What are we discussing with clients?

• Note what is NOT publicly available data. That might impact interpretation of other laws with this term.
• Note what IS “reasonably likely to be accessed by minors” for the same reason. It is a very broad term here.
• The duty of care is vague (result based) and thus a tall order to follow.
• Note the legal obligