:14:14+00:00</dc:date>
    <link>https://www.attorneyatwork.com/data-driven-law-firm-valuation/?mc_cid=8b76962049&amp;mc_eid=93b1286af1</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[For Private Equity Deals, It’s All About the Data

Recently, I was talking with Chad Dudley in preparation for a panel I’ll be speaking on at Mass Torts Puerto Rico. If you don’t know Chad, then Google “Dudley Debosier private equity” and check out the articles in The Wall Street Journal and Financial Times about this landmark deal. Somewhere in the middle of our conversation on management services organizations (MSOs), Chad said something that should make every law firm owner a little uncomfortable:

MSOs don’t set their fees based on what you earned last year. They set them based on what they believe you’re going to earn next year.

Let that sink in for a second.

Not your historical performance. Not your gut feel. Not what you hope will happen.

Your anticipated earnings.

And if you’re wondering, “Well, how would they know that?” that’s exactly the point. They know because they track the data.

The Quiet Shift in How Law Firms Are Valued
If you haven’t been paying attention, MSOs are quickly becoming private equity’s workaround to the non-attorney ownership problem. They don’t own the law firm. They don’t share in legal fees. They’re “just” a services company that consolidates intake, marketing, case management support, and everything else that isn’t technically the practice of law.

Then they charge the firm a cost-plus-market-rate fee for those services. Perfectly compliant. Structurally sound. Increasingly common.

Here’s where it gets interesting.

That MSO fee? It’s not static. It gets reevaluated annually based on what the MSO believes your firm is going to produce in the coming year.

In other words, they are underwriting your future.

And they’re doing it with a level of precision most law firms simply don’t have.

Firm A (and Why This Should Make You Nervous)
Let’s talk about Firm A.

Firm A thinks they’re having a pretty good year. Revenue is up. The partners feel busy. There’s a general sense that “things are working.”

If you asked them what next year looks like, you’d get something along the lines of:
“Well, probably about the same … maybe a little better.”

Now put that same firm in front of an MSO.

The MSO isn’t asking how things feel. They’re digging into:

Case mix
Pipeline velocity
Conversion rates
Time to resolution
Revenue per matter
Win rates (where applicable)
Staffing leverage by case type
They’re looking at the entire portfolio and saying, “Based on this data, here’s what we believe this firm will generate over the next 12–24 months.”

And then they price their services accordingly.

Here’s the uncomfortable part: The MSO is often more accurate about your future revenue than you are.

Why This Changes the Game, Whether You Join an MSO or Not
You don’t have to join an MSO for this to matter. Because the existence of MSOs is changing the baseline expectation of what a “well-run” firm looks like. The firms that will win in this environment are not the ones with the best instincts. They’re the ones with the best data.

If someone outside your firm can model your revenue more accurately than you can, you don’t have a data problem. You have a leadership problem.

Because at its core, this isn’t about spreadsheets. It’s about visibility.

Do you know which cases actually drive profitability?
Do you know how long they take, on average, from intake to resolution?
Do you know where your bottlenecks are and what they’re costing you?
Do you know, with any level of confidence, what next year looks like?
Do you know which data affects your law firm valuation the most?
If the answer to any of those is “sort of,” you’re already behind.

Data Discipline: The Real Opportunity (and Where Most Firms Miss It)
Here’s the irony.

Most firms think MSOs are about offloading back-office work — and yes, that’s part of the appeal. You get scale, better vendor pricing and systems that would be expensive to build on your own. But that’s not the real value. The real value is the data discipline.

Because once you can accurately predict your revenue and understand the influences on law firm valuation, everything changes:

You make better hiring decisions.
You invest in the right cases and clients.
You stop overreacting to short-term fluctuations.
You negotiate from a position of strength, whether with vendors, lenders or even an MSO.
Without that, you’re guessing. Just more confidently.

A Quick Reality Check
It is critical for law firms to build the systems and visibility to actually understand their case portfolio and forecast revenue with precision.

Not because everyone needs to sell to private equity. But because everyone needs to run their firm like someone might evaluate it that way.

Because increasingly, someone will.

The Shift to Data-Driven Law Firm Valuation
You can ignore MSOs. You can decide they’re not for you. You can wait and see how the regulatory landscape evolves. But you cannot ignore what they represent: a shift toward data-driven law firm valuation.

And in that world, the firms that win won’t be the ones with the best stories about their numbers. They’ll be the ones who actually know them.]]></description>
<dc:subject>privateequity succession</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:dffd1ba175a0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:succession"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legalfutures.co.uk/latest-news/sra-puts-size-of-suspected-pm-law-fraud-at-40m">
    <title>SRA puts size of suspected PM Law fraud at £40m - Legal Futures</title>
    <dc:date>2026-05-15T18:11:56+00:00</dc:date>
    <link>https://www.legalfutures.co.uk/latest-news/sra-puts-size-of-suspected-pm-law-fraud-at-40m</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[The Solicitors Regulation Authority’s (SRA) investigation into PM Law “involves a sophisticated suspected fraud”, with the improper removal and misuse of £39.5m of client funds, the regulator has revealed.

It has also paid out £16m to the Sheffield-headquartered group’s former clients.

It described the intervention into PM Law as one of the largest and most complex it has ever undertaken, involving 11 companies, 25 offices and more than 30 trading names spread across Yorkshire, Cumbria, Berkshire, Derbyshire and London.

A fortnight after PM Law suddenly closed its doors in February, the SRA confirmed that it had uncovered a “potential fraud” but could not at that stage say how large it was.

As of last week, 92 claims, totalling £9.3m, have been paid to former clients from the SRA Compensation Fund – up from £3.7m in the last update at the start of March – with “hundreds” of further claims in train worth a further £12.2m.

It has moved extra staff into the compensation fund team to help deal with them.

The SRA has also paid out £6.8m from money held in PM Law’s client accounts at the time it intervened.

At the same time, the SRA has introduced a new approach to prioritisation of applications to the compensation fund – for both PM Law and more generally – under which it will deal with claims based on the risk of harm faced by those making them.

It stressed that this would “not impact the likelihood of whether any individual claim is successful when considered”.

The intervention agent, Yorkshire firm Gordons, has sent 25,000 emails or letters to people identified from the seized files as having live matters, dealt with 17,000 enquiries, and returned 9,300 live files to clients, with a further 20,000 transferred in bulk to insurer clients.

The SRA said Gordons’ staff were working “round the clock, including on weekends, to handle client queries”.

Paul Hastings, the SRA’s director of client protection, said: “We are continuing to do all we can to support former clients of PM Law, including by reuniting them with their money or files.”

Law Society chief executive Ian Jeffery praised the SRA for moving “quickly” in its investigation and acting “with openness and transparency”.

He continued: “However, a case this large coming so soon after Axiom Ince and SSB Group, reinforces the need for the SRA to focus on their core regulatory role and deliver the changes needed to reduce the risk of future large-scale collapses and re-build consumer confidence.

“The compensation fund provides crucial protection and reassurance to consumers. It is unfortunate the SRA has had to use the fund in this case and we hope any increase to the fund will be kept to a minimum.”]]></description>
<dc:subject>regulation governance fraud ethics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:5475a0d26a2e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:regulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:governance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:fraud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ethics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law360.com/pulse/modern-lawyer/articles/2461235?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0">
    <title>Arizona's Law Firm Experiment Faces Conflict Question - Law360 Pulse</title>
    <dc:date>2026-05-15T18:10:45+00:00</dc:date>
    <link>https://www.law360.com/pulse/modern-lawyer/articles/2461235?nl_pk=eb3f2140-a0f3-485e-b2ed-29ef917b5fa0&amp;read_main=1&amp;nlsidx=0&amp;nlaidx=0</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[In the five years since Arizona launched a program allowing non-attorney ownership of law firms, more than half of the at least 160 applicants to go before the program's regulatory committee saw at least one member recuse themselves from a vote on their licenses, according to a Law360 Pulse analysis.

The recusal pattern, while not indicative of any kind of ethical violation, could be a problem of public perception for the alternative business structure program, whose regulators and regulatees can sometimes overlap in a state with one of the smallest legal industries in the country.

The ABS program, a model pioneering how law firm ownership could be expanded, is among the country's most closely watched experiments in legal ownership as private equity and other buyout funds look to gain a foothold in the industry that offers recurring revenue and steady returns.

Critics have raised concerns about the potential influence of outside investors on how attorneys perform their work. But proponents point to the program's strenuous regulations, including requirements that ABS entities hire a compliance lawyer tasked with reporting any wrongdoings to the state's Supreme Court and go before a regulatory committee every two years in order to renew their licenses.

However, a Law360 Pulse analysis of Arizona ABS committee meetings since the program launched in 2021 shows that members recused themselves from votes at least 191 times. At least 86 ABS applicants — more than half of the 160 ABSs approved for licensure in Arizona — saw a committee member recuse themselves from a vote on at least one of their matters before the committee.

Of the panel's 11 current members, six have been employed by, invested in, or provided outside counsel to an ABS.

Judge Anni Hill Foster, the committee's chair, told Law360 Pulse that while she feels there is enough professional diversity on the committee, she hopes to keep conflicts to a minimum as the ABS program continues to expand.

"We want to make sure that we are not having too many people involved in ABSs that are on the committee because then the public isn't going to have confidence in what's going on," she said.


It is not unusual that a regulatory body would include market participants, and more than half a dozen legal ethics lawyers, legal industry regulators and committee members themselves told Law360 Pulse that firsthand experience with forming or running an ABS can provide critical insight into how best to regulate them.

But while wearing two hats is not illegal, it can create a problem of public perception — especially as non-attorney ownership of law firms is already met with wariness by many lawyers in the U.S.

As more ABSs continue entering Arizona's regulatory sphere, the program has never been more in flux. In 2026, states like Illinois and South Carolina have begun floating restrictions on fee-sharing with ABSs similar to the legislation that went into effect in California in January.

And internally, Arizona is grappling with increasingly complex questions about what types of firms should be granted ABS licenses.

For instance, in December, the Arizona Supreme Court denied licensure to an applicant over its lack of ties to the state, marking the first time the court went against a recommendation from the ABS committee. The split prompted a closer look at what kinds of firms are being approved by the committee, which in five years has voted against an initial licensure application just three times, a committee spokesperson confirmed as of April 20.

In February, two stories in the Arizona Republic highlighted concerns with the program. Separately, the State Bar of Arizona also recently warned that the committee's leniency in allowing out-of-state investors, as well as referral-model firms, into the program would "increase the risk of consumer harm."

And a 200-page complaint filed in December alleged that legal staffing and service provider Axiom's efforts to establish an ABS firm in Arizona were improperly driven by the company's private equity backer putting "revenue over ethics." The suit named ABS committee member Lynda Shely as a defendant for her role as compliance lawyer for the firm.

A Conflicting Narrative

In a conference room in the Arizona State Courts Building in September, an attorney fielded a barrage of questions from ABS regulators as they considered his application to launch a new personal injury firm.

The firm would be wholly owned by a hedge fund — something strictly prohibited in almost every other state. In a public video of the meeting viewed by Law360 Pulse, members raised concerns about potential conflicts with the firm's parent company and its lack of ties to the state. In response, the attorney gave a nod in Shely's direction.

"We have hired what we think are the best ethics counsel around, one of whom is in this room," he said.

Shely sat amid her fellow members with her chair pushed back, her hands in her lap. She had recused herself from voting on the application, which passed through with just one dissenting vote.

Shely has sat on the ABS committee since 2022. Over that time, Law360 Pulse's analysis found that she has recused herself 128 times on votes for over 70 separate applicants — the most of any current or past committee member by a large margin.

In the judicial requirements for certification and licensing boards in Arizona, it says committee members shall recuse themselves when there is a conflict of interest, or it could appear there is a conflict of interest. This could include situations where the applicant shares any kind of direct or indirect financial interest with the committee member, or when the relationship between the member and the applicant is one that would affect the member's ability to be impartial.

Members aren't required to publicly disclose why they recused, and most members of the ABS committee, including Shely, do not in most cases. In a public meeting in January, however, Shely said her practice was to "recuse on people I've consulted with if it was about the ABS."

She, until recently, had provided consulting services specifically for ABSs and potential ABS applicants.

Shely, who also co-founded the National ABS Law Firm Association, aimed at advocating for the ABS model nationwide, told Law360 Pulse via email that she has "retired from advising [ABS] clients as of December 2024."

"While I remain on the ABS committee, I'm not representing clients any longer (in the hopes of being able to do more travel)," she said.

Since retiring at the end of 2024, Shely has recused herself on 13 initial licensure votes and 19 votes to renew licensure. She said in that January meeting that the choice to recuse isn't an exact science, but rather is often a personal one.

"If it was years ago and I didn't help them with their application and I have no financial involvement with them, I don't represent them now, then it gets to a personal interest," she said. "Do I feel like I'm going to be biased or am I being impartial?"

Shely isn't the only member to have built out an ABS consulting practice. Members Andy Kvesic and Taylor Bell each have practices offering clients advice on complying with ABS rules and applying for a license.]]></description>
<dc:subject>abs ethics governance</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:cbd6103bdeb0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:abs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ethics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:governance"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/04/23/inside-freshfields-partnership-with-anthropic-and-what-it-means-for-the-legal-industry-/?kw=Inside%25252BFreshfields%25252527%25252BPartnership%25252BWith%25252BAnthropic%25252Band%25252BWhat%25252BIt%25252BMeans%25252Bfor%25252Bthe%25252BLegal%25252BIndustry&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803">
    <title>Inside Freshfields' Partnership With Anthropic and What It Means for the Legal Industry | Law.com</title>
    <dc:date>2026-05-15T18:10:11+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/04/23/inside-freshfields-partnership-with-anthropic-and-what-it-means-for-the-legal-industry-/?kw=Inside%25252BFreshfields%25252527%25252BPartnership%25252BWith%25252BAnthropic%25252Band%25252BWhat%25252BIt%25252BMeans%25252Bfor%25252Bthe%25252BLegal%25252BIndustry&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Freshfields announced a partnership with Anthropic Thursday that will allow the firm to strengthen its proprietary generative artificial intelligence platform and promote widespread internal AI adoption.

As part of the partnership, the Claude suite of products and frontier AI models will be deployed across 33 Freshfields offices, all practice groups and business services and will include Anthropic’s agentic AI platform, Cowork. The firm will also receive early access to future Anthropic models and assist the AI developer in building AI-powered legal services.

Freshfields chief innovation officer Gil Perez as well as partner and co-head of Freshfields’ internal innovation and legal tech development lab Gerrit Beckhaus sat down with Law.com to discuss how the firm will use Anthropic’s Claude large language models, how it will contribute to Anthropic’s products, and the Freshfields' broader vision with technology partnerships.

This Q&A has been edited for length and clarity.

How was Freshfields’ relationship with Anthropic and Claude formed?

Perez: About eight or nine months ago, we began to see that Anthropic was starting to get a lot of buzz in the enterprise with our clients, and in talks with also our testing, we began seeing the rise of Claude code also specifically. That's what they're known for. Their approach to focusing on the enterprise was another one that was quite appealing, so that was really the trigger. The trigger to all of this is really client demand and meeting our client's requirements, that allowed us to begin evaluating that ... there's a lab, ... that was able to then parlay that into actually testing and capabilities. Moreover, [it] also fits very clearly with our approach of being tech agnostic, of not being locked in on any specific AI platform.

A year ago, we did not know whether it's going to be Perplexity or Anthropic or Grok that may come around the corner, but we knew that it's really important to have optionality. That's why we struck the strategic agreement with Google last year, yet in parallel, we began adding additional providers that we think are the right ones, and luckily for us we made two very sound decisions on two strategic partnerships.

Why and how will you be using Anthropic’s model?

Beckhaus: The Claude models are part of our proprietary solutions. So we developed a number of strategic platforms for mandate types like due diligence, case management, multijurisdictional surveys, compliance assessment, restructurings and, for those platforms, we basically integrate the gen AI models on various steps of the production chain. There it gives us a lot of flexibility to choose again, the right model for the right task and then we have a more general AI platform internally with a modular approach where we continuously, based on the leads from our lawyers and our clients, build our modules and looking [at] what's the best model available. That switches a bit from model generation to model generation. ... There are certain tasks where this works really well and it's again about the flexibility of using the right model for the right task.

Perez: I would add another element to this, which was in the press release, it's what's called the early access program. A key part of this partnership is the fact that we'll give Anthropic feedback on their future products with ensure that they meet the requirements of the legal industry, specifically around security, residency of data ... As a representative of the entire industry, the entire industry will benefit from it because then the products will be fit for purpose for the legal industry as well and will accelerate hopefully their adoption for any company across all industries, obviously legal included. That is a very important element because it will allow us also to get an understanding of those tools ahead of time, like a couple of months or sometimes it's weeks, sometimes it's longer. But then, when those products become generally available, we're able to immediately use them in full strength across all of our matters and to the benefit of our clients.

Will the partnership impact the firm's operations and business model?

Beckhaus: How it affects the operations is the broader theme that AI will be part of everything we do, and being integrated and not to press a button and then send it off, but to make us better and to serve our clients better and to add value with that technology. That's the infrastructure part that does not only refer to the lawyers, but also to the whole organization. ... Then there is of course the service layer. When you look at how legal services are delivered, then currently one element is the production chain, I would call it, and how AI is integrated into that production chain with a focus on not only efficiency gains, but providing a better service to our clients and adding value with the technology.

On top of just producing the same as before, the technology allows us apparently to also come up with enhanced and new types of services that are AI-powered. One example would be on the kind of regulatory-compliance side, where basically a lot of clients are currently having the need to check whether their services or products comply with regulation in certain countries and there is a lot of moving pieces, as we know, on the regulatory side. There, for example, in one of our platforms, we have an AI element that basically does the updates assessment, etc., and thereby speeds up the process, then is validated and controlled by the lawyers. That's one piece that changes the product and it's similar in due diligence exercises.

Perez: If you take a macro view, the important thing that we're communicating is two clear messages. One, technology is now becoming a core skill and proficiency of the legal profession. ... The second message is that this is a continuous, evolving effort to stay on top. Just like you're an athlete, you might be the best athlete, [but] if you don't continue training, you lose your edge. ... We're changing the organization, the thought, the culture, and how we're doing to that mindset of being best fit and a top shape all the time.

Will this impact the partnership with Google Cloud?

Perez: No, I'm right now at Google Cloud Next in Las Vegas. We have a very strong relationship with Google. There's a very strong partnership between Google and Anthropic that is obviously very public. ... As Gerritt said, we will use all models, we're not locking ourselves. It's a really inefficient and shortsighted approach to say I'm going with a single vendor because things are changing so fast. So tomorrow when Gemini comes up with a better model, we'll use that, when OpenAI comes with a better model, we use that. ... All of that goes back to optionality.

What areas of work have you guys found that Claude has worked better compared to other models?

Beckhaus: It's really good in the coding area, it's really good at drafting, it's really good at nuanced reasoning and those are areas where the other models are not bad and to a certain extent, it's also a matter of taste, but [Anthropic’s models are] particularly good.

Perez: One topic I wanted to stress is we began this journey a couple of years ago, but we think that the legal industry needs more optionality, and we've taken steps last year with the announcement of Google to begin that journey. This is the second strategic AI partnership that we have. ... We're clearly, with these two [partnerships], ahead of the competition. ... This is something that we should not take for granted and we're going to continue to move forward, but we're delighted to be at least at this point in this position, and it's important to take that in the context of not only this announcement, but really a two-year journey and a longer perspective.]]></description>
<dc:subject>ai firms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:635080572ada/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:firms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legalfutures.co.uk/latest-news/eight-out-of-10-candidates-say-sqe-is-not-fit-for-purpose">
    <title>Eight out of 10 candidates say SQE is not fit for purpose - Legal Futures</title>
    <dc:date>2026-05-15T17:58:41+00:00</dc:date>
    <link>https://www.legalfutures.co.uk/latest-news/eight-out-of-10-candidates-say-sqe-is-not-fit-for-purpose</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Eight out of 10 current and former Solicitors Qualifying Examination (SQE) candidates do not consider the exam is fit for purpose or good value for money, a survey by the National Junior Lawyers Division (NJLD) has found.

The NJLD said there were “structural issues” with the SQE requiring “urgent attention” and called, among other things, for the cost structure to be reviewed.

Almost half of candidates (44%) reported that the total cost of the SQE, including exams and preparatory courses, was or would likely be over £10,000.

The group said the survey findings reflected “a consistent and deeply felt set of concerns across factors such as cost, accessibility, transparency, employer readiness and candidate welfare”.

“The NJLD recognises that the SQE was still a relatively new system and that some transitional difficulty was inevitable.

“It further recognises that many candidates have successfully completed the SQE on the path to qualification and that accurately surveying and synthesising the views of this cohort is challenging.

“However, the strength and consistency of the evidence gathered here suggests that there are several structural issues that require urgent attention.”

The NJLD said 476 candidates completed the survey last year, which was self-selecting in terms of respondents rather than randomised. As a result it should be read as “strongly indicative of individual candidate experience, rather than statistically representative of the entire SQE candidate population”.

The University of Law was the most widely used provider of preparatory courses for the SQE, followed by BPP and BARBRI.

A large minority of candidates, 37%, said their course only prepared them ‘somewhat’ for the exam, while 3% said ‘not at all’.

Almost two-thirds of candidates (63%) did not regard their preparatory course as good value for money.

A majority had difficulties booking their SQE assessments – 27% citing significant or extreme problems: “Qualitative feedback frequently cited the first-come, first-served booking system, limited test centre availability, and the requirement to pay within a short window of receiving a booking slot.

“Several respondents reported queuing online for extended periods, only to find no available centres in their region.”

Nearly half of all candidates experienced difficulties on examination day, most commonly technical failures, inadequate test centre facilities and the need to travel long distances to sit exams.

Of the 80 candidates who required reasonable adjustments, only half reported that they were provided adequately.

A significant minority of candidates (28%) rated the SQE resit and appeal process as ‘terrible’, with 16% rating it as ‘poor’. Only 15% rated it as ‘good’.

The NJLD said: “The escalating cost of resits was a recurring theme, alongside dissatisfaction with the three-attempt limit, the perceived lack of transparency in the appeals process and the absence of detailed feedback on failed assessments.”

The “single strongest negative finding in the survey” related to value for money, with 82% saying the SQE was not “good value for money in terms of administration and examination fees”.

While 44% of candidates reported ‘some’ understanding and support for the SQE process from employers, 19% received none at all.

The 172 detailed responses from candidates to a question about their mental health and wellbeing “conveyed consistent themes of exhaustion, isolation, anxiety and financial stress”.

The NJLD called on the legal profession to “engage seriously” with the findings, calling for the cost structure to be reviewed, including resit fees “with a view to ensuring affordability and proportionality”.

They called for “detailed, verified pass rate data by preparatory course provider” to be published to improve transparency and “more meaningful, tailored feedback on failed assessments, including an identification of areas of weakness”.

An independent review should also be conducted of the reasonable adjustments process and legal employers given “clear, public-facing guidance on SQE support”.

NJLD chair Harry Clark commented: “We have shared an anonymised copy of the underlying survey results with key stakeholders, including the SRA and the Law Society.

“It is encouraging to see the SRA hold discussions with the likes of Kaplan and to identify the SQE as a key focal area for the coming months.

“We hope that these findings are informative in driving the necessary reforms and reviews of the exam.”]]></description>
<dc:subject>sqe competence barexam</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:36ce9961a2e3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:sqe"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:competence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:barexam"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legalfutures.co.uk/latest-news/us-personal-injury-firm-attracts-125m-private-equity-investment">
    <title>US personal injury firm attracts $125m private equity investment - Legal Futures</title>
    <dc:date>2026-05-15T17:58:08+00:00</dc:date>
    <link>https://www.legalfutures.co.uk/latest-news/us-personal-injury-firm-attracts-125m-private-equity-investment</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[A personal injury law firm in Arizona has launched a management services organisation (MSO) with a $125m (£94m) investment from an unnamed private equity backer.

The deal values the MSO, Rafi Law Services, at approximately $450m. It was created by Rafi Law Group.

It follows a similar deal done in January between Louisiana-based Dudley DeBosier Injury Lawyers and Uplift Investors, but that did not specify the amount invested.

The MSO model has been touted as a way to get around the bans in most US states on non-lawyer ownership of law firms and fee sharing with non-lawyers.

Rafi Law Group was set up in 2015 and has 26 attorneys and around 250 support staff in seven offices across Arizona. It has reportedly acted for around 100,000 clients in that time.

Rafi Law Services will house the firm’s non-legal operations, including technology, marketing and administration. Rafi Law Group will remain the legal practice and the announcement stressed that the move preserved lawyer independence and ethical governance.

But the investment will support “expansion into new markets”, investment in technology and infrastructure, and potential partnerships with “aligned” personal injury firms nationwide that could also use the MSO.

“This structure allows us to modernise how we operate without changing who we are,” said founder Brandon Rafi, who has retained majority control of the MSO.

“Our mission remains the same: deliver outstanding results for clients. What’s changing is our ability to scale that mission responsibly. This isn’t disruption for disruption’s sake. It’s modernisation with clear guardrails that keep clients and ethics first.”

Andy Halaby, chief legal officer of Rafi Law Services, said: “Capital can support efficient delivery of legal services while ensuring independence of legal decision making.

“This structure ensures that lawyers retain sole authority over client representation, while giving us the operational strength to expand access to justice.”

Mr Rafi said personal injury firms were at the forefront of a broader shift toward consolidation in the legal sector. Transparency and governance were “essential” and he intended to play a “visible leadership role” in shaping best practices for ethical growth.

“As the legal industry evolves, firms have a choice about how they grow,” he added. “It’s about building a sustainable structure that puts clients first, supports lawyers, and is prepared for the future of the legal profession.”

Meanwhile, a newly published academic paper has warned about a “governance gap” in the operation of MSOs.

“The MSO model is predicated on the fragile assumption that ‘legal practice’ and ‘business operations’ can be clearly and durably separated to preserve professional independence despite the firm’s near-total dependence on an investor-controlled platform,” wrote Lev E Breydo, assistant professor of law at William & Mary Law School in Virginia.

“The problem is not the structure per se, but the lack of institutional infrastructure required to ensure that separation. Without guidance, ex ante review, or ongoing oversight, the private ordering equilibrium will predictably track investor preferences rather than broader policy considerations.”

Neither the American Bar Association nor state bar associations have issued comprehensive standards for law firm MSOs, he noted, and no court has adjudicated on the boundary conditions.

Mr Breydo said healthcare’s three decades of MSO experience showed a pattern of “control creep”, where “formal separation deteriorates toward de facto control over professional decisions”.

He acknowledged that investors have strong incentives to support robust governance, given the impact disciplinary or regulatory action could have on the business.

“The problem is that even as deal templates standardise, market participants lack a baseline understanding of what robust ‘governance’ requires in the law firm MSO context.”

As a minimum, the academic recommended structural and contractual safeguards in the management services agreement, and requiring that each of the law firm and the MSO should have separate boards, with law firm representation on the MSO board but not vice versa.

“Ideally, law firm MSO boards should be composed of a majority of independent directors, consistent with public company requirement and best practices for regulated entities. Given sponsor constraints, however, the bare minimum should be at least one independent director that serves as chair.”

The MSO board should have an independent director-chaired standing ethics and professional independence committee, to which a dedicated chief compliance officer should report. The MSO should also engage independent outside ethics counsel to conduct an annual compliance review.

Mr Breydo concluded: “As the accounting experience shows, alignment of interests between investors and target firms can drive rapid proliferation – transforming a sector in the process. That trajectory makes governance urgent…

“While closing the governance gap does not mean banning MSOs, it does require governance beyond paper separation.”]]></description>
<dc:subject>privateequity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:b7d60dfcb73a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.thomsonreuters.com/en-us/posts/legal/honing-legal-judgment-training-lawyers/">
    <title>Honing legal judgment: The AI era requires changes to how lawyers are trained during and after law school - Thomson Reuters Institute</title>
    <dc:date>2026-05-15T17:55:45+00:00</dc:date>
    <link>https://www.thomsonreuters.com/en-us/posts/legal/honing-legal-judgment-training-lawyers/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[The key skills that comprise legal judgment have received mixed reviews, according to a recent white paper from the Thomson Reuters Institute that advocated for cultivating practice-ready lawyers. The white paper was based on feedback from thousands of experienced lawyers, judges, and law students and raises questions about how legal judgment forms when AI assistance is used for task completion.


Law21 blog author Jordan Furlong notes that decoding and deploying legal judgment calls for “a new approach to lawyer formation… to accelerate the development of legal judgment early in lawyers’ careers.”

The challenge is that each part of the profession — law schools, employers, state supreme courts (as regulators) — have distinctly separate responsibilities. That means, that in the age of AI, coordination across the entire legal profession is needed, especially as AI reduces the availability of traditional first jobs.

Furlong points out that there is no consensus for what legal judgment is or any agreed upon standards for in what instances AI should be used in legal. To bring clarity to these issues, the white paper proposed a profession-wide model that integrates three critical elements: i) work-based learning that’s modeled on medical residencies; ii) micro-skill decomposition of legal judgment; and iii) AI-as-thinking-partner throughout pedagogy.

Three pillars for an AI-era lawyer formation system
Not surprisingly, overreliance on AI can erode critical analysis and solid legal judgment skills. Addressing these concerns requires a comprehensive reimagining of how lawyers are educated and trained. One solution lies in three interconnected pillars that together form a cohesive system for developing legal judgment in an AI-integrated world.

Pillar 1: Integrate work experience into legal education
Core skills such as legal research, writing, and document review help develop legal judgment; yet these skills could collapse once AI assumes such tasks. The Brookings Institution recently proposed adapting the medical residency model to preserve entry-level professional development in an AI era. This parallels the TRI white paper’s calls for mandatory supervised postgraduate practice as a key part of legal licensure.

While implementing a full residency model presents challenges, several law schools have already pioneered approaches that demonstrate the viability of work-integrated legal education that, if scaled appropriately, could improve new lawyer practice and judgment skills. For example, Northeastern Law School guarantees all students nearly a full year of full-time work experience before graduation through four quarter-length legal positions. The program integrates supervised practice into the curriculum so graduates can gain substantial hands-on experience alongside their classroom instruction.

Also, UNH Franklin Pierce’s Daniel Webster Scholar program offers an alternative pathway to bar admission through practice-based assessment rather than the traditional bar exam. The program demonstrates that competency can be evaluated through supervised experiential learning.

Pillar 2: Decompose legal judgment into teachable micro-skills
The legal profession needs to come to a common definition of legal judgment and develop its components to teach the concept effectively. “We can’t teach what we can’t describe,” Furlong says. To develop legal judgment, the profession must define its components, including:

Pattern recognition — The ability to identify when different fact patterns are related to similar legal frameworks and distinguish when superficially similar cases are legally distinct.
Strategic calibration and proportionality — This means understanding what level of effort, precision, and risk each matter requires and matching responses to the stakes involved.
Reasoning through uncertainty — This is the capacity to make defensible decisions and provide sound counsel even when the law is ambiguous, unsettled, or silent on an issue.
Source evaluation and authority weighting — This includes knowing which legal authorities are most suitable and being able to assess their persuasive value.
Ethical judgment under pressure — This means spotting conflicts, confidentiality issues, and duty-of-candor moments while maintaining competence and knowing when to escalate beyond expertise.
Breaking down legal judgment into these discrete components makes it possible to design targeted teaching interventions. For example, Kevin Lee, former law professor and executive director of the Institute for AI & Democratic Governance, suggests we hardwire judgment work back into AI-assisted workflows by requiring a short verification log (detailing sources checked, changes made, and why); running attack-the-draft drills (find missing authority, weak inferences, and jurisdictional mismatch); and preserving slow work as formative work (citation chaining, updating, and adversarial research memos).

With judgment skills clearly defined and work experience integrated into training, the profession must then tackle how AI itself should be incorporated into lawyer development.

Pillar 3: AI-as-thinking-partner throughout a lawyer’s career
Warnings that AI could degrade critical thinking are mounting. The legal profession must provide clear standards for in what instances and how AI should be used, with training in verification and judgment skills. Overreliance on AI could compromise lawyers’ capacity to fulfill their fiduciary duties to clients.

A phased approach in the introduction of AI in legal work helps protect critical thinking while building AI competency. For example, in Year 1, law students could complete core legal reasoning exercises without AI assistance in order to better develop their analytical muscles. In Year 2, students use AI as a research assistant with mandatory verification protocols that teach students to check outputs against authoritative sources. Finally, in Year 3, residencies can immerse students in real-world AI workflows under proper supervision and while providing feedback.

These three pillars form a coherent vision for lawyer formation in the AI era. However, the most well-designed system faces the obstacle of funding.

The challenge of who pays
Perhaps the most difficult part of any overhaul is the cost. The medical residency model works because hospitals get Medicare funding — up to $15 billion-plus annually — for teaching young medical students to be doctors. Legal education has no equivalent. Without addressing funding, however, even the best reforms will fail.

One idea is to establish a legal education fund that’s supported by an assessment of a small percentage of the legal industry’s gross legal services revenue (while exempting solo practitioners and firms with less than $500,000 in annual revenue). These funds could be used to subsidize thousands of supervised residency placements, fund law school curriculum development, support bar exam alternative assessments, and provide employer training and supervision stipends.

The challenge is that each part of the profession — law schools, employers, state supreme courts — have distinctly separate responsibilities, and that means coordination across the entire legal profession is needed.
This proposal, of course, would require unprecedented coordination and financial commitment from the legal profession. Skeptics might argue that market forces can solve this problem, or that firms will simply create new training pathways, or that AI will prove less disruptive than feared. However, waiting for market forces risks a lost generation of lawyers. The medical profession already learned this lesson more than a century ago when the medical industry’s voluntary reform failed. Only later did coordinated regulatory intervention produce the consistent quality standards the medical industry sees now.

What is clear is that inaction is resulting in degradation of lawyering skills. “Maybe… we need catastrophic external intervention to bring about the wholesale changes we can’t manage from the inside,” Furlong suggests.

However, the question is whether the legal profession will wait for a crisis to force change or act proactively to make the needed changes now, before the crisis hits.]]></description>
<dc:subject>judgment ai skills competence jf</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:5d37091b7cbb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:judgment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:skills"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:competence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:jf"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.thomsonreuters.com/en-us/posts/wp-content/uploads/sites/20/2025/09/2025-NCSC-Judges-White-Paper.pdf">
    <title>[untitled]</title>
    <dc:date>2026-05-15T16:47:46+00:00</dc:date>
    <link>https://www.thomsonreuters.com/en-us/posts/wp-content/uploads/sites/20/2025/09/2025-NCSC-Judges-White-Paper.pdf</link>
    <dc:creator>JordanFurlong</dc:creator><dc:subject>competence schools training litigation admission</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:9ccaea172896/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:competence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:schools"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:training"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:litigation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:admission"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.thomsonreuters.com/en-us/posts/innovation/thomson-reuters-and-hotshot-partner-to-close-the-gap-between-law-school-and-legal-practice/">
    <title>Thomson Reuters and Hotshot Partner to Close the Gap Between Law School and Legal Practice - Thomson Reuters Institute</title>
    <dc:date>2026-05-15T16:25:32+00:00</dc:date>
    <link>https://www.thomsonreuters.com/en-us/posts/innovation/thomson-reuters-and-hotshot-partner-to-close-the-gap-between-law-school-and-legal-practice/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Today, Thomson Reuters and Hotshot are proud to announce a landmark partnership designed to meet that challenge of the rapidly changing profession head-on – giving law students an unparalleled opportunity to approach their summer positions (and beyond) with the skills, knowledge, and technological fluency that modern legal practice demands.

Thomson Reuters recently announced that more than 120,000 law students across the U.S. will have access to their latest AI technology, CoCounsel Legal and Deep Research from Westlaw – making it the first company to provide this scale of  fiduciary-grade AI access to law students nationwide. Thomson Reuters serves more than 200 law schools across the U.S., including top-tier T14 institutions, extending a 150-year legacy of supporting legal education.

Hotshot has built a reputation as the go-to learning platform for lawyers at every stage of their careers. Hotshot now helps over half the Am Law 100, top law schools, and in-house teams provide on-demand learning, interactive learning, and experiential training programs in remote, live, and hybrid settings. Founded on the insight that even the smartest people who went to the best law schools don’t yet know what they’re doing when they start practicing law, Hotshot’s solution was to bring innovations in digital learning to the legal industry – things like short, practical videos, experiential, hands-on workshops, and mobile learning.

Together, these two organizations are combining the most advanced AI-enabled legal technology in the market with the most practical, skills-based legal training content available – and putting it directly in the hands of law students before they ever set foot in a law firm.

What the Partnership Delivers
Hotshot and CoCounsel Legal provide law students with hands-on experience to the very latest in AI technology, making them more appealing to employers and preparing them for practice right after graduation. By combining these resources, students gain exposure to cutting-edge AI tools, practical skills and essential methods to succeed from the start of their legal careers. With Hotshot videos, students learn substantive concepts, then use CoCounsel Legal to apply this knowledge – creating well-structured, research-driven work product that meets future workplace standards.

To give students a clear and structured path to practice readiness, Thomson Reuters and Hotshot have together curated four “prepare to practice” learning tracks built around Hotshot courses: AI Foundations, Professionalism & Business Skills, Civil Litigation Basics, and Transactional Practice Overview. Available to the more than 120,000 law students across the country who already have access to Thomson Reuters’ platform, each track brings together short, practical courses designed to deliver immediately applicable knowledge – and for every course a student completes, they earn a co-branded Thomson Reuters and Hotshot Certificate of Completion that can be added directly to their LinkedIn profile.

These credentials signal to employers that a candidate has already developed the core skills and knowledge the profession demands. That foundational competence, paired with hands-on fluency in CoCounsel Legal, positions students to contribute meaningfully from day one – and to stand apart in an increasingly competitive market for legal talent.

The Future of Legal Education Starts Now
The legal industry is no longer asking whether AI will transform practice – it already has. “Professionals are not deciding whether to use AI anymore. They are deciding which AI they trust when their reputation and their clients’ data are on the line,” said Pat Eveland, general manager, Government, Thomson Reuters.

This partnership ensures that when today’s law students make that decision, they’ll do so with the experience, confidence, and skills to use these tools responsibly and effectively. The gap between law school and practice has long been one of the profession’s most persistent challenges. Thomson Reuters and Hotshot are closing it.]]></description>
<dc:subject>ai training competence</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:d9ada1f1e575/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:training"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:competence"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/04/01/better-service-and-higher-rates-inside-goodwins-ambitious-ai-training-program-/">
    <title>Better Client Service? Inside Goodwin’s Ambitious AI Training Program | Law.com</title>
    <dc:date>2026-05-15T16:18:14+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/04/01/better-service-and-higher-rates-inside-goodwins-ambitious-ai-training-program-/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Artificial intelligence training programs are often structured as one-off events, but some law firms are thinking of AI adoption and training as longer-term challenges.

Artificial intelligence training programs are often structured as one-off events, but some law firms are thinking of AI adoption and training as longer-term challenges.

That’s the approach Goodwin Procter has taken with Propel, a new firmwide AI training program rolled out this year. The firm hopes the initiative can improve the value of representation it provides to clients and perhaps lead to higher hourly rates.

The program is led by Eric Tan, Goodwin’s chief digital and technology officer, who arrived at the firm last September after serving as chief information officer and chief security officer at Flock Safety.

Tan told Legaltech News that "one-and-done” training programs tend to fail, whether in law firms or other enterprises, because they lack “continuous effort in terms of thinking about how we not just track, but how do we consistently drip information to our employees to help them really get better.”

Propel is a multipart program, which begins with in-person sessions designed to deliver hands-on training. The firm’s London office hosted the first two-day event, which over 200 employees attended, in January, and Goodwin plans to hold events at the firm’s East Coast offices in the next few months and across the West Coast in the second half of the year.

The program is structured to provide all Goodwin employees with a shared foundation of knowledge on generative AI, coupled with content specific to each individual’s role and area of law. The event will feature training on firmwide platforms such as Microsoft Copilot as well as practice group-specific tools.

Tan said his team worked with small cohorts within the firm’s practice areas to determine what tools and tasks would be most relevant for them.

“If you're a litigator, you'll be trained on certain specific tools on how to improve what you do as a litigator, as opposed to the mergers and acquisition practice, you're going to be trained on different tools as part of that program,” he said. “We also have a broad purpose [session] on, ‘How do you use Copilot better, in terms of not just chat, but how you would build AI workflows?’”

The introductory events also feature sessions on designing agents with Microsoft Copilot for more advanced users.

Following the introductory sessions, employees will continue with role-based training tailored to their practice groups over a number of months. In addition to lawyer-led training sessions, Goodwin plans to bring in experts from vendors such as Legora, which the firm rolled out in 2025, to help deliver hands-on assistance. The program will also feature online training modules, and the option of live practice sessions to develop discrete skills.

While some law firm AI training programs are solely aimed at attorneys, Goodwin’s is designed to include every employee of the firm. Tan said AI-powered tools can improve the performance of any part of the organization, noting that the security team had built an agent that analyzes access records to identify vulnerabilities on its own initiative before the launch of Propel.

Better Outcomes From Better Outputs 

Goodwin plans to rely on three indicators to gauge the success of the program. The firm hopes to see more than 90% of employees using AI tools in their day-to-day work by the end of 2026, as measured by surveys and usage dashboards. It also aims to measure the efficiency of work performed with AI quantitatively and qualitatively, as well as the firm’s ability to leverage its transactional data to deliver insights to clients more quickly.
Success on those indicators may start to reshape how Goodwin engages with clients as it aims to become an “AI-native firm.” Tan said clients frequently asked about the firm’s use of AI, and that clients stood to be the ultimate beneficiaries of the firm’s investments in the program.

“If you think about it now, in terms of the work, the review process, I've got agents that are doing reviews on draft documents that improve the level of accuracy and quality,” he said. "Something that used to take, call it 30 days—I'm doing it in three days. Why would a client complain?”

Even as many are worried about the future of the billable hour model, Tan said the use of AI may improve the speed and quality of representation so greatly that clients may be willing to pay higher hourly rates than they do now.

“Maybe we come to a point where the billable hour for a firm could be ... two times, three times whatever is being billed today, because the value far exceeds what the client is getting [now],” he said.]]></description>
<dc:subject>ai training ai-first pricing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:83e43d16cb18/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:training"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai-first"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:pricing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/04/01/google-xs-discovery-litigation-strategy-leader-gen-ai-is-fundamentally-reshaping-the-legal-department-outside-counsel-relationship-/?kw=Google%25252BX%25252527s%25252BDiscovery%25252C%25252BLitigation%25252BStrategy%25252BLeader%25253A%25252BGen%25252BAI%25252Bis%25252B%25252526lsquo%25253BFundamentally%25252BReshaping%25252527%25252Bthe%25252BLegal%25252BDepartment%25252C%25252BOutside%25252BCounsel%25252BRelationship&amp;utm_position=3&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803">
    <title>Google X’s Discovery, Litigation Strategy Leader: Gen AI is ‘Fundamentally Reshaping’ the Legal Department, Outside Counsel Relationship | Law.com</title>
    <dc:date>2026-05-15T16:14:06+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/04/01/google-xs-discovery-litigation-strategy-leader-gen-ai-is-fundamentally-reshaping-the-legal-department-outside-counsel-relationship-/?kw=Google%25252BX%25252527s%25252BDiscovery%25252C%25252BLitigation%25252BStrategy%25252BLeader%25253A%25252BGen%25252BAI%25252Bis%25252B%25252526lsquo%25253BFundamentally%25252BReshaping%25252527%25252Bthe%25252BLegal%25252BDepartment%25252C%25252BOutside%25252BCounsel%25252BRelationship&amp;utm_position=3&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[The 2026 Legalweek Leaders in Tech Law Awards honor those who have made significant contributions to legal innovation from law firms, corporate legal departments and legal tech providers.

These awards recognize the efforts of legal professionals or organizations over the past year, specifically how they are pushing the boundaries of legal innovation, redesigning processes and improving the way legal professionals work, and / or building the foundation for a more innovative, creative and knowledgeable legal industry.

As part of our awards series, we asked our winners about what they see as the biggest barriers and drivers of innovation, the impact of emerging technologies, and how they believe the market will change in the near future.

Here’s our Q&A with Alex Ponce de Leon, senior discovery and litigation strategy leader at GoogleX and winner of the award for Innovator of the Year - Legal Department (Individual).

How do you believe legal tech providers and law firms can better support or enable innovation in legal departments?

Legal tech providers and law firms can better support and enable innovation in legal departments by shifting their focus from selling products or billing hours to becoming strategic partners in systemic re-engineering. This collaborative support must center on two pillars: specialized technological partnership and a fundamental shift to value-based engagement.

First, legal tech providers and law firms must deliver and co-develop specialized and integrated gen AI solutions that focus on strategic augmentation, moving beyond simple automation to accelerating legal work. The goal is to maximize efficiency gains in high-volume tasks like contract review, drafting, and legal research, thereby freeing in-house teams to focus on higher-value, judgment-based work. This partnership ensures technology is not just implemented, but that its use is merged with legal strategy to eliminate waste and drive speed wherever possible.

Second, both groups must prioritize strategic partnership and change management supported by a move away from the traditional billable hour. Innovation is ineffective without adoption. Law firms can enable this shift by running targeted pilot programs and offering alternative, value-based fee models that incentivize the efficient use of technology rather than simply tracking hours. This strategic partnership, focused on efficiency and value, is the most effective way to drive innovation and speed within the legal department.

How do you expect legal tech and emerging technologies will impact legal departments’ outsourcing and relationships with outside counsel?

Generative AI is fundamentally reshaping the relationship between legal departments and outside counsel by enabling greater self-sufficiency and driving a profound shift toward value-based service delivery. The key impact is the significant trend toward insourcing and increased reliance on law firms for the highest complexity work. 

Gen AI provides efficiency gains that allow in-house teams to become augmented legal advisors. This insourcing pressure is forcing a re-evaluation of the outside counsel relationship. Law firms that are not transparent about or are slow to adopt gen AI risk being perceived as less cost-effective. Consequently, client demand is poised to disrupt the billable hour, with a majority of in-house professionals likely to push for a change in how legal services are priced. The future lies in law firms becoming true strategic partners who leverage gen AI to offer value-based billing and focus their expertise on complex, high-stakes advisory work, rather than commoditized tasks. Meanwhile in-house attorneys will be able to leverage gen AI to be more hands-on and better strategic leaders on specific case inflection points, therefore creating tighter relationships with outside counsel.

What technology or innovation do you predict will have the biggest impact on legal departments in the near future, and why?

Undoubtedly generative AI is having the biggest impact on legal departments. The profound impact of gen AI is driven by its ability to shift the legal function from a traditional cost center to a proactive, strategic partner. This transformation is realized through two key areas: efficiency and strategic augmentation. Gen AI is poised to deliver significant efficiency gains by automating high-volume, time-consuming, and low-value tasks, allowing legal professionals to focus on high-judgment work. Key functions being streamlined include contract drafting and review, and legal research, where gen AI can provide near-instantaneous synthesis of millions of documents and precedents. However, gen AI’s greatest impact is its capacity for strategic augmentation. It moves beyond simple automation to fundamentally redesign the legal process, for instance, in litigation by applying AI models to inform case strategy, optimize the entire litigation docket, and synthesize evidence into defensible case narratives. This innovation accelerates case strategy, quantifies risk, and helps the legal department become a predictive, tactical partner.]]></description>
<dc:subject>ai clients firms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:100a547cff13/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:clients"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:firms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://michaelplaxton.substack.com/p/to-our-next-law-dean">
    <title>To Our Next Law Dean - Michael Plaxton</title>
    <dc:date>2026-05-15T15:29:23+00:00</dc:date>
    <link>https://michaelplaxton.substack.com/p/to-our-next-law-dean</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[The University of Saskatchewan College of Law is beginning its search for a new dean. We’ve been invited to think about the main challenges facing the lucky winner. And there are a few things one could mention - every law school, large or small, has its issues. But, right now, at this moment in history, there’s really only one challenge worth talking about. Because it’s existential, and it’s an issue for all law schools: AI.

I’m not talking about the use of AI by students to cheat - though, as I noted in my last post, that is a troubling problem in itself. Without belaboring the point, a law school that cannot, practically speaking, require its students to write - and therefore learn to write better, more persuasively, more elegantly - is not a law school as many of us understand it. A law school that cannot depend on its students to read large quantities of material, digesting it, synthesizing it - i.e., because they can now outsource the hard work to a machine - is not able to perform one of the basic functions traditionally expected of a law school. We can stop assigning take-home written assignments - research papers, memos, (sigh) reflective journals - and replace those modes of assessment with hand-written, in-class examinations invigilated by a platoon of heavies. That, however, is not victory. It is an admission of failure; an admission that we can no longer get future lawyers to learn some of the basic skills of lawyering.

(Oral examinations are great, but they are not replacements for written communication skills. They are, at best, supplements for written work. And there is a reason they fell out of vogue: they are intimidating for many students, and (more important) they are not easily scalable.)

Nor am I talking about the problem of academics using AI to produce and peer review “scholarship”. Again, this is a real, profound issue. The idea of law professors using AI to churn out papers they didn’t write, which are then reviewed by AI and added to a database of AI-generated papers used to generate still more… well, it’s just a soul-crushing thought.

These are big concerns for the entire academy, not just law schools. But in many ways they are symptoms of a malaise that had long afflicted the legal academy before AI. Wherever did students get the idea that it was okay not to do the assigned reading, or create their own notes on the material? Could it have something to do with the fact that law schools have, for the last 30 years, steadily diminished use of closed-book exams (which would require a sustained focus on memorizing and internalizing knowledge), while simultaneously reducing assigned readings to a fraction of their former level, and also turning a blind eye to the circulation of “CANs” that offer a distillation of previous iterations of the same course taught by the same professor, and also inflating grades to ever-higher levels?

Or could it also have something to do with the legal academy’s ever-increasing emphasis on “work-life balance” - on treating the study of law as something that not only can but must be confined to a fixed number of hours per subject per week - perversely sending the message to students that they should actively try to minimize the amount of time they spend wrestling with a given subject, or researching a paper, or trying to grasp a doctrine or idea that is elusive; rather than treat the pursuit of knowledge as an end in itself, a beautiful rabbit-hole down which one might happily fall forever?

And could all that, in turn, have something to do with the wildly increased emphasis - at least since I was a law student - on law school as an institution principally (if not exclusively) dedicated to the acquisition of ‘skills’ necessary to become practicing lawyers; an emphasis that would always create the impression that the work being done in classrooms is, well, not really all that important next to the hands-on (“experiential”) learning that could be obtained elsewhere?

Could the use of AI by faculty, likewise, have something to do with the fact that law schools have increasingly hired people with little interest in law as an area of knowledge that is worth pursuing - worth being genuinely, deeply curious about - in its own right? And could even those who want to indulge their curiosity (“let a thousand flowers bloom”) be discouraged or outright thwarted by student editors of law journals who relentlessly demand to know - because we have trained them to think this way - what immediate practical, concrete purpose is served by this research?

We created many of the cultural problems in the legal academy ourselves. They would be there if AI had not emerged on the scene. Had it not, we would have just continued to ignore them; continued to rot slowly from the inside.

But I actually want to focus on what is, I think, an even greater, practical threat to the legal academy as an institution.

The central challenge for the dean of any law school in 2026 is, quite simply, to justify its continued existence in an era of artificial intelligence. Law schools, for better or for worse, principally hold themselves out as places to train future lawyers. And we may already be at a point when higher-end AI products, particularly those pitched at a professional legal market, can do much of the work expected of a junior- or associate-level lawyer in a law firm. The emergence of agentic AI allows lawyers to leave much of the work of drafting, writing, and analysis to a machine. The technology is only going to get better.

(Yes, I have heard about The Hallucinations. These stories tell us more about the lawyers - and, often, unrepresented litigants - who filed the submissions, than about the state of the technology at its best. Sure, if a person uses the basic version of ChatGPT to make their legal submissions, they will get what they get. But there are vastly better products out there if one is prepared to pay for them - and they are certainly cheaper than hiring lawyers.)

This technology is, I want to emphasize, a very good thing from some perspectives. From an access-to-justice point of view, the kind of assistance that agentic AI could provide to unrepresented and indigent ‘clients’ – at a small fraction of the cost of even lower- to middle-tier lawyers – would be a godsend. It should, moreover, drastically reduce the costs absorbed by the state in the form of legal aid, duty counsel, Rowbotham/G (J) applications, staffing costs for the Crown and judiciary, and more. It is no exaggeration to say that the existence, and widespread availability, of high-quality agentic legal AI could make the administration of justice truly scalable for the first time.

More good news: There is little reason to believe that AI could replace human lawyers altogether. There will, I suspect, always be a place for human judgment, human contact, human relationships, and human accountability. For those who can afford the very best (human) legal representation and services, there will always be a lucrative market for lawyers who have the legal understanding, skill, knowledge, acumen, and judgment to critically scrutinize and analyze the work produced by AI in light of their on-the-ground experience. There will always be a market for those lawyers who can vouch for that work (or not), ‘translate’ it into accessible and practically useful terms for laypersons and other actors in the legal system, understand and explain the limitations of a rarefied legal analysis in light of local conditions, build relationships with clients and ‘repeat players’ in the justice system, and generally be the accountable human in the room. (I often think about Hollis Robbins’ discussion of ‘the last mile’.)

So that’s the good news. But notice that all of the things that law schools can effectively teach at scale – i.e., to a large number of fee-paying students at once, thereby making content-delivery practically achievable – are things that high-quality legal AI can already do or will be able to do better and much more efficiently than many or most of the law students we graduate. Insofar as what we are teaching is sufficiently general that it can be - and has been - delivered in a more or less standardized fashion across a range of casebooks and textbooks and across a range of law schools, it is something that AI can also assimilate and deliver with vastly greater efficiency.

Observe too that the required courses in law school have a shared core content, as reflected in the syllabi, that renders them more or less interchangeable across schools. Different professors might have different ‘takes’ on this or that topic, but the core of what we teach is not so very different. (This is precisely why law professors often roll their eyes when students complain about having to adjust their studies for this or that individual professor’s proclivities. We know very well that the subject itself does not vary too much across different instructors.) This interchangeability and generality of much of what we teach suggests that AI can do it at least as well - and faster and cheaper.

Notice, too, that all of the things that people will want human lawyers for – human judgment, human relationships, human accountability – are things that law schools cannot effectively teach at scale. For the knowledge that AI cannot assimilate pertains to matters that are not general; that are profoundly local in some sense. The knowledge might be local to an extremely niche sub-sub-sub-field of law, involving a very small number of repeat players. Preparing students for that field of law involves familiarity with the highly bespoke practical and legal problems faced by participants in that specific context, and may also involve acquiring some familiarity with the participants so that one can understand why and how certain legal solutions are attractive to them.

The knowledge might be, to some significant degree, geographically local: immigration practice in Chinatown in downtown Toronto; or a legal practice in a given rural community in Saskatchewan. What do people want in that community? Who are they? What customs and practices and understandings inform their approach to the legal questions they confront on a day-to-day basis? How are they resolved? Alternatively, it might be knowledge local to a given corporation’s in-house counsel.

A lawyer who possesses this local knowledge is highly desirable (to someone), and cannot be replaced by AI. But a law school cannot really deliver that - not, anyway, to the vast bulk of enrollees. Every law school offers experiential learning opportunities; indeed, the Federation of Law Societies requires law schools to offer them. I chose my example of a rural legal practice in Saskatchewan because the University of Saskatchewan College of Law literally offers an externship for a rural legal practice in Saskatchewan. Most if not all Canadian law schools provide opportunities like these.

I, however, want to stress several points. First, precisely because they are local, experiential learning opportunities are resource-intensive and exert real pressures on general program requirements. They require special arrangements and dispensations. There is, I submit, a reason why the FLSC only requires law schools to offer opportunities for experiential learning; requiring every student to participate in them would likely be cost-prohibitive.

More importantly, though, they impose special pressures on the relationship between the student and the law school. Even if a full-time professor could drop what he or she is doing for a term and spend it in rural Saskatchewan running a practice with a student, or working in-house for a corporation, what possible use would that be? The local knowledge that a student needs is almost certainly not possessed by the professor, but by a lawyer who regularly works in that community. Experiential learning opportunities of the kind I’m talking about are therefore, first and foremost, run by practicing lawyers who liaise with a member of faculty. That faculty member’s role is, mainly, to ensure that the experiential ‘course’ has ‘academic’ content - meaning some role for critical reflection on the experiences, possibly through the assignment of a paper or reflective journals.

I don’t want to speak ill of this, since I think critical reflection is an important thing for universities and law schools to provide to students. But I want to stress that the critical reflection may be the part of the ‘course’ least valued by the students - simply the price of admission for doing the sort of experiential learning that they would do without any academic mediation at all if they had the opportunity to do so. It may also be the part of the course least valued by the profession and the local community ostensibly served by students participating in the experiential learning opportunity. And insofar as the ‘critical’ dimension draws on general ideas about law, ethics and professional responsibility, it is the part that can most effectively be offloaded to AI. The value added by the course - the “last mile” - is not the critical dimension, but the uncritical exposure to local knowledge.

There are other kinds of local knowledge. It might be the local knowledge of a discipline that only a person who has done serious, committed research in that field his or her entire life could acquire: the legal historian who has done first-hand archival research and turned up fascinating new tidbits to which AI could not have access; the legal philosopher who engages with debates about the nature of law by looking to an unjustly neglected thinker from another philosophical tradition; the legal anthropologist working within a community, showing students first-hand how anthropological methods might be applied to it; academics bringing students into the debates that they have with other academics in their field, introducing them to the personalities and idiosyncracies of leading minds.

This is deeply honourable work for an academic. I would feel much better about the state of the legal academy if more of us were doing this sort of intellectual labour of love. But again I want to stress that this is not scalable: a tidbit is not new forever; a thinker is neglected until she isn’t. This requires active, ongoing work by academics deeply committed to knowledge for its own sake, working with students who also have that sort of commitment. And it is precisely the sort of work that most law schools under-value, and that most law schools - especially smaller, regional law schools - cannot afford to emphasize. Realistically, it is only the ‘elite’ law schools that could do it; the schools that, not coincidentally, are most regularly criticized for being impractical and insufficiently concerned with the inculcation of legal ‘skills’.

What about values? I know that many of my colleagues across the legal academy believe that this is the thing we are here to teach to students. I have doubts that this kind of answer will satisfy our critics. Leave aside the fact, for now, that questions about what a lawyer ought to be trying to do simply because he or she is a lawyer are deeply contested. (Look at the arguments over the Notwithstanding Clause, the controversy in Ontario over the Indigenous cultural training course, DEI/EDI initiatives, the TWU controversy a few years ago, the COVID-19 measures and response to the convoy protest, and much, much, much more. These reflect deep divisions over the nature and significance of the rule of law, its relationship to democracy and other values, and what it means to be committed to law.) Leave aside that it is not a good look for a university to even appear to be indoctrinating students on controversial questions. Leave aside even that legal academics, given the public pronouncements that many of them make on social media, are not obvious role models for the bar and bench. The fact remains that many law professors simply lack the background in legal, moral, and social philosophy to engage with students on the meaning and significance of law at more than a superficial level; i.e., to engage in much more than vacuous sloganeering. (Some do, and I’m sure everyone will choose to think of themselves as the exception.) Even if AI could not produce passable philosophical papers on these issues - and we know it can - the idea that many law professors can offer instruction to a roomful of law students that travels ‘the last mile’ on those issues is, with the greatest respect, implausible.

What about just doing what we have always done, but doing it better, more rigorously? Continuing to focus on the teaching of general legal doctrines, concepts, methods, techniques, but insisting that students learn them at an exceedingly high level - such that every law graduate could critically assess the output of an AI-generated brief or memorandum? Perhaps that kind of high-level mastery would amount to a kind of local knowledge. Maybe. But even if it does, that kind of mastery cannot be delivered in anything like the way we deliver legal education at present. It cannot be massified. Though it is not a popular thing to say, we know full well that most law students do not have a deep understanding of the material we teach; many lack even a superficial understanding. To provide the sort of deep understanding of the law that will be in demand would require vastly more intense, curated, one-to-one, ongoing mentoring, with iterative assessment on every topic. A single professor could not possibly do this with every student we currently enroll. It would not be scalable and we know it.

Back to my central theme. If AI can do all the things we are capable of teaching, and law schools are not capable of teaching much (if anything) else, then what is the case for law schools? A dean must be able to answer that question when it is inevitably raised by external stakeholders. (Yes, it is inevitable. Don’t kid yourselves.) The problem is especially sticky because, for several decades, law schools (like universities more broadly) have defended their existence principally on the basis of the marketable skills and credentials they confer upon graduates. Law schools are unused to defending knowledge as a worthwhile pursuit in itself. To do so now would invite unwelcome comparisons to humanities departments that are themselves in deep trouble.

And, to be clear, deans do not just confront a public relations exercise. Whatever it is that law schools are expected to provide, the dean must ensure that we provide it. I anticipate that there will be a profound level of disruption to legal education – and sooner than people want to believe.

Perhaps there is room for optimism. I don’t want my next dean to indulge in despair. But a would-be dean who tells me I have nothing to worry about - well, I can’t take that person seriously.]]></description>
<dc:subject>schools ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:6345706766ea/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:schools"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legalfutures.co.uk/latest-news/entry-of-pe-puts-focus-on-capital-growth-not-annual-cash-distribution">
    <title>Entry of PE &quot;puts focus on capital growth, not annual cash distribution&quot; - Legal Futures</title>
    <dc:date>2026-05-15T14:51:29+00:00</dc:date>
    <link>https://www.legalfutures.co.uk/latest-news/entry-of-pe-puts-focus-on-capital-growth-not-annual-cash-distribution</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Private equity allows law firms “to build for capital growth rather than cash distribution” and represents a “fundamental shift in how firms can compete”, the Law Firm Growth Summit heard yesterday.

Crispin Passmore told the Legal Futures event in London that when he left his role as an executive director of the Solicitors Regulation Authority in 2018 to launch his consulting practice in 2018, he identified regulatory reform, technology and client pressure as three forces reshaping the market.

“But I underplayed a fourth. Capital. In 2018, capital was circling. It was cautious. It hadn’t yet committed. The investment theses were being written, but the deals weren’t being done at scale.

“In 2026, capital has committed. And everything is accelerating. I speak with newly interested investment banks, venture capital, family offices, private equity, asset managers and sovereign wealth funds almost daily.

“And their reach is far and wide – England and Wales of course, but also the United States, Canada, Australia and increasingly Europe.”

In his keynote speech to the conference, Mr Passmore – founder of Passmore & Oliver Partners – said that investors saw legal markets in the UK and US that were “fragmented, under-managed, under-invested and historically insulated from competition.

“These are markets where the major participants have distributed their balance sheet to zero every year-end for decades, which means very limited long-term investment in technology, no patient capital for M&A, limited capacity to build something that outlasts the current financial year – markets where there are no national brands and where the largest law firm in the world is just one eighth the size of Deloitte or Accenture.”

Client demand was “enormous and largely unmet”, and even sophisticated businesses were trying to exert more control over legal spend “not because they need less law, but because they can’t afford more”.

Mr Passmore explained: “Investors see an opportunity: to bring capital, management discipline, and a longer-term perspective to firms that have been operating with one hand tied behind their backs.”

The private equity investment horizon, typically five years, was actually longer than that of the partnership model, given its focus on year-end profit distribution

This was “a fundamental shift in how firms can compete – for clients, for talent, and for the future”.

He predicted that the pace of change would accelerate. “The question for law firm leaders is no longer whether to engage with external capital – it is what your strategic response would be if your major competitor suddenly has a strong balance sheet, backed by a long-term investor.

“How, and when, and on what terms to engage with investors will become a key strategic driver for all firms. Waiting is itself a strategic choice.”

He described talent as “the defining competitive battleground”, going on: “The firms that can offer genuine equity participation will have a structural advantage in attracting and retaining the best people. Those that cannot, will find themselves losing rainmakers, losing associates, losing clients, and losing ground.

“The talent war is already intense. Capital will intensify it further. If you cannot offer a genuine share in the upside of the business to more and more of your people then you risk becoming a talent farm for those that will.”

He also foresaw the emergence of “genuinely global legal businesses with diversified ownership structures” and the major City law firms needed to act now to be part of this group.

Most importantly, Mr Passmore said, was that “the firms that thrive will be the ones that are clear about their strategic purpose”.

While not every firm needed external capital, they did need to understand their options.

This meant knowing their “enterprise value”. This was not profit per partner but what a sophisticated buyer would pay for their firm and why.

“Most law firm leaders cannot answer that question. Investors answer it before they walk into the room. You should too. It changes how you think about strategy, about M&A, about talent – about everything.”]]></description>
<dc:subject>privateequity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:c98494643956/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law360.com/pulse/modern-lawyer/articles/2449518">
    <title>UK Law Sector's Private Equity Boom Offers Lessons For US - Law360 Pulse</title>
    <dc:date>2026-05-15T14:15:09+00:00</dc:date>
    <link>https://www.law360.com/pulse/modern-lawyer/articles/2449518</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Private equity money is pouring into the U.K. legal sector, fueling a wave of consolidation in consumer-facing practices and offering a glimpse of what it could look like if outside investment in the U.S. legal industry takes off.

More than a decade after the U.K. deregulated its legal sector, private equity firms have become a major player, driving a frenzy of deals activity resembling the "buy-and-build" model investors have followed in other professional services industries like healthcare and accounting.

To name two examples, personal injury firm Fletchers and Stowe Family Law have both been on aggressive acquisition sprees since they were bought by private equity in 2021 and 2017, respectively, and are now two of the U.K.'s largest firms in their respective areas of law.

However, the investment surge has also led to the £342 million ($457 million) buyout of a top-20 U.K. law firm — a deal that thus far appears to be a one-off due to several unique factors — and contributed to a handful of troubling law firm collapses.

"In a way, the U.K. has become a kind of lab rat for the legal industry," said David Morley, the London-based former head of Allen & Overy before the firm merged with Shearman & Sterling in 2024. He now runs a consultancy that guides outside investment in law firms.

Proponents say private equity-backed consolidation is dragging law firms into the 21st century, freeing lawyers up to focus on legal matters instead of administrative headaches like cybersecurity and human resources. Critics worry such investment is undermining lawyers' unique societal role and taking the focus off of serving clients.

Consultants, attorneys and private equity executives say the U.K.'s experience makes for a fascinating case study as U.S. law firms begin to warm to the idea of outside investment after decades of considering it verboten.

"The business model has to change with the times," said Nigel Savage, an academic who guided a deal in which one of the U.K.'s largest law schools sold itself to a private equity firm. Savage is now on the board of directors at Fletchers.

"I think the future is private equity," Savage added. "Now it's the U.S. that's behind the curve."

But the dust is still far from settled, and many observers stress that due to structural differences, private equity's growing involvement in the legal sector might not play out in the U.S. as it has in the U.K.

In England and Wales, for example, legal deregulation occurred at the federal level, while the U.S. effectively has 50 separate regulators because legal ethics policies are determined by state supreme courts, forcing U.S. firms to embrace so-called managed services organizations as a cumbersome workaround.

But for now, the U.K. legal sector remains the only real point of comparison.

"Is your average American lawyer aware of what's going on in the U.K.? No," said Austin Maloney, a U.S.-based private equity attorney and managed services organization specialist at Hunton Andrews Kurth LLP. "Is your average American private equity investor paying attention? Yes."

The Big Bang

In a move similar to the "Big Bang" legislation that deregulated the U.K.'s financial sector in 1986, U.K. Parliament passed the Legal Services Act in 2007 to shake up the stodgy legal industry.

The LSA went into effect in 2011, allowing everything from outside investment in law firms to nonlawyer ownership of firms via "alternative business structures" to law firm listings on stock exchanges. That led to a period of experimentation of ABS firms, followed by a highly anticipated round of law firm initial public offerings from 2015 to 2019.

Now, with the benefit of hindsight, most observers agree that the track record of publicly traded law firms in the U.K. has been a mixed bag at best.

"The energy has gone out of that," said Tony Williams, a principal with U.K.-based Jomati Consultants LLP. "Now most partners think, 'Why would I even bother?'"

Of the six law firms that went public, two collapsed due to fraud and mismanagement, one was taken private after a yearslong slide in share price and three remain.

Of those three, only Keystone Law has a share price that's actually risen since its IPO. Founded in 2002, Keystone is a so-called virtual law firm that provides back-office support but eschews overhead costs like fancy office space, allowing its lawyers to keep roughly 75% of their billings.

James Knight, the founder and CEO of Keystone Law, said he used private equity money to buy out his former partner and bring in business expertise with the expectation of going public later on. But even though it worked for him, he worries that other senior partners might not realize what they're getting themselves into.

"Fundamentally, the only thing private equity cares about is money," Knight said. "They love this idea of 'Buy, build, amalgamate.' That's what they wanted us to do, too, and I had to tell them to put a sock in it."

"But the law firm IPO experiment has been so bad that now it's on to private equity," he added.

Gold Rush Mentality

Private equity is now a major player in the U.K. legal sector — an outcome many never anticipated when the LSA was being debated 20 years ago.

"Nobody in their wildest dreams saw this coming," said Jeff Zindani, a law firm broker who runs Acquira Professional Services. "I don't think that was on the table when they were talking about modernizing the legal profession."

Adil Taha, a private equity executive who has run several ailing law firms, attributes the recent surge in interest to the COVID-19 pandemic.

"While the rest of the world was shut down, law firms made more money during the pandemic than before," Taha said. "Private equity saw how resilient law firms are through macro shocks, and realized just how fragmented the market is."

Thus far, the private equity-fueled deals spree has brought the number of U.K. firms to below 9,000 for the first time since tracking began in 2010, even as the size of the U.K. legal market has continued to grow, according to a recent report.

There are signs that this is just the beginning. Last year, a study by Acquira found that private equity firms invested roughly £1.2 billion in the U.K. legal sector from 2019 to 2024, with nearly half of that in 2024 alone. Comparable figures for 2025 aren't yet available, but a January 2026 survey found that roughly 70% of midsize U.K. law firms fielded calls from private equity investors last year.

Taha, who now runs a consultancy that advises on outside investment in law firms, said it's important not to overstate private equity's impact at this early stage. But he also acknowledges that all the deals activity and press coverage has created a gold rush mentality with law firm brokers, which in turn has led to a bubble in law firm valuations.

"It's getting a bit ridiculous," Taha said.

One attorney with knowledge of the situation, who requested anonymity to speak candidly, said that mindset has spread to the other side of the pond as well.

"The private equity guys are calling up lawyers and telling them, 'Look at Keystone Law. It's trading at 21 times earnings. That's what we can do for you in a few years,'" the attorney said.

Aggressive Expansion

So far, private equity investors in the U.K. legal sector have primarily followed the classic buy-and-build model: Buy a law firm at three or four times annual revenue, juice it with acquisitions, invest in technology and benefit from economies of scale, then resell at a multiple of eight or nine times annual revenue.

In addition to firms like Fletchers and Stowe that have grown aggressively through buying up competitors, the past few years have seen consolidator platform firms, like Beyond Law, Lawfront and Adeptio, spring up.

Starting with one platform firm, these groups aim to buy up regional practices, meaning small or midsize specialist and full-service firms that operate outside the expensive London market. They generally allow acquired firms to retain their name and branding, but consolidate back-office operations like information technology and payroll.

All told, there are now at least a dozen private equity-backed consumer law firms currently operating in the U.K., most of which have followed a similar strategy of expansion, technology investment and cost-cutting.

Late last year, Swiss private equity firm Ufenau Capital Partners purchased a majority stake in Britain's largest personal injury firm, Express Solicitors, for an undisclosed sum, suggesting that investors are beginning to take aim at bigger targets.

Taha said he expects to see more of those kinds of larger deals going forward.

"I think some investors wasted a lot of time fishing in that small pond," he said, referring to deals that saw consolidator firms buy up small firms with just a handful of attorneys.

Practices like personal injury, family law and real estate conveyancing, as well as midsize full-service business firms, are attractive to private equity because the cases they handle are generally more standardized than the complex corporate transactions and disputes that BigLaw firms charge top dollar for.

They also rely more on marketing and less on star partners for revenue, making the departure of key rainmakers less of a risk.

In addition, most small and midsize law firms have only a handful of equity partners that need to sign off on a deal, compared to dozens or even hundreds at BigLaw firms.

Structural hurdles tied to the size and complexity of BigLaw firms have mostly kept investors out of that area in both the U.K. and the U.S. despite intense interest.

The one deal that bucks that trend is the buyout of DWF.

DWF was the last U.K. law firm to go public in 2019 and was taken private by PE firm Inflexion in 2023 for £342 million — roughly £24 million less than its market capitalization when it listed.

That deal seems to hinge on factors specific to DWF, however. DWF is a combined legal and professional services firm, and 60% of its revenue comes from multiyear panel agreements with corporate clients like insurance companies, according to the trade publication PE Hub.

The deal also shows another way that private equity ownership could reshape how law firms are run.

DWF is spending £69.2 million a year to service £270.5 million in debt largely left over from the buyout, according to Law.com International. Last year, the firm generated revenues of £573 million, and its all-important measure of EBITDA — earnings before interest, taxes, depreciation and amortization — was £71 million.

"Those debt levels are fascinating," said Acquira's Zindani. "At a traditional law firm, the partners wouldn't sleep at night. That would be a nightmare."

'A Lot of Heavy Lifting'

Private equity's initial foray into the U.K. legal market has also resulted in a few dismal failures, according to coverage in the U.K. legal press.

For instance, in 2014 private equity firm NorthEdge Capital bought Roberts Jackson, a personal injury firm that specialized in industrial disease claims, similar to a mass tort firm in the U.S. The firm collapsed into insolvency a few years later due to mismanagement and a lengthy dispute with insurers, costing NorthEdge £23 million.

And Parabis, a personal injury and insurance claims consolidator that was one of the first U.K. firms to take on private equity investment, collapsed in 2016. Parabis owed creditors £121 when it fell into insolvency, with private equity firm Duke Street alone owing nearly £70 million.

A postmortem report by the insolvency consultancy AlixPartners said regulatory changes led to a steep drop in the firm's profit margin on the simplistic, fixed-fee insurance cases it handled in bulk. That cash crunch exacerbated revealing deeper problems stemming from a string of overpriced acquisitions.

"Crucially, the LLP failed to fully integrate its business acquisitions," the report said, according to the Law Society Gazette, noting that different parts of the business used different case management and accounting systems.

Similar law firm collapses involving private equity money, like Metamorph, Pure Legal and Kingly, were mostly attributable to a combination of mismanagement and outright fraud, according to reports and regulatory reviews.

Observers say it's difficult to pinpoint whether private equity itself was the driving factor in any of those collapses, and the relatively small sample size makes it hard to draw broader conclusions. But in general, Taha said, a major challenge of investing in law firms is the difficulty of actually changing how they operate.

When he was the CEO of London-based private client firm Child & Child, for instance, Taha decided to raise rates by 20% after conducting extensive market research. The rate hike worked, Taha said, but led to months of strife.

"The partners were distraught," Taha said. "You would've thought I canceled Christmas."

While some senior partners have reaped multimillion-pound windfalls from selling their firms to private equity, the process has raised concerns among some younger attorneys and support staff. Fletchers and Stowe in particular came in for criticism in a Financial Times article, with employees grousing that a relentless focus on productivity and growth has pushed staff to their limits.

Fletchers and Stowe dispute those negative characterizations.

A spokesperson for Fletchers said that since the firm was bought by private equity in 2021 caseloads per attorney have decreased.

Stowe Chairman Ken Fowlie, meanwhile, said private equity investment has been "critical" to the firm's success over the past decade.

"Stowe wouldn't be the firm it is today without the support we've had from our private equity sponsors," Fowlie said.

It appears private equity investment in the U.S. legal sector is following a similar course to what's unfolded in the U.K., with some of the first such deals announced taking place in the personal injury and mass torts spaces.

Charles Martin, a mergers and acquisitions attorney who previously led the London law firm Macfarlanes and still advises on private equity deals, said he expects things will only accelerate on both sides of the pond from here on out, as it did when private equity investors first entered healthcare and accounting.

"The most powerful part of this early stage is the transformation of privately run businesses into an asset class that is truly investable," Martin said. "There's a lot of heavy lifting that must be done to get things to that point."]]></description>
<dc:subject>privateequity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:9bb4f3f21121/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legaltechnologyhub.com/contents/law-firms-want-to-change;-they-just-cant/?_hsenc=p2ANqtz-9ieqmsoDQ0tp7slmhquQtAo2i_5e2WkDcF-neDNyEWkJFLEIauNQOdRZ8Lc9JIrKasfsjj-PWNqf21oE4t4IHmPVFu6g&amp;_hsmi=417739967">
    <title>Law Firms Want to Change; They Just Can’t | Legaltech Hub</title>
    <dc:date>2026-05-10T19:28:40+00:00</dc:date>
    <link>https://www.legaltechnologyhub.com/contents/law-firms-want-to-change;-they-just-cant/?_hsenc=p2ANqtz-9ieqmsoDQ0tp7slmhquQtAo2i_5e2WkDcF-neDNyEWkJFLEIauNQOdRZ8Lc9JIrKasfsjj-PWNqf21oE4t4IHmPVFu6g&amp;_hsmi=417739967</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[At our recent LTH Horizons conference in London, one of the speakers pushed back on the familiar narrative that law firms don’t want to change. In his view, that criticism no longer holds, since many firms are actively deploying AI and trying to drive adoption.

He's right - but understanding that change is necessary is not the same as being able to change. 

Contrary to what many commentators believe, the real constraint is not intent, it’s structure. And until law firms are willing and able to change various structures, they will not be able to change in the way that is required to meet the AI-driven future. 

When we talk about the law firm business model, the conversation tends to begin and end with the billable hour. But the billable hour is only one expression of a broader system. The deeper challenge is that the entire model - economic, operational, and institutional - is calibrated around time, individual effort, and matter-based delivery. The obstacles to change are systemic, which means the response must be too - and, unfortunately, systemic change is really hard. 

 

Structural Disincentives 
The most commonly cited tension in discussions about AI in law firms is the conflict between efficiency and the billable hour: that the economic model of law firms doesn’t make sense in a world where an estimated 44-80% of legal work can be automated using AI. 

Most conversations around this are incomplete. The deeper issue is not simply that AI reduces time; it’s that the law firm economic model is built on time both as a proxy for value and the mechanism through which value is distributed across the organization. Once that foundation begins to erode, the consequences cascade. 

AI doesn’t just make lawyers faster, it changes the very shape of legal work. Tasks that previously required hours of manual human effort can now be completed in minutes or absorbed into repeatable workflows that operate with minimal marginal cost. In that environment, time no longer functions as a reliable unit of measurement. It no longer reflects effort, and increasingly, it doesn’t reflect value. 

This creates an immediate commercial tension. If clients are aware that large portions of legal work can be completed more efficiently, they will push for lower costs (and they are, both aware and starting to push). At the same time, firms that continue to rely on time-based billing lose visibility into how to price that work in a way that preserves margin. The result is a narrowing corridor: pressure on rates from clients, and no clear internal mechanism to redefine value in response. With AI deployment in corporate legal departments reportedly doubling between 2024 and 2025, that client pressure will only intensify.  

But there are more significant impacts internally that are spoken about far less. 

Associate performance, progression, and compensation are still overwhelmingly tied to billable hours. The system assumes that time spent is the clearest and fairest way to measure contribution - rather than, say, merit, or value of work undertaken. As long as that remains true, any shift away from time-based work will create misalignment. Efficiency in this scenario is no longer neutral; it becomes economically and professionally ambiguous. 

Consider the following scenario. An associate contributes to the development of a workflow that automates a recurring category of work for a major client. Once implemented, that workflow reduces the time required to deliver the work by 80% and becomes embedded in the client relationship, generating significant and sustained revenue for the firm. Under the current model, that contribution is largely invisible. 

The associate has not accumulated hours. The value they have created, which is repeatable, scalable, and commercially meaningful, does not map cleanly to existing evaluation frameworks. Compensation, bonuses, and promotion decisions remain tied to time, not to the creation of systems that replace time. The rational response for the associate, ultimately, is to prioritize the activities that are measured and rewarded and deprioritize those that are not. In this way, the system doesn't just fail to incentivize new forms of value creation, it actively discourages them. 

This misalignment extends beyond lawyers. As firms increasingly require expertise in areas such as data science, process design, and applied AI, they face a parallel structural constraint. Non-lawyer professionals are essential to building and maintaining the kinds of workflows and systems that AI enables. Yet law firms are not designed to reward these roles on equal footing. Profit-sharing, status, and long-term incentives remain concentrated within the partnership model. Even prior to partnership, many firms reward practicing lawyers with benefits that exceed those provided to other types of professionals in the business. “Non-lawyers” are often branded as second-class citizens. 

The result is a persistent gap between what the firm needs to build and what it is able to attract and retain. High-impact roles are structurally undervalued, even as their importance increases.

Structural Walls 
If the economic model of the law firm determines what is rewarded, the operating model determines what is possible. And here, the constraints are just as significant, even if they are discussed less frequently. 

Modern law firms are architected around a set of assumptions about how legal work is initiated, delivered, and managed. At the center of that architecture sits the “matter”- a discrete, scoped engagement, owned by a supervising partner, staffed by a team of lawyers, and priced according to expected time input. This construct has served firms well for decades. But it’s fundamentally mismatched with the current direction of travel. 

Much of the value created by AI does not sit comfortably within a matter-based framework. It emerges instead from the development of repeatable workflows, productized services, embedded processes, and continuously improving systems. These are not discrete engagements. They are ongoing capabilities - built once, refined over time, and deployed across multiple clients and use cases. 

A matter is episodic. It begins and ends. A workflow, once operationalized, persists. It cuts across matters, clients, and even practice areas. It's not easily “owned” by a single partner, or even, necessarily, by a lawyer. Nor is it naturally priced as a one-off engagement. And yet, it’s exactly this kind of capability that will define competitive success in an AI-enabled market. 

The friction between these two models - episodic matters versus continuous workflows - creates a series of structural tensions. 

First, ownership becomes unclear. Law firms require a supervising partner to take responsibility for each matter. This is a sensible mechanism for managing legal risk, but it doesn’t translate cleanly to multidisciplinary, system-driven work. When value is created by teams that include lawyers, technologists, data specialists, and operations professionals, the idea of a single “owner” who must be a lawyer becomes both artificial and restrictive. 

Second, pricing struggles to keep pace. Traditional pricing models are designed around scoped pieces of work. They don't easily accommodate offerings that are ongoing, embedded, or subscription-based in nature. While some firms have experimented with alternative fee arrangements, these are often layered onto the existing model rather than replacing it. As a result, they inherit many of the same limitations. 

Third, the commercial functions of the firm - marketing, business development, and sales - are not equipped to support these new types of offerings. Law firms are highly sophisticated in selling bespoke legal advice. They are far less experienced in positioning, packaging, and selling products, managed services, or operational capabilities. Where new offerings do emerge, they often struggle to gain traction - not because they lack value, but because the firm lacks the mechanisms to take them to market effectively. 

Finally, the extension of legal workflows onto the client side introduces entirely new requirements. As firms begin to embed tools, processes, and AI-enabled systems into client environments, the nature of the relationship shifts. Delivery becomes more continuous. Support expectations change. New roles are required to manage and maintain these systems. Yet most firms have not built the infrastructure or the career paths to support this kind of work at scale. 

Layered on top of these operating constraints are institutional considerations that further slow change. Insurance structures, tax treatments, and regulatory frameworks are all calibrated to the traditional model of legal service delivery. Moving beyond that model is not simply a strategic decision; it often requires navigating complex and unfamiliar territory with which firms are understandably cautious to engage. 

Even where leadership is aligned around the need for change, continuity presents another challenge. Law firm governance structures, with relatively short leadership cycles, make it difficult to sustain long-term transformation efforts. Strategies evolve, priorities shift, and initiatives are reset. The result is a pattern that is familiar across the market: bursts of innovation activity that fail to translate into sustained structural change. 

The operating and institutional architecture of the firm is simply not designed to support the forms of value creation that AI enables, and that the market now requires. As a result, even well-conceived initiatives struggle to deliver genuine value. 

 

What Would It Take to Change? 
If the barriers to transformation are structural, then the responses must be as well, but this is where many discussions about innovation in law firms lose traction. The focus tends to be on tools, pilots, and incremental improvements. These are important in their own right, but insufficient to address the underlying constraints. The question is not whether firms can adopt AI. They can, and, in most firms, they are. The question is whether firms can realign their structures to capture the value that AI makes possible. 

Some firms have attempted to navigate this challenge by creating separate subsidiaries or innovation arms. These entities sit outside the core partnership and are designed to operate with greater flexibility, free from some of the constraints that define the main business. In certain cases, this approach has enabled meaningful experimentation and the development of successful new offerings (see, for example, Cleary X, which has just launched CX+, a legal tech product for corporate legal departments, and SixFifty, Wilson Sonsini’s software subsidiary, the recent sale of which proves that investment in secondary businesses can pay off for law firms). Done well, subsidiaries offer a real third-horizon option—a way to compete in a new market without dismantling the existing one. The risk is that by relocating innovation to the periphery, firms insulate the core from change, so that the mothership, left largely unchanged, risks atrophy while innovation flourishes at the edges. Without parallel change at the center, the firm risks becoming structurally divided between where innovation happens and where value is still primarily generated. 

A more difficult path is to begin reshaping the core business. This does not preclude a subsidiary strategy; in fact, the firms best positioned for the future are likely to be those that manage to do both. But without movement at the core, even the most successful subsidiary is unlikely to be sufficient to shift the trajectory of the firm itself.  

This doesn't require wholesale reinvention overnight. But it does require deliberate movement in a few critical areas, and given the competing forces currently at work in the market, that movement has to begin with some urgency. 

First, firms need to develop the ability to price value independently of time. This goes beyond alternative fee arrangements. It requires a more fundamental understanding of where value is created in AI-enabled delivery, and the confidence to anchor pricing accordingly. Without this shift, efficiency gains, which is where too many firms have stayed focused in the GenAI era, will continue to translate into margin pressure rather than competitive advantage. 

Second, firms need to operationalize legal workflows in a way that persists beyond individual matters and individual lawyers. This means moving from isolated pilots to embedded systems - capabilities that are maintained, improved, and deployed at scale. It also requires creating roles, incentives, and career paths that support this kind of work over the long term. 

Third, firms need mechanisms to sustain strategy across leadership cycles. Transformation at this level rarely happens within a single term of office. It requires continuity of vision, investment, and execution. Without that continuity, even the most well-articulated strategies will struggle to take hold. 

Underlying all of this, though, is a more immediate imperative. 

Firms need to identify, now, where their future differentiation will come from. Not in abstract terms, but in prioritizing the right practices and clients, and in focusing on concrete workflows, capabilities, and client-facing offerings. In an environment where AI is rapidly becoming table stakes, competitive advantage will not come from access to technology. It will come from how that technology is embedded into the way work is done. 

This is where the distinction between incremental improvement and structural change becomes most visible. Using McKinsey's three horizons framework for innovation - optimize, extend, transform - most firms are active in the first two, driving efficiency and exploring adjacent sources of value. Far fewer are engaging with the third: the development of fundamentally different models of legal delivery, in areas where they have special expertise.  

And yet, it's in this third horizon that the structural constraints of the current model are most exposed. Firms are, in effect, attempting to compete in a fundamentally different market while operating within structures designed for a previous one. As long as that remains the case, progress will be uneven and  limited. 

Change is possible, but it’s not frictionless. The next few years will require firms to make explicit choices about what they are willing to adapt, and, in some cases, what they are willing to let go. So the better question is no longer whether firms want to change. It's which ones are prepared to. 

]]></description>
<dc:subject>firms ai culture pricing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:c55078190ab7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:firms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:culture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:pricing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legaltechnologyhub.com/contents/the-shift-beyond-prompting-why-legal-ai-is-moving-to-systems-that-act/?_hsenc=p2ANqtz-9gt9QUprf7Bwj2h0JF_-mHDoo0oSqAtwpKz_ZApfd6jFbpVCYZqn4dJyL5jjopbh1CoJ0za1rvLWXWcm2OjIF1hywibw&amp;_hsmi=417091366">
    <title>The Shift Beyond Prompting: Why Legal AI Is Moving to Systems That Act | Legaltech Hub</title>
    <dc:date>2026-05-05T18:42:04+00:00</dc:date>
    <link>https://www.legaltechnologyhub.com/contents/the-shift-beyond-prompting-why-legal-ai-is-moving-to-systems-that-act/?_hsenc=p2ANqtz-9gt9QUprf7Bwj2h0JF_-mHDoo0oSqAtwpKz_ZApfd6jFbpVCYZqn4dJyL5jjopbh1CoJ0za1rvLWXWcm2OjIF1hywibw&amp;_hsmi=417091366</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Standard playbooks enable agentic systems to process routine contracts at scale. But non-standard scenarios—complex indemnification structures, cross-border regulatory overlap, systemic legal change—depend on how decision rules are defined upfront. The system will act either way. The question is whether it escalates uncertainty or proceeds with misplaced confidence. At this level, prompt engineering becomes a form of risk management. 

The pattern reverses in high-stakes, non-routine work. Novel regulatory questions and complex, precedent-free M&A structures fall outside system design. In these cases, the lawyer’s ability to construct a precise prompt remains a distinct advantage. The skill endures exactly where standardization breaks down. 

The reframe is straightforward, but its implications are not: prompt engineering will soon no longer be the primary interface between lawyers and AI. In a systems-driven model, it moves upstream—embedded in the design of workflows, guardrails, and decision logic that operate without constant instruction. 

The shift is not in what AI can produce on demand, but in what it can carry forward without being asked. Context persists. Work progresses. Decisions are anticipated rather than initiated. 

Its impact extends beyond efficiency. It reshapes where expertise resides, how advantage compounds, and what it means to use technology in legal practice. The lawyers who gain ground will not simply be those who know how to prompt, but those who understand how work can be structured, delegated, and governed within systems that operate continuously. 

What emerges alongside the interface—and increasingly beyond it—is something more subtle but consequential: systems that carry context, execute intent, and extend judgment across time. ]]></description>
<dc:subject>ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:e173493b1656/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6461619&amp;dgcid=ejournal_html">
    <title>Private Equity’s Law Firm Workaround: MSOs, Rule 5.4, and the Governance Gap by Lev E. Breydo :: SSRN</title>
    <dc:date>2026-05-01T20:31:39+00:00</dc:date>
    <link>https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6461619&amp;dgcid=ejournal_html</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Private equity is moving aggressively into the legal profession—and its oversight infrastructure is wholly unprepared for this generational shift. To work around prohibitions against nonlawyer ownership, investors are repurposing the management services organization (MSO): a split-entity model in which attorneys retain the regulated practice, but investors acquire the firm’s operating platform. 

This Essay provides the first systematic account of PE investment in law firms and the governance gap in which it is occurring—a vacuum unrecognized by the ABA, state bars, or the courts. The playbook is well-trodden, and the risks are not hypothetical. In just a few years, private equity fundamentally reshaped accounting through hundreds of transactions, with regulators scrambling only after the fact. Law is next.

The MSO model rests on the fragile assumption that "business operations" and "legal practice" can be clearly and durably separated. Healthcare and accounting experience proves otherwise, with similar split-structures consistently exhibiting formality erosion and investor “control creep” through financial and operational pressure. Governance tensions also run deep: the structurally conflicted MSO board must build value while policing its own influence over the interlinked law firm.

The problem is not the MSO per se, but the transactions proliferating in darkness without guardrails. This Essay proposes a three-part governance framework: (i) structural safeguards limiting MSOs to genuine support functions; (ii) independent directors and a board ethics committee; and (iii) ongoing compliance monitoring. The costs of the governance gap—compromised representation and reduced independence—will fall on the public, not investors. The window to act is closing fast. ]]></description>
<dc:subject>privateequity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:62c2ef6f12d6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law360.com/pulse/modern-lawyer/articles/2468330">
    <title>Law Firm Pricing Progress May Lag Tech Advancement - Law360 Pulse</title>
    <dc:date>2026-05-01T20:31:15+00:00</dc:date>
    <link>https://www.law360.com/pulse/modern-lawyer/articles/2468330</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[When asked to identify the top drivers of profitability for their firms, 84% of respondents pointed to pricing as the top lever they used last year.

The next-highest lever was billing and collections efficiency, which was selected by 60% of respondents, followed by demand and market growth; cost structure optimization and productivity; and capacity utilization.

The factor on the list that the fewest respondents said drove profitability at their firm was technology and AI, at 12%.

"The 72-point gap between pricing and technology … reveals a market still in the early innings of technology-driven profit transformation, signaling significant upside for firms that move early on AI-enabled pricing and analytics," the report said.

Fifty-seven percent of respondents to LawVision's survey included leaders at firms with fewer than 250 lawyers, and the remaining 43% were at larger law firms. Approximately one-quarter of respondents were at law firms with 500 or more lawyers.

"Some believe that AI can reduce demand, and if firms don't price differently than they do now … There's definitely a risk to relying on pricing to drive profitability," said the report's author, Mark Medice, pointing to data that shows around 80% of law firm work in the U.S. is currently performed on a billable hour basis.

"There's a bigger opportunity to think of pricing in a different way that awards innovation, to come up with an economic model that serves the client well and drives profitability," Medice added.]]></description>
<dc:subject>ai pricing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:df4ae780439f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:pricing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://acoup.blog/2026/03/25/miscellanea-the-war-in-iran/">
    <title>Miscellanea: The War in Iran – A Collection of Unmitigated Pedantry</title>
    <dc:date>2026-05-01T20:21:06+00:00</dc:date>
    <link>https://acoup.blog/2026/03/25/miscellanea-the-war-in-iran/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[This post is a set of my observations on the current war in Iran and my thoughts on the broader strategic implications. I am not, of course, an expert on the region nor do I have access to any special information, so I am going to treat that all with a high degree of uncertainty. But I am a scholar of military history with a fair bit of training and experience in thinking about strategic problems, ancient and modern; it is this ‘guy that analyzes strategy’ focus that I want to bring to this.

]]></description>
<dc:subject>global</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:12af035a89ec/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:global"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://thewildcat.co.uk/project-items/noslegal/">
    <title>NosLegal – wildcat</title>
    <dc:date>2026-05-01T20:12:43+00:00</dc:date>
    <link>https://thewildcat.co.uk/project-items/noslegal/</link>
    <dc:creator>JordanFurlong</dc:creator><dc:subject>competence schools taxonomy</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:7c507692d9f1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:competence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:schools"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:taxonomy"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.lek.com/insights/business-services/how-legal-msos-are-restructuring-law-firm-operations">
    <title>How Legal MSOs Are Restructuring Law Firm Operations | L.E.K. Consulting</title>
    <dc:date>2026-05-01T20:07:09+00:00</dc:date>
    <link>https://www.lek.com/insights/business-services/how-legal-msos-are-restructuring-law-firm-operations</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[The legal services market is large and fragmented and generates consistent demand. Yet law firms have historically underinvested in technology and back-office infrastructure, operating more as attorney-led partnerships than modern service businesses.

This underinvestment is becoming harder to sustain. Client acquisition has grown more competitive, technology expectations have risen and compliance requirements have expanded. But traditional partnership structures constrain the capital needed to keep pace.

The barrier has been regulatory: ABA Model Rule 5.4 restricts nonlawyer ownership, fee sharing and control of law firms across most U.S. jurisdictions. Rather than wait for those rules to change, firms and investors have organized around them through managed services organizations (MSOs).

Momentum is building. Uplift Investors formed Orion Legal MSO with Dudley DeBosier Injury Lawyers in 2025, and legal industry observers report that roughly a dozen MSO deals closed in 2025, primarily in personal injury and mass tort practices.

L.E.K. Consulting has written previously about alternative business structures (ABSs), which allow direct equity investment in a handful of states. But MSOs remain the more established pathway, working across jurisdictions without requiring new regulatory approvals.

The legal MSO model: Definition and context
The MSO model originated in healthcare, where regulations prevent nonphysicians from owning medical practices. MSOs emerged as a workaround: A separate entity handles administrative functions while physicians retain ownership and control of the clinical practice. The structure has since scaled across dentistry, ophthalmology and other healthcare specialties.

In the context of legal services, an MSO is a separate operating company that provides back-office services to a law firm under a long-term management services agreement. Under this agreement, attorneys control all legal work while the MSO owns and runs the business infrastructure, typically handling marketing and intake, technology and data systems, finance and accounting, human resources (HR) and recruiting, facilities and procurement, and administrative operations. The MSO often employs and sets performance metrics to manage the firm’s entire nonlegal workforce.

How MSOs differ from ABSs and traditional outsourcing
ABSs allow direct equity ownership in law firms, whereas MSOs maintain separation; investors own the MSO entity, which contracts with the attorney-owned law firm to provide services.

Traditional outsourcing handles discrete tasks such as payroll, information technology (IT) support or bookkeeping. MSOs take over the entire business side: all back-office operations, technology infrastructure and administrative functions under a single long-term contract.

Some platforms, such as Federate, Legal Back Office or Delegate.Legal, provide MSO-like operations through an outsourced service model. Investor-owned MSOs are built around an investable entity with long-term contract economics.

Law firm functional taxonomy and MSO structure
Law firms operate across six functional areas. Under the MSO model, legal work and attorney-supervised roles remain with the firm. Everything else moves to the MSO: marketing and intake, technology and data systems, finance and accounting, HR and recruiting, facilities and procurement, and administrative operations.

These functional areas break down as follows:

Legal delivery and professional judgment. All attorney work, legal strategy, case decisions and supervision of substantive legal work must remain with the attorney-owned law firm under ABA Model Rule 5.4.
Client relationships and regulated activities. Client engagement agreements, client files, trust accounts and conflicts management must stay with the law firm because they involve fiduciary duties that cannot be delegated to nonlawyers.
Business development and marketing. Lead generation, intake operations, call centers and advertising spend can move to the MSO. Synergies emerge from scale, data infrastructure and specialized expertise that many firms cannot build internally.
Operations and technology. IT systems, case management platforms and process automation can move to the MSO. Synergies come from centralized purchasing power and access to specialized technical talent.
Finance and human capital. Accounting, HR, recruiting, payroll and benefits administration can move to the MSO. Synergies include economies of scale in benefits negotiation and centralized payroll systems.
Real estate and facilities. Office leases as well as equipment, facilities management and vendor contracts can move to the MSO. Synergies arise from bulk purchasing and lease negotiation leverage.
The paralegal question. Paralegals sit at the boundary. They may be employed by the MSO but must remain under attorney supervision from the law firm and cannot provide independent legal advice. North Carolina State Bar guidelines confirm that paralegals can be employed by entities other than law firms as long as they perform substantive legal work for which a lawyer remains responsible.

The organizational chart below illustrates how these functional areas split between the law firm and the MSO in a typical midsize firm.

Image
Figure 1 represents typical midsize firm law firm org chart

How MSOs get paid without fee splitting
All legal fees belong to the law firm. The MSO is compensated through a management fee defined in the management services agreement. ABA Model Rule 5.4 prohibits this fee from being calculated as a percentage of the law firm’s legal revenues or profits. Texas Ethics Opinion 706 (February 2025) confirmed this prohibition.

Common compliant fee structures are flat monthly or annual fees or cost-plus pricing where the firm reimburses the MSO for actual operating costs plus a predetermined margin.

The fee must reflect fair market value; when benchmarked against comparable market pricing, it should fall within a reasonable range. MSOs document their costs, pricing methodology and industry benchmarking to demonstrate compliance.

The law firm collects client revenues, pays the MSO its management fee and distributes the remaining funds to partners after covering legal expenses and attorney compensation.

What this means for law firms and investors
Healthcare provides a useful precedent. When corporate practice of medicine doctrines prevented nonphysicians from owning clinics, the MSO model emerged as a work-around. The model has since scaled nationally across dentistry, ophthalmology, anesthesia and a number of other specialties.

Legal MSOs work when the division between legal practice and business operations is genuine and when the MSO delivers operational value. The value proposition differs by stakeholder:

For law firms: MSOs provide a path to professionalize the business side, attract capital and build scalable infrastructure without violating ethics rules.

For investors: MSOs offer exposure to legal services within existing regulatory constraints. The model is structured around fee-based cash flows from the MSO. Returns come from operational efficiencies, margin expansion and the ability to scale a platform across firms.

As firms face increasing operational complexity and investors seek entry into a large, fragmented market, MSOs have become the most practical structure available.

But structure alone doesn’t guarantee success. In our next article, we’ll look at how investors evaluate legal MSOs, where the model fits best and what breaks when these deals are done poorly.]]></description>
<dc:subject>privateequity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:8960e0fee864/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.canadianlawyermag.com/resources/professional-regulation/law-that-replaces-law-society-of-bc-diminishes-bars-self-regulation-is-constitutional-bc-court/394038">
    <title>Law that replaces Law Society of BC, diminishes bar’s self-regulation is constitutional: BC court | Canadian Lawyer</title>
    <dc:date>2026-04-30T15:48:50+00:00</dc:date>
    <link>https://www.canadianlawyermag.com/resources/professional-regulation/law-that-replaces-law-society-of-bc-diminishes-bars-self-regulation-is-constitutional-bc-court/394038</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[A British Columbia law that eliminates the Law Society of BC and reduces the power that lawyer-elected lawyers have over their regulator is constitutional, the BC Supreme Court ruled Wednesday, allowing the law to be implemented.

Passed in 2024, the Legal Professions Act will replace the LSBC with a new regulatory body that oversees lawyers, paralegals, and notaries.

The legislation also reduces the proportion of seats that lawyer-elected lawyers will hold on the new regulator’s governing board, effectively giving them a minority presence alongside board members elected by notaries, paralegals, the Lieutenant Governor in Council, and the board itself.

At the LSBC, which only regulates lawyers, approximately 80 percent of board seats are currently held by lawyers elected by members of the bar – an arrangement that the regulator argues is key to the bar’s ability to self-regulate.

The LSBC and the Trial Lawyers Association of BC had filed constitutional challenges to the Legal Professions Act shortly after the BC legislature passed the law.

In a 63-page decision on Wednesday, BC Supreme Court Chief Justice Ronald Skolrood said the central issue in the case was whether the BC legislature had acted beyond its authority by passing the Legal Professions Act.

He concluded that the legislation “does not improperly undermine the independence of the bar and is not ultra vires the provincial legislature. Nor does it violate the Charter.

“The actions of both the LSBC and the TLABC are dismissed,” Skolrood said.

The chief justice noted that in their written submissions and at trial, the Crown “offered no clear rationale for the significant changes brought about to the regulation of lawyers under [the Legal Professions Act] or to the jettisoning of the long-established practice of consultation and collaboration with the legal profession about changes to their governing legislation.”

However, the chief justice agreed with the Crown’s argument that “absence of a clear justification for the legislation, as well as the failure to obtain consensus with lawyers and the public, are irrelevant to the constitutionality of the legislation ultimately enacted by the legislature.”

Skolrood said he agreed with the plaintiffs’ stance that the independence of the bar is an “unwritten constitutional principle.” But he ultimately concluded that the BC legislature has the authority to determine how lawyers should be regulated, writing that "while the legislature has historically chosen a self-governance model, that model is not constitutionally mandated as a requirement for maintaining an independent bar." 

In a statement, Trial Lawyers Association of BC President Rebecca McConchie said the organization was “disappointed about the outcome of today's decision, but we will be reviewing it over the course of the coming days to determine whether we should initiate an appeal to the BC Court of Appeal.

"Given the public interest significance that this case represents and given the essential importance of preserving the independence of the legal profession and the rights of our clients, I think I can say now that an appeal of this decision is likely,” McConchie added.

The LSBC said it is also considering an appeal. LSBC President Thomas Spraggs said, “This case was about protecting the ability of lawyers to serve their clients without government intrusion and ensuring that regulation of the profession remains focused on protecting the public interest in the administration of justice. This decision does not change that position."

The Canadian Bar Association was among several intervenors in the case. In a joint statement, Canadian Bar Association President Bianca Kratt and CBABC President Patricia Blair said the organization intervened in the case “to defend the independence of the legal profession.”

Kratt and Blair added that “when Canadians seek legal counsel, they should be confident that their lawyer’s advice is wholly independent of government preferences or pressure. Lawyers must be answerable to their clients, their professional obligations, and the courts – not to the state.”

Shortly after the LSBC and the Trial Lawyers Association of BC filed their challenges in 2024, the BC Supreme Court rejected the organizations’ pleas for an injunction to suspend the law until the litigation was resolved, forcing the LSBC to comply with the legislation's transitional provisions. This included having LSBC benchers appoint four members to a transitional board to help implement the legislation.

Last fall, weeks before the case went to trial, BC Attorney General Niki Sharma told the LSBC and the Society of Notaries Public of BC, the province’s regulator for notaries, that the province would not move forward with implementing the law without notice until the BC Supreme Court issues its decision in the case.

At trial, the LSBC and the Trial Lawyers Association separately told Skolrood that the Legal Professions Act undermines the bar's independence, which has long regulated itself. Counsel for the LSBC clarified that it agrees with some provisions of the law, including the creation of a single regulator for lawyers, notaries, and paralegals in BC.

The Crown, meanwhile, argued that the Legal Profession Act does not interfere with lawyer independence to an unconstitutional degree.

Among the case’s intervenors, the Canadian Bar Association and the Law Society of Manitoba sided with the plaintiffs. But the Society of Notaries Public of BC and the Indigenous Bar Association were less swayed by their arguments of unconstitutionality. The latter also pushed back against the plaintiffs’ argument that the law, which establishes an Indigenous council to advise BC’s new legal regulator on aligning its practices with BC’s reconciliation mandates, interferes with lawyers’ independence.

A similar scenario is playing out in Ontario, where the legal regulator revealed similar plans to slash the proportion of lawyer-elected lawyers on its governing board shortly after BC passed the Legal Professions Act.

The Law Society of Ontario has since amended its plans to reduce the board's size while still allowing lawyers to maintain a 65 percent majority. Benchers are slated to vote on the new proposal on Thursday.

Spokespeople for the BC Attorney General did not immediately provide comments on Wednesday’s decision.]]></description>
<dc:subject>regulation governance access</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:ecdb1c64f2c3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:regulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:governance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:access"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.argmin.net/p/cosma-shalizi-is-aware-of-all-internet">
    <title>Cosma Shalizi Is Aware of All Internet Traditions</title>
    <dc:date>2026-04-28T20:13:17+00:00</dc:date>
    <link>https://www.argmin.net/p/cosma-shalizi-is-aware-of-all-internet</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[AI is a cultural technology for several years. He’s gone through several iterations of what that means and what it implies, but mechanized tradition is the characterization that resonates most with me. Mechanized tradition of Barzun’s artificial intellect is a far better description of GenAI technology than “artificial intelligence.” This frame helps us get away from the silly C-suite sci-fi navel-gazing about the personalities inside the data centers. Claude is not a person. It is a mechanized intellect. A Lore Laundering Machine. The frame of mechanized tradition helps me build a social metascience of our LLM condition.]]></description>
<dc:subject>ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:67ad7bc3f895/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.victorialawfoundation.org.au/research-projects/measure-for-measure">
    <title>Measure for Measure: A People‑Centred Approach to Tailoring Justice | Victoria Law Foundation</title>
    <dc:date>2026-04-28T20:05:56+00:00</dc:date>
    <link>https://www.victorialawfoundation.org.au/research-projects/measure-for-measure</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Measure for Measure is foundational research that aimed to map and understand a range of justice initiatives from across Victoria. It is an effort to identify the common elements of success in responding to legal need and capability, and to discuss what that means for practice, evaluation, and better outcomes at a range of levels.]]></description>
<dc:subject>access</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:e12f37cb14ee/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:access"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legalfuel.com/as-ai-allows-lawyers-to-better-serve-clients-firms-must-prepare-for-the-post-ai-world/">
    <title>As AI Allows Lawyers to Better Serve Clients, Firms Must Prepare for the Post-AI World | LegalFuel</title>
    <dc:date>2026-04-28T18:11:49+00:00</dc:date>
    <link>https://www.legalfuel.com/as-ai-allows-lawyers-to-better-serve-clients-firms-must-prepare-for-the-post-ai-world/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[The legal industry has reached a pivotal turning point where the integration of artificial intelligence is no longer a futuristic concept but a daily operational reality. Recent industry insights suggest that over 80% of legal tasks ranging from contract review and research to client intake now have the potential to be automated or significantly altered by AI. As these technologies begin to handle the routine work traditionally assigned to junior associates, the profession faces a critical shift. Survival in this post-AI landscape requires practitioners across all firm sizes to actively level up their skills to navigate a world where traditional task-based legal work is rapidly evolving.

]]></description>
<dc:subject>jf ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:5418070ea850/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:jf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/04/21/norm-laws-hires-from-ropes--gray-sidley-discuss-their-tech-driven-transition/?kw=Norm%25252BLaw%25252527s%25252BHires%25252BFrom%25252BRopes%25252B%25252526%25252BGray%25252C%25252BSidley%25252BDiscuss%25252BTheir%25252BTech-Driven%25252BTransition&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803">
    <title>Norm Law’s Hires From Ropes &amp; Gray, Sidley Discuss Their Tech-Driven Transition | Law.com</title>
    <dc:date>2026-04-27T21:37:29+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/04/21/norm-laws-hires-from-ropes--gray-sidley-discuss-their-tech-driven-transition/?kw=Norm%25252BLaw%25252527s%25252BHires%25252BFrom%25252BRopes%25252B%25252526%25252BGray%25252C%25252BSidley%25252BDiscuss%25252BTheir%25252BTech-Driven%25252BTransition&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Over the last few months, hybrid law firm Norm Law announced new hires from several Am Law 100 firms, including Ropes & Gray and Sidley Austin.

In early April, Norm Law appointed former Ropes & Gray partner Bill Mone to serve as partner and head of private equity, and in January the firm appointed former Sidley Austin executive committee chair Mike Schmidtberger to be its chair and head of investment funds and regulatory.

Mone and Schmidtberger sat down with Law.com to discuss how they plan to operate out of their new hybrid law firm, how they will interact with artificial intelligence agents and the law firm’s relationship with software company Norm AI.

This Q&A has been edited for length and clarity.

What has it been like being a part of a law firm trying to be more tech-forward from the start?

Schmidtberger: It's been a wonderful, exciting, fast-paced transition. The technology really is in a place where it's a differentiator, and that wasn't true [about] a year ago. I give [Norm AI founder and CEO] John Nay a lot of credit for seeing where it was going to go and then the possibilities of really deploying it in the compliance space first, but then at higher levels, including really at the practice of law level.

The transition is unique because it's not a copilot method or an approach where you work side by side with AI. This idea of being AI first is really to train the AI agents to build them at such a level of sophistication that they do the full first pass of the work autonomously and in conformity with the client's playbooks, guidelines, proclivities and the rest, so really at the level that a really well-trained third-year would do the work. That is a different adjustment in the way you're practicing. In some ways, it's a relief because there are things you don't have to do as a lawyer that really aren't part of the life of the mind; they're just routine. In some ways it is quite an adjustment, but pretty welcome.

Mone: I was really surprised by the number of inbound LinkedIn messages and emails and calls I got from not just clients, but other PE sponsors I hadn't even really worked with or investment bankers saying, "This sounds really interesting. Let's meet and talk about this." It's something that has captured the imagination of not just lawyers, but obviously clients and others in the marketplace in the midst of a potential transformation of the entire knowledge economy. Everyone is focused on AI. So from the moment I signed up, there's been lots of inbound interest to the point where I said, "I better get down here, start right away, start figuring things out so I can start responding with some actual knowledge and data, not just high-level statements."

How are clients understanding this law firm and how it operates with technology, and how does transparency work in your experiences so far?

Schmidtberger: The way clients are interacting is like any other law firm. They have access to a partner with real domain expertise and real trust in the market, and we still are in the process of onboarding. We're only about 15 lawyers right now, but we'll be 25 by the first week of May. We have a pipeline of laterals that were waiting to join us, and they've given notice at their firms. We are going to grow substantially, but the model is one where the client is going to interact with Norm Law, just like they would continue to interact with their legacy counsel and have a person with real knowledge and trust that knows them, and then they will work with more senior associates.

The difference is that at the lowest level, you have an automated workflow that leads up into the firm, and so clients are very interested, particularly also around the quality, because the knowledge that is embedded into the domain knowledge and the client knowledge that is embedded into the agents is never lost. You don't have the same slippage that you have with associate turnover or lateral partner movement.

Moreover, it's accessible by in-house, so they can not only see the latest iteration of the contract, but they can see all the annotations that led to that version and why it's there, why they gave on some points, didn't give on others, how often they did it. If they want to go back to the original source document, they can do that, it's just much more powerful. They're interested in that respect too, because it frankly empowers the in-house legal in a way that currently they can't do without being charged for it. ... They're very interested in the preservation of that knowledge and the ability to leverage that knowledge within the legal department permanently, and they're interested in speed and the fact that it can go faster.

Mone: We had an initial meeting last week talking about basically building the agents and sub-agents, which we'll base our private equity transactions platform. It's going to be training agents to do the types of things that a third-year associate used to do completely manually, which is you get a draft merger agreement, ... you're meant to review it and pull together comments and issues within whatever time frame you're given. It's a combination of, “Well, how do you train the agent? How do you tell it what to do?” Well, it's got to come from some set of human knowledge and experience and practice. That's actually something I'm really excited about doing, taking apart a merger agreement, purchase agreement and block by block, piece by piece of it, training the agent to be able to assess an agreement like that with nuance and suggest changes and say where it's deviating from market practice or client preferences.

At some level, clients are going to be interacting with us the way they would at any law firm, but I feel like if I don't have a very fundamental understanding of how the technology works, what I'm relying on to deliver at the end of the day, I won't be doing my job and I won't be as effective. I'm focused right now on building a team of people.

Schmidtberger: I've been doing some of that in the investment management space, and both Bill and I have built associates before. They come in as first and second years and you train them and teach them, and that is a very analog thing in the old world, but that's the only way the associates really learned in the past. I'm doing that again, but everything I am saying is being taken down and permanently embedded in teaching an agent how to do it instead of teaching a new associate. The difference for the people at Norm Law is they'll have to do that only one time because once they've done it, that agent is not going to quit. ... We are not hiring associates with planned obsolescence, so it is not bringing in a whole bunch of people and winnowing them out. We are hiring people as we need them, and then the expectation is we will teach them, and they will grow to whatever level they grow, but we don't need to run them at two o'clock in the morning because the AI can work at two in the morning. We can create a better and more permanent career path for our humans, and that will be a step forward in the practice. They call it “downloading your brain.”

You are still planning on hiring associates, but does training the agents as well lift some of the burden from them?

Mone: At least in an M&A practice, I'd say there's some work that's just grunt work that's just multiple junior associates, many hours [spent] slogging through a data room. I'm not sure that work really makes you a better lawyer over time. It does lead to burnout, and it turns people off to the practice, but then there are other things we're going to be able to automate that have been good training tools for lawyers. When you're given a draft merger agreement, it's important that part of your learning is to go through it and figure out, okay, what's missing? Where are the issues? Where are the pitfalls? Where are the risks? And that's something that you do develop as a junior lawyer over time. ... There's going to be a balance to be struck between, if we're able to automate too much, there's potentially a gap in learning.

How do Norm Law and Norm AI interact with each other?

Schmidtberger: Norm Law is a New York LLP, and Norm AI is a Delaware corporation, but there is a synergy or symbiosis between them. Norm AI develops a technology, including the legal engineering and the hardcore engineering that builds also the way information moves within the different workflows and how it gets from automation to human and back and all the rest. All of that technology is being built at Norm AI and then it is utilized by Norm Law by the lawyers to work through the output. First the input comes in from the clients and then work through the output, deliver it back to the client, but then the domain knowledge of the lawyers goes back into the legal engineering at Norm AI to make the models more up to date, more efficient, more knowledgeable. There is a symbiotic circle that happens in ultimately delivering the technology benefits to Norm Law, gaining the additional client information, domain knowledge, and that's circling back in and making the technology better and it just keeps going. They interact every day, but they interact in parallel.

Norm AI does other things. It does compliance product and software solutions and the rest, much of it around regulated spaces. ... There will be things Norm Law does that don't relate to Norm AI because as a law firm, there will be things that don't need technology and that we will do as a law firm, but there is a great deal of parallel movement in these workflows that we're identifying with clients.

In 2020, the hybrid law firm Atrium shut down, and it had a similar concept to Norm as a software company and a law firm. What exactly is powering Norm Law differently from Atrium?

Schmidtberger: Gen AI is a paradigm shift. We will never go back to where we were before gen AI, and Atrium was absolutely on the right path. They saw a place where technology could be a real differentiator. The problem is the technology wasn't yet where it is today. ... There's enough understanding of how gen AI is a differentiator at the boardroom of many clients and the CEO suite and the general counsel suite, that it really is a different environment, and it's just the bad luck that Atrium started in 2020, but they had the right idea.]]></description>
<dc:subject>ai-first associates</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:adeccc8e8fa8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai-first"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:associates"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law360.com/pulse/modern-lawyer/articles/2468243">
    <title>Fewer Law School Grads Found Jobs Last Year - Law360 Pulse</title>
    <dc:date>2026-04-27T21:17:34+00:00</dc:date>
    <link>https://www.law360.com/pulse/modern-lawyer/articles/2468243</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[The portion of 2025 graduates from U.S. law schools employed in full-time roles that made use of their degrees 10 months after graduation fell by 6.4% compared to the previous year, according to data released Wednesday by the American Bar Association.

Overall, 87.7% of 2025 graduates from ABA-approved law schools had found a full-time, long-term job that either required a law degree or made use of one in some way as of March 16, roughly 10 months after graduation, according to data from the ABA's Section of Legal Education and Admissions to the Bar.

Although that number was up slightly from the 87.1% seen with the class of 2024, the data showed that the percentage represents a smaller overall number of full-time, long-term jobs requiring a law degree, as the class of 2025 was 7% smaller than the supersize class of 2024.

According to the data, 31,743 of the 2025 graduates of the 195 law schools included in the count were approved or provisionally approved in JD advantage jobs nearly one year after graduation. 33,931 of the 2024 graduates reported finding similar full-time, long-term jobs last year.

However, the report noted that this year's 87.7% total included bar admission required/anticipated and JD advantage jobs that were law school-funded. If law school-funded positions had been included in last year's percentage, the 2024 number would have been 88.1% rather than 87.1%.

The portion of unemployed graduates for the class of 2025 increased to 4.9% from 4.7% for the previous class year.

Slightly more than 60% of all 2025 graduates accepted a position at law firms of all sizes, down 4.6% year over year. The number of solo practitioners increased by 17.2%.

Areas of employment that saw decreases included public interest, which was down 14.8%; government, which declined 13.5%; and business/industry jobs, falling 11.0%.

The vast majority of jobs secured by law school graduates in 2025 — 90.7% — were full-time, long-term jobs.]]></description>
<dc:subject>ai schools associates admission</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:5915b4cb4d68/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:schools"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:associates"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:admission"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6461619">
    <title>Private Equity’s Law Firm Workaround: MSOs, Rule 5.4, and the Governance Gap by Lev E. Breydo :: SSRN</title>
    <dc:date>2026-04-27T21:17:05+00:00</dc:date>
    <link>https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6461619</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Private equity is moving aggressively into the legal profession—and its oversight infrastructure is wholly unprepared for this generational shift. To work around prohibitions against nonlawyer ownership, investors are repurposing the management services organization (MSO): a split-entity model in which attorneys retain the regulated practice, but investors acquire the firm’s operating platform. 

This Essay provides the first systematic account of PE investment in law firms and the governance gap in which it is occurring—a vacuum unrecognized by the ABA, state bars, or the courts. The playbook is well-trodden, and the risks are not hypothetical. In just a few years, private equity fundamentally reshaped accounting through hundreds of transactions, with regulators scrambling only after the fact. Law is next.

The MSO model rests on the fragile assumption that "business operations" and "legal practice" can be clearly and durably separated. Healthcare and accounting experience proves otherwise, with similar split-structures consistently exhibiting formality erosion and investor “control creep” through financial and operational pressure. Governance tensions also run deep: the structurally conflicted MSO board must build value while policing its own influence over the interlinked law firm.

The problem is not the MSO per se, but the transactions proliferating in darkness without guardrails. This Essay proposes a three-part governance framework: (i) structural safeguards limiting MSOs to genuine support functions; (ii) independent directors and a board ethics committee; and (iii) ongoing compliance monitoring. The costs of the governance gap—compromised representation and reduced independence—will fall on the public, not investors. The window to act is closing fast. 

]]></description>
<dc:subject>privateequity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:097f4ee24f8a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law360.com/pulse/modern-lawyer/articles/2469238">
    <title>Private Equity MSO Deals Heating Up In Legal Industry - Law360 Pulse</title>
    <dc:date>2026-04-27T14:47:07+00:00</dc:date>
    <link>https://www.law360.com/pulse/modern-lawyer/articles/2469238</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Private equity is driving a surge in managed services organization deals with U.S. law firms, with the focus on consumer-facing practices like personal injury for now and the potential to one day reshape how even BigLaw firms do business.

Attorneys, consultants and investment bankers who spoke with Law360 Pulse estimate that 30 to 40 deals have closed in the first quarter of 2026, but said it's difficult to give a precise number because the vast majority of these deals are not publicly disclosed.

The trend could have a seismic impact on the legal industry, as it intersects with law firms' race to deploy artificial intelligence and the talent wars still raging in BigLaw.

"By raising capital through the MSO structure, you can completely change how you compete for laterals, invest in AI and manage your business," aid Al Laufenberg, a managing director at investment bank Keefe Bruyette & Woods, a unit of the Stifel investment management company, which has worked on several of the largest private equity law firm deals to date.

"These aren't widget manufacturers that have just decided to sell themselves to private equity," he continued. "This is a transformational moment for the industry and these transactions are part of that."

Despite regulatory backlash in a handful of states fueled by lawmakers' distaste for mixing private equity and the legal profession, and lingering uncertainty about how the widespread adoption of legal managed services organizations will work in practice, industry players said that, for now, lawyers and investors are barreling ahead.

"In 2026, there is simply more volume and a greater seriousness" to managed services organization deals and discussions than there was last year, said Mike McNamara, chief executive officer of legal growth consultancy Baretz + Brunelle.

'The Market's on Fire'

Most managed services organization deals entail splitting off a law firm's back-office operations into a separate entity, the so-called managed services organization, which does not practice law and is therefore not subject to Rule 5.4 of the American Bar Association Model Rules, which prohibits fee-sharing between lawyers and non-lawyers.

The organization then charges the law firm a fee for handling things like internet marketing and human resources. Outside investors can purchase equity in the managed services organization, keeping them on the right side of Rule 5.4 while giving them "exposure to the law firm's economics," to use the careful phrasing of industry practitioners. 

That workaround has allowed private equity firms to invest in other regulated industries such as healthcare and accounting, driving consolidation and injecting profit-maximizing practices into those professions.

Now it's beginning to happen in the U.S. legal industry.

"The big bang event was the explosion in private equity accounting deals that we saw in 2024 and 2025," said Larry Gresser, co-founder and managing partner of Cohen & Gresser LLP, an international law firm with roughly 70 attorneys that turned heads in November when it announced that it's considering a managed services organization deal.

"That made lawyers realize the MSO model could be applied to them, and it got private equity investors thinking," he continued. "They realized law firms are one of the last plump birds still waddling around in the valleys of late capitalism that haven't yet been rationalized by outside investment."

Given that law firms are not required to publicly disclose such deals and are often loath to discuss them even in private, it's nearly impossible to give a comprehensive tally. But all the sources who spoke with Law360 Pulse agree that they've spiked in recent months. 

Seth Deutsch, a longtime private equity executive who now consults on law firm managed services organization deals and is a founder of the Private Equity Legal Alliance — a trade group that advocates for the emerging sector — said he's personally closed 10 such deals this year compared with 20 in all of 2025.

"If I worked on 10 myself in the first quarter, then how many happened in total?" he said. "I would estimate 30 or 40."

Most of the sources who spoke with Law360 Pulse declined to specify how many deals they've closed in 2026, but agreed with Deutsch's rough estimate for total deal volume thus far.

Adil Taha, like Deutsch a former private equity executive who's now a consultant on such deals, said he's currently involved in roughly 50 pending transactions, including deals in the U.K.

Trisha Rich and Joshua Porte of Holland & Knight LLP, two of the leading managed services organization deal attorneys in the U.S., said they've closed several deals this year and have roughly 70 more in the pipeline.

"The market's on fire," said Porte. "We're burning the candle at both ends" to keep up.

Right now, the majority of those deals are in consumer-facing practices like personal injury. Another big chunk is so-called AI native law firms like Norm AI, which seek to revolutionize the practice of law via generative artificial intelligence. Private equity giant Blackstone invested $50 million in Norm AI late last year, and the managed services organization is affiliated with New York law firm Norm Law LLP.

Some firms are also restructuring themselves as an MSO without a private equity sponsor, for various reasons. 

No managed services organization deals are believed to have closed in BigLaw yet, but several observers said nearly every managing partner and executive committee at big corporate firms is taking a close look at the phenomenon.

They believe that a handful of BigLaw firms are deep into discussions and could potentially close deals as soon as late 2026.

David Morley, the former head of law firm Allen & Overy, who now guides outside investment in law firms, said that if and when the first BigLaw firm closes a managed services organization deal. it will act as a catalyst for the rest of the industry.

"It would echo around the world," Morley said. "That's the same way it happened in accounting. You saw smaller rollup deals as capital came into the sector, and then as both sides got more comfortable, the deals got bigger and bigger."

Turning Point

So far, most of the managed services organization deals in the U.S. legal sector involve personal injury firms and similar practices like insurance defense, creditors' rights and construction defect litigation.

These are attractive to private equity because they're high-volume, process-driven practices that rely more on the overall business model for success than the contributions of any one attorney. That makes investing in advertising — the lifeblood of personal injury firms — worthwhile and reduces the risk that rainmakers will leave and take valuable business with them.

These firms are often owned by just one or two equity partners, which also means that negotiating a deal is relatively straightforward.

Many of these deals involve a law firm partnering with a private equity investor to pursue a so-called rollup strategy, where the firm uses a capital injection to make hires, buy other firms, invest in technology and benefit from economies of scale.

In one of the few publicly announced such deals, Arizona-based Rafi Law Group announced earlier this month that it has spun off its back-office operations into Rafi Legal Services. An unnamed investor paid $125 million to take a minority stake in Rafi and valued the managed services organization at $450 million, the firm said.

Firm founder Brandon B. Rafi said he hopes to stay ahead of the curve and use that money to expand nationwide.

"I think the practice of law is at a turning point," Rafi told Law360 Pulse when the deal was announced. "We want to be a leader in this space, not a follower."

A similar deal was announced in January, when Louisiana personal injury firm Dudley DeBosier Injury Lawyers revealed it's spun off its back-office functions into a managed services organization and will seek to expand with the help of private equity firm Uplift Investors.

In the U.K., where outside investments are allowed in law firms, private equity investment in the legal industry has surged over the past few years. The most conspicuous effect thus far has been a wave of consolidation in consumer-facing practices such as personal injury, family law and regional full-service firms.

"I think investors are making the same play here," said Deutsch, the private equity executive. "Ten years from now you could see five private equity-backed personal injury firms the size of Morgan & Morgan," the largest such firm in the U.S.

Sweet Equity

For BigLaw firms, one appeal of restructuring as a managed services organization is that it allows senior partners to cash out. Even more alluring than the initial infusion of capital, however, is how the use of long-term equity might change their business model.

"The traditional bonds of partnership that held partners together have dissolved under market pressure," said Morley.

"The primary challenge now is how do you keep all the frogs in the wheelbarrow," he added, referring to the challenge of BigLaw firms retaining key rainmakers.

By giving partners equity in a managed services organization that only vests after several years, the thinking goes, BigLaw firms might be able to finally end the talent wars that now see partners flitting from firm to firm and fetching $20 million annual guaranteed salaries in the process.

That would essentially mean introducing to BigLaw the same financial incentives for top executives that exist in nearly every other industry.

If a top firm spins out a managed services organization that's producing a steady revenue stream, managing partners could dole out equity to reward top partners and lure new rainmakers.

Those shares wouldn't vest for several years, so if the partners jump ship in the meantime they'll be walking away from a major payday.

And unlike the law firm itself, the managed services organization can sell shares to outside capital that are valued at a multiple of its current earnings. If an organization is generating $10 million per year, for example, a private equity firm might value it at $100 million and pay $30 million for a 30% stake, allowing the organization to turn predicted future value into an upfront lump sum.

"When the MSO equity vests it's taxed at the lower, capital gains rate and there's a multiple applied to it," Morley said. "In the partnership model one dollar is one dollar. With true equity one dollar can be multiplied 10, 20, 30 times. That's what most partners don't fully appreciate yet."

There are still a host of risks involved. If the deal isn't structured just right, for instance, and key partners are scared off in the process, a firm could collapse before it even has a chance to reap the potential benefits of the structure.

That's on top of general anxieties about who the winners and losers will be when AI has been fully integrated into the legal profession, and the regulatory risk of embracing a structure that three state legislatures have discussed trying to ban.

Nonetheless, Morley said, at least some firms and investors will see the cost of doing nothing as higher than taking the plunge.

"The investors with a track record of success have plenty of cash to deploy," Morley said. "They have to put it somewhere. They are condemned to invest."]]></description>
<dc:subject>privateequity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:73fa9b09260b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/legaltechnews/2026/04/15/inside-an-ai-native-law-firm-started-by-cooley-fenwick-and-thomson-reuters-veterans-/?kw=Inside%25252Ban%25252B%25252527AI-Native%25252BLaw%25252BFirm%25252527%25252BStarted%25252Bby%25252BCooley%25252C%25252BFenwick%25252Band%25252BThomson%25252BReuters%25252BVeterans&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803">
    <title>Inside an 'AI-Native Law Firm' Started by Cooley, Fenwick and Thomson Reuters Veterans | Law.com</title>
    <dc:date>2026-04-18T19:35:23+00:00</dc:date>
    <link>https://www.law.com/legaltechnews/2026/04/15/inside-an-ai-native-law-firm-started-by-cooley-fenwick-and-thomson-reuters-veterans-/?kw=Inside%25252Ban%25252B%25252527AI-Native%25252BLaw%25252BFirm%25252527%25252BStarted%25252Bby%25252BCooley%25252C%25252BFenwick%25252Band%25252BThomson%25252BReuters%25252BVeterans&amp;utm_position=1&amp;oly_enc_id=&amp;user_id=5162ee7434b9b0a8048a8803</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Law firms of all sizes are adopting artificial intelligence at a rapid clip, but a new class of "AI-native" and "AI-enabled" firms hope to claim business from incumbents by using AI-powered tools to dramatically reshape legal workflows.

One such firm is San Francisco-based General Legal, founded by Ryan Walker, Javed Qadrud-Din and J.P. Mohler in 2025. General Legal provides contract review and drafting services for early-stage startups, covering standard commercial agreements including master service agreements, nondisclosure agreements and end-user license agreements.

Prior to launching General Counsel, Walker was formerly the chief technology officer of Casetext and served as a technology vice president overseeing CoCounsel at Thomson Reuters following its purchase of Casetext. Qadrud-Din, who began his career at Fenwick, served as head of AI at Casetext and was director of machine learning and applied research at Thomson Reuters. Moehler was an associate with Wilmer Cutler Pickering Hale and Dorr and Cooley, and most recently was a senior machine learning and applied research scientist at Thomson Reuters.

Legaltech News sat down with Qadrud-Din to discuss what it means to be an AI-native law firm, why traditional firms struggle to change how they work, and what areas may prove resistant to automation.

This conversation has been edited for length and clarity.

We’ve seen an increasing number of people use the term "AI-native law firm" in recent months. What does that phrase mean to you, and why did you and your co-founders want to start one?

What it means is we use AI maximally, mainly behind the scenes. Our AI takes the first cut at anything that comes in to us, and then our lawyers review that output and remove some of the output, add to it, modify it and then give it back. That is much faster than the traditional process of doing everything manually. We use AI in a more complex way than most law firms do. We have lots of tailor-made scripts that use AI behind the scenes.

We've been building tools for lawyers for a long time. The last 10 years, I've been at different companies building AI tools for lawyers, and so have my co-founders—we built CoCounsel at Casetext, and we got acquired by Thomson Reuters. ... There's a lot of really good AI tools out there for lawyers, and lawyers are starting to use them, but we have not seen any of the gains from AI make it back to the clients. If anything, the cost of hiring a lawyer is now more expensive than it used to be. The turnaround times are still super slow, days [or] weeks to get back to you, and legal work is often riddled with errors that could be caught with AI. ... We see that as an opportunity, and we're taking it—we're using AI maximally and then delivering to the end user, the clients, the gains from using AI.

Firms are experimenting with some of these tools that are on the market, and they're doing their own internal development. Are they just not well equipped to change how they work?

Someday, a long time in the future, they probably will change. But by that time, it'll be too late, and there are going to be AI-native law firms that have gotten very big in the meantime. And the reason we think it's tough for them to change—there's normal human inertia, but there's also the way these firms are structured. It's very difficult for them to lower their prices in the short term so that hopefully they get more clients in the long term. It's very difficult for them to get off the billable hour. And the reason it's difficult is that the partners are taking the profits off the table every year and using that to pay their mortgages and stuff, so if you ask them to take a huge pay cut in one year or a few years, that's a very difficult proposition in a traditional law firm model. That's why we think there's a structural reason it's very difficult for them to change, certainly very difficult to do it quickly.

We've also seen people experiment with combining legal services and tech development under alternative legal service provider (ALSP) models. Why did you want to structure General Legal as a law firm instead of going the ALSP route?

ALSPs are limited in the level of services they can provide, because they're not lawyers. They can't practice law. It's not a law firm. They can't truly practice law. The AI tools are allowing such complex work to be done that the opportunity now is in this—not super complex, big [mergers and acquisitions] transactions—but more complex than what an ALSP is able to do.

Risk aversion is relatively common in the legal industry, and people will often revert to "the way we've done things in the past." Do you have any concerns about the firm’s ability to attract clients, given the novelty of the business model?

There are a few different sorts of client profiles. There are clients where there's already a big legal team at the company, and those take some convincing. Then there are clients where there aren't any lawyers working at the company yet, or there's one lawyer working at the company, and that person is overwhelmed, so there it's an easier sell. Essentially, we do think the value proposition is so strong it's not that hard to sell to anyone, but there are these different profiles and different levels of persuasion that you need.

Do you worry that that same kind of openness to experimentation and to new models may lead to them at some point saying, "Why don't we try to bring this work in house?"

We can take pretty routine work off the table for the general counsel (GC) that the firm ultimately hires or for a GC that's already there, stuff that they don't really want to be doing, so that they can focus on the strategic advice that they should be giving to the company that they work for. ... We're kind of your army of associates, and you could focus on the strategic side.

You guys have a clear focus at the moment, working on contracts for growth-stage companies. Do you think the AI-native law firm model is one that can work well across practice areas and client types? Are there areas where it may struggle to handle going forward?

I think it can work well across industries. We're starting with growth stage tech companies because they are often early adopters of technology solutions, so it's a good place to start. It's also an area we know really well, because we are Silicon Valley people. It's just a sensible place to start for us, but I think it works very well across industries.

Across practice areas, that's a little bit different. There are certain types of litigation [where] there's just a ton of human work, ... it's two humans talking to each other, or multiple humans talking to each other. It's going to be hard to automate depositions. A lot of the time, in certain types of litigation, it's just difficult to automate. Not to say it'll never happen, but it's tough. We also see the high-level strategic advice that top firms are giving for big mergers or venture financings or big bet-the-company transactions—we also see that as a place where people are going to want this very elite, high level human lawyer to walk them through the situation.]]></description>
<dc:subject>ai-first ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:eed617427c7f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai-first"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legalfutures.co.uk/latest-news/vos-legal-education-needs-complete-rethink-in-age-of-machine-justice">
    <title>Vos: Legal education needs &quot;complete rethink&quot; in age of machine justice - Legal Futures</title>
    <dc:date>2026-04-18T19:34:15+00:00</dc:date>
    <link>https://www.legalfutures.co.uk/latest-news/vos-legal-education-needs-complete-rethink-in-age-of-machine-justice</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[There needs to be “a complete re-think of how we prepare our young lawyers for practice in the machine age”, the Master of the Rolls said yesterday.

]]></description>
<dc:subject>book admission schools competence</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:e677d699ef63/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:book"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:admission"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:schools"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:competence"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.law.com/international-edition/2026/04/16/inside-private-equitys-law-firm-fishing-expedition/">
    <title>Inside Private Equity's Law Firm Fishing Expedition | Law.com</title>
    <dc:date>2026-04-18T19:29:37+00:00</dc:date>
    <link>https://www.law.com/international-edition/2026/04/16/inside-private-equitys-law-firm-fishing-expedition/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Inside Private Equity's Law Firm Fishing Expedition
Law.com goes behind the scenes of private equity’s courtship of law firms, speaking to the leading financial advisers about why the money is moving now and what types of deals will happen.

If you want to gauge the growing appetite for private equity investment into law firms, look at the call logs of the advisers serving as the industry’s new matchmakers.
Gareth Hunt, a managing director at investment bank KBW, now fields three to four calls a day from law firm leaders interested in understanding the pros and cons of selling stakes in their businesses to outside investors.
It’s a similar story for David Morley, who co-founded advisory firm Dejonghe & Morley with former A&O Shearman senior partner Wim Dejonghe last year. He says the firm has had over 500 meetings with interested parties since launching and gets around three to four investment houses approaching it a week for advice on investments in the legal sector.
Such is the interest from private equity that when the firm held a breakfast briefing with mid-market U.K. law firms last month, all 20 of the attendees said they had been approached by buyout firms.
For those that are interested, there are now a range of discreet events to connect deal-makers with managing partners.
In April, Harvard Law School held an invite-only summit on “law as a new asset class” and the "likely future of private equity investment in the market for legal services” with senior figures flying in from across the U.S. and Europe to attend.
Rothschild’s Arrowpoint also held a legal services dinner to connect managing partners in London in April.
At this stage, nigh on every major firm has run the numbers to see what its practice would fetch on the open market.
But despite the chatter rippling across the sector, the talk has yet to translate into many deals getting done.
After extensive interviews with the key financial advisers and investment bankers in this emerging area, Law.com found a sector receptive to change but cautious about how deals would work in practice. The result is a bifurcated landscape where the biggest players and smaller law firms are expected to strike first, leaving the mid-market on the sidelines.
Why so long?

First, the timing of it all. Why on earth has it taken so long for private equity to become interested in law firms?

External investors have been able to invest in law firms in the U.K. since 2012 and the option of investing in U.S. law firms through management services organisations has been available for a number of years.

But anyone speaking to private equity firms about investing in law firms in 2013 would have found the responses scathing.
One buyout executive said at the time that these deals were “not attractive”, complaining about “wretched partnerships” that moved at a “palaeolithic pace” that made it impossible to make big changes to management and overall strategy. He also wasn’t sure what he’d buying, as most firms did not have predictable recurring revenues and partners could leave (with their clients) at any time.
While the fundamental business model of most law firms has changed little, there have been subtle changes behind the scenes that have made these businesses more appealing. Most firms have moved away from lockstep pay to floating performance-based pay. Many have more corporate-style boards and structures and generally are run less like partnerships and more like ‘normal’ companies.
Bankers have also rechristened law firm revenue as ‘re-ocurring’ rather than ‘recurring’ to stress that law firm fees while not contractually locked in are pretty predictable.
But it’s been the success of deals in the accountancy sector that has really boosted interest in legal and led to a huge uptick of interest in the past 18 months.
David Morrison, director at investment bank Rothschild & Co, says: “Even 15 years ago, investing in professional services was not really the done thing.”
Morrison says that the fragmentation, sheer size and nature of their embedded clients made accounting particularly attractive and led to a flurry of successful deals.
Research from The International Federation of Accountants found that over 1,000 accountancy firms worldwide had received private equity investment over the past decade—with a significant uptick in activity from 2022. In 2024, U.S. accounting firm Baker Tilly, as well as Grant Thornton’s U.K. and U.S. businesses, sold stakes in themselves to private equity firms.
“If you look at all of those components and overlay it onto the legal services space, you will see there is a lot of read across and a lot of the same features in legal services,” he says.

Getting deals done

So what deals will we see happen in law?

This is where things get a bit more unclear. While there is certainly interest, few are willing yet to put their money where their mouth is.
The biggest deal to happen so far in the U.K. was Inflexion’s £342 million take-private of mid-market firm DWF in 2023.
On the face of it, the biggest opportunity would seem to be in this part of the market where there is a huge swathe of firms with chunky revenues, good profitability but little to distinguish one from another. All must invest in technology and are subject to consolidation.
Law firms of this size in the insurance or public services sector would be particularly attractive as they have predictable recurring revenues.
But similar deals will be hard to pull off. DWF’s unusual history was a major catalyst for the deal; it was converted to an ABS and listed in 2019, but market volatility and a lacklustre share price meant that many partners at the firm were unhappy with the structure.
Matthew Doughty, CEO of DWF, believes there are cultural and structural challenges to getting private equity investment in traditional partnerships—and that the model will not work for many firms.
Speaking to Law.com, he said: “There will be more investment from PE, but I don’t think this will be mainstream. We will see very specific situations where it makes sense, but law firms are highly individual, people-driven businesses and many will continue to prefer partnership or alternative structures that better reflect their business model and objectives.”
So it seems probable that although more mid-market law firm deals will eventually happen, it is more likely to take place in the second wave of transactions that get done.
Smaller firms

Instead, many private equity firms are looking at the smaller boutique or consumer-focused law firms.

These are similar to August Equity’s buyout of Midlands-based Higgs LLP last year. The firm spent four years talking to law firms before acquiring Higgs, aiming to take it from £25 million of revenues to £150 million in four years through bolt-on acquisitions and organic growth.
In April, U.S. personal injury law firm Rafi Law Services received $125 million of backing from a U.S-based outside investor to expand nationally and invest in technology, in a deal that valued the firm at $450 million.
Similar deals could also happen with profitable teams at big law firms spinning out to form boutique firms with private equity backing.
The other area attracting the most interest is the idea of minority deals in the large-cap space.

Bankers say they are seeing the most interest in this type of deal from elite U.S. law firms, with strong private capital practices, with McDermott Will & Schulte and Cohen & Gresser reportedly looking into the concept of selling stakes in themselves.

Rob Mann, co-head of equities & advisory Europe at investment bank Stifel, says that while it is harder to structure deals in the U.S., law firms in the country are fundamentally keener to understand how they can access private equity cash.
“As with many industries, we suspect that what will ultimately happen will be that the U.S., despite coming from a more complex regulatory backdrop will end up leading the charge, and then everybody else will have to catch up,” he says.
Minority deals, where a private equity firm takes a sliver of a firm, say 10%, rather than taking full control, would certainly be easier to do as they involve giving up less decision-making power to external parties.
Burford Capital is pitching this sort of ‘private equity lite’ approach to law firms. Take our money but you don’t need to undergo drastic cultural changes. Instead the firm would establish a Managed Service Organization, providing external cash but not meddling in day-to-day operations.
Talent retention

There is particular interest in how buyouts could be used to solve one of the biggest issues for managing partners: how to keep top talent from walking to a rival.

David Morley, former A&O Shearman managing partner, says talent retention is a “really huge headache” that “preoccupies every firm at the top of the market”.

“The biggest limitation of the partnership model is there is in effect no real financial incentive to stay or invest for the long term, and there's little or no financial penalty for leaving,” says Morley.
He explains that by selling a stake to an outside party, a law firm could reinvest some of the money in a share and management incentive plan that would lock partners in for a number of years and potentially provide a big payout when the private equity firm sold their stake on to another buyer.
Profits from the sale of shares deal would be taxed as capital gains and not income, providing a big tax advantage over ordinary partner drawings. It would also give partners a strong financial incentive to stay and to increase the value of the law firm overall.
Morley says: “I can see that there will be some firms at the very top, who will say, ‘let's go down this road. Let's steal a march on the competition by converting to a corporate-type structure so that we can introduce these options. Now we can offer the lateral market, not only high income, but also the possibility of a large tax advantaged capital gains’.”
While there has been little in the way of signed deals so far, there is a sense that that could all change relatively quickly.
Gareth Hunt of KBW puts the delay down to the complexity of large law firm partnerships. Experienced leaders at the top want to understand the details of how deals might work, but then must “seek the approval of hundreds of people who are trained to be skeptical”.
“Word is getting around,” says Hunt. “There are lots and lots of people on reconnaissance at the moment. It takes time to get there, but get there they will.” 
Bankers are hoping that when big U.S. firms start doing these deals, it could kick-start the market and cause a cascade of activity, particularly in the U.K., as firms rush to keep up.
Martin Tomaszewski, a partner at Rothschild & Co, has advised on several accountancy firm buyouts and says he saw a similar dynamic in that sector.
"If more deals happen, does that create a little bit of an avalanche?" he says. "What's happened in accounting is people hadn't done any deals and then suddenly they started and it's just been one after the other—people look around saying, hang on, I don't want to miss out."
It is, he says, exactly what everyone is waiting for.
April 16, 2026

Inside Private Equity's Law Firm Fishing Expedition
]]></description>
<dc:subject>privateequity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:6b3c4c7840e1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:privateequity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://davidoks.blog/p/why-the-atm-didnt-kill-bank-teller">
    <title>(3) Why ATMs didn’t kill bank teller jobs, but the iPhone did</title>
    <dc:date>2026-04-16T20:35:37+00:00</dc:date>
    <link>https://davidoks.blog/p/why-the-atm-didnt-kill-bank-teller</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[But why? Why did the ATM, literally called the automated teller machine, not automate the teller, while an entirely orthogonal technology—the iPhone—actually did?

The answer, I think, is complementarity.

In my last piece, on why I don’t think imminent mass job loss from AI is likely, I talked a lot about complementarity. The core point I made was that labor substitution is about comparative advantage, not absolute advantage: the relevant question for labor impacts is not whether AI can do the tasks that humans can do, but rather whether the aggregate output of humans working with AI is inferior to what AI can produce alone. And I suggested that given the vast number of frictions and bottlenecks that exist in any human domain—domains that are, after all, defined around human labor in all its warts and eccentricities, with workflows designed around humans in mind—we should expect to see a serious gap between the incredible power of the technology and its impacts on economic life.

That gap will probably close faster than previous gaps did: AI is not “like” electricity or the steam engine; an AI system is literally a machine that can think and do things itself. But the gap exists, and will exist even as the technology continues to amaze us with what it can now accomplish.]]></description>
<dc:subject>future innovation ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:7a43fb0e158d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:future"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:innovation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legaltechnologyhub.com/contents/aba-techshow-2026-superpowers-in-theory-and-in-practice/">
    <title>ABA TECHSHOW 2026: Superpowers, in Theory and in Practice | Legaltech Hub</title>
    <dc:date>2026-04-09T19:24:27+00:00</dc:date>
    <link>https://www.legaltechnologyhub.com/contents/aba-techshow-2026-superpowers-in-theory-and-in-practice/</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[This year’s theme was superheroes—but the more interesting question was: what are lawyers actually good at? 

]]></description>
<dc:subject>jf</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:299e3ac28ecd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:jf"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=N5JDzS9MQYI&amp;t=1214s">
    <title>Anthropic's CEO: ‘We Don’t Know if the Models Are Conscious’ | Interesting Times with Ross Douthat - YouTube</title>
    <dc:date>2026-04-07T19:01:22+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=N5JDzS9MQYI&amp;t=1214s</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Anthropic's CEO: ‘We Don’t Know if the Models Are Conscious’ | Interesting Times with Ross Douthat
]]></description>
<dc:subject>ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:7c5324c52764/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.legaltechnologyhub.com/contents/ai-vocabulary-agentic-systems-architecture-and-governance/?_hsenc=p2ANqtz--G56uLmXbQDvLb31Sy7J7FlvlHocQM7jDHmo78PCh7CzHZ2p8jBcWRj0QjRqSvD5GcI0UopG4VqPbRif5MoabdLFMVBQ&amp;_hsmi=412008385">
    <title>AI Vocabulary: Agentic Systems, Architecture &amp; Governance | Legaltech Hub</title>
    <dc:date>2026-04-06T20:39:38+00:00</dc:date>
    <link>https://www.legaltechnologyhub.com/contents/ai-vocabulary-agentic-systems-architecture-and-governance/?_hsenc=p2ANqtz--G56uLmXbQDvLb31Sy7J7FlvlHocQM7jDHmo78PCh7CzHZ2p8jBcWRj0QjRqSvD5GcI0UopG4VqPbRif5MoabdLFMVBQ&amp;_hsmi=412008385</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[Since generative AI (GenAI) launched into the legal industry in 2023, LTH has regularly updated its readers on the key vocabulary terms professionals should know in order to develop fluency. Like many things AI-related, this is not a one-time leaning exercise. As AI systems evolve, so does the language we need to describe, and govern, them.  

Over the past year, the conversation has shifted from standalone models and point solutions to agents; as 2026 evolves, that shift will continue with hot topics likely to include orchestration, interoperability, and system-level governance. These concepts are already shaping how AI is being deployed inside law firms, corporate legal departments, and legal technology platforms. 

The vocabulary list below focuses on terms with immediate, practical relevance. Many of them sit at the intersection of capability and risk, where autonomy, delegation, and coordination begin to challenge traditional control frameworks. Understanding this language is a prerequisite not just for innovation teams, but for IT, risk, KM, and leadership roles grappling with increasingly complex AI portfolios. 

Agent 
A software entity that can perceive its environment and operational context, reason about goals and constraints, and autonomously select, execute, and evaluate actions to achieve defined objectives. Agents have access to tools such as systems, data sources, and workflows and can decide when and how to use those tools in pursuit of a goal, including assessing whether success conditions have been met or whether further action is required.

Unlike traditional automation or rule-based chatbots, agents can adapt their behavior based on new information and observed outcomes. This adaptive, goal-directed autonomy makes agents powerful, but also harder to predict and control, requiring different governance and oversight approaches than deterministic systems.

Agentic System 
A system designed around one or more agents that operate with delegated authority to plan, decide, and act. These systems often combine models, tools, memory, and decision logic into a continuous loop. Because behavior can emerge dynamically, agentic systems introduce new oversight and accountability challenges. Governance must focus on boundaries, monitoring, and escalation, not just initial configuration.

Auditability 
The ability to trace, inspect, and explain what an AI system did, when it did it, and why. Auditability is essential for trust, compliance, and defensibility, especially in regulated environments. In agentic systems, auditability must extend across decisions, tool calls, and inter-agent communication. Without this, organizations may be unable to explain or justify outcomes after the fact.

Autonomy Gradient 
A way of describing levels of AI autonomy, from fully human-controlled workflows to independently acting agents. Rather than treating AI as “on” or “off,” the autonomy gradient highlights incremental delegation. This concept is useful for aligning risk, controls, and accountability with system behavior. Governance should scale along the gradient, not remain static.

Composable Architecture 
A modular system design where capabilities are assembled from interchangeable components such as models, agents, tools, and data sources. This approach enables flexibility, faster iteration, and vendor interoperability. However, composability also increases integration complexity and expands the governance surface. Organizations must manage not just components, but their interactions.

Context Engineering 
The practice of deliberately structuring what information an AI system can access, retain, and use. Context includes documents, instructions, memory, metadata, and prior interactions. Poor context engineering is a major cause of hallucination, inconsistency, and unintended behavior. In agentic systems, context becomes an operational and governance concern, not just a prompt design issue.

Decision Boundary 
The defined point at which an AI system may act independently versus requiring human approval. Decision boundaries determine where responsibility shifts between humans and machines. Clear boundaries help prevent over-delegation and reduce ambiguity when things go wrong. They are especially important in multi-step or multi-agent workflows. 

Delegation 
The act of assigning tasks, authority, or decision-making power to an AI system. Delegation can be narrow and procedural or broad and judgment-based. As delegation increases, so does the need for oversight, constraints, and rollback mechanisms. Poorly scoped delegation is a common source of AI-related risk.

Emergent Behavior 
Unexpected behavior that arises from interactions between agents, tools, and data rather than explicit programming. Emergence can produce powerful outcomes, such as creative problem-solving. However, it can also generate unpredictable or undesirable results. This makes testing and governance more complex than with linear systems. 

Execution Environment 
The technical and policy constraints under which an AI system operates, including permissions, data access, and runtime limits. Execution environments shape what an AI system can and cannot do in practice. Secure environments reduce risk by enforcing least-privilege access. They are a foundational control for safe agent deployment. 

Human-in-the-Loop (HITL)
A governance pattern where humans remain involved in review, approval, or intervention at specific stages. HITL is commonly used to manage risk in AI-assisted workflows. However, it does not scale well for highly autonomous or high-volume systems. In agentic contexts, HITL must be complemented by stronger system-level controls. 

Interoperability
The ability of different AI systems, tools, and platforms to work together effectively. Interoperability enables composable architectures and multi-vendor ecosystems. Standards play a key role in making interoperability feasible. At the same time, increased interoperability expands the attack surface and governance complexity. 

Model Context Protocol (MCP)
A standard for how AI systems access, manage, and persist context across tools and interactions. MCP shifts intelligence from isolated prompts to shared, structured context layers. This enables continuity, collaboration, and more sophisticated agent behavior. It also raises new questions about access control, persistence, and governance.

Multi-Agent System
A system composed of multiple agents that collaborate, coordinate, or specialize to achieve goals. Each agent may have distinct roles, tools, or decision authority. As agents interact, risk compounds and becomes harder to trace. Effective governance requires coordination logic and shared oversight mechanisms.

Observability 
The ability to monitor AI system behavior in real time through logs, metrics, and traces. Observability makes system behavior visible rather than assumed. It is critical for detecting drift, failures, or unintended actions early. Without observability, governance remains largely theoretical.

Orchestration 
The coordination of tasks, agents, tools, and workflows to achieve a desired outcome. Orchestration defines sequencing, dependencies, and escalation paths. In agentic systems, orchestration shapes how autonomy is exercised in practice. It is a central lever for control and efficiency. 

Orchestration Layer
The control plane that manages coordination, permissions, routing, and oversight across agents and tools. This layer determines which agents can act, when, and with what authority. Increasingly, the orchestration layer is where governance is implemented in practice. It is becoming a strategic and risk-critical component.

Policy-as-Code
The practice of encoding governance rules directly into system logic rather than relying on documentation or training. Policies can govern access, behavior, escalation, and limits. This approach enables consistent enforcement at scale. It also allows governance to evolve alongside system architecture.

Prompt Chaining
A technique where outputs from one prompt feed into subsequent prompts or agents. Prompt chains enable complex, multi-step reasoning and workflows. However, they can obscure accountability if steps are not logged or monitored. In agentic systems, prompt chaining often becomes an implicit orchestration mechanism. 

Provenance 
Information about the origin, transformation, and handling of data or outputs. Provenance supports trust, traceability, and defensibility. In legal and regulated contexts, it is often essential for audit and review. Agentic systems make provenance harder—but more important—to maintain.

RACI for AI
An adaptation of the RACI (Responsibility, Accountability, Consulted, Informed) framework to clarify responsibility, accountability, consultation, and information flows when AI systems act. It helps organizations avoid ambiguity about ownership. As AI autonomy increases, traditional accountability models often break down. RACI for AI is one way to restore clarity.

Runtime Governance
Controls that operate while an AI system is running, rather than only at design or deployment. Runtime governance includes monitoring, intervention, throttling, and shutdown mechanisms. This is essential for managing emergent behavior and drift. It reflects a shift from static to continuous oversight.

System Drift
Gradual changes in AI system behavior over time due to data shifts, model updates, or evolving context. Drift can degrade performance or increase risk without obvious warning signs. It is particularly problematic in long-running or autonomous systems. Ongoing monitoring and recalibration are required to manage it.

TEVV (Testing, Evaluation, Validation & Verification)
A framework for assessing AI system performance, safety, and reliability across its lifecycle. TEVV originated in model evaluation but now applies to full systems. In agentic contexts, TEVV must cover orchestration, context, and tool use. It is a cornerstone of responsible deployment

Tool Use
An AI system’s ability to invoke external systems such as databases, APIs, documents, or actions. Tool use significantly expands what AI systems can do in the real world. It also increases risk by bridging digital and operational environments. Strong controls are required to govern access and execution.]]></description>
<dc:subject>ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:555f73d7d2d5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://lawyerforward.substack.com/p/yes-they-are-trying-to-replace-you">
    <title>Yes, They ARE Trying to Replace You - by Mike Whelan, Jr.</title>
    <dc:date>2026-04-02T14:36:40+00:00</dc:date>
    <link>https://lawyerforward.substack.com/p/yes-they-are-trying-to-replace-you</link>
    <dc:creator>JordanFurlong</dc:creator><description><![CDATA[I take the companies on the Techshow floor at their word when they say they’re here to augment lawyers. Frankly, they’re more like vertical SaaS plays than they are these foundational model-makers out here raising infinite billions of dollars, so augmentation makes sense.

But let’s stop pretending augmentation is everyone’s goal. Our AI economy is built on labor replacement. If the big companies don’t replace us, they’ll collapse. That seems pretty obvious at this point—they’ve said it out loud.

As Northwestern Engineering’s Kristian Hammond said at an event this morning, “We are in a place where it’s time for every field to take control. You can’t wait for this technology. If you wait for this technology it’ll make something you don’t like.”

So, dear lawyer, do your job. Stop predicting the future and start crafting it.

If you don’t, a small handful of CEOs with perspective-skewing incentives will do it without you.]]></description>
<dc:subject>AI</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:JordanFurlong/b:0ff10d4f9af1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:JordanFurlong/t:AI"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>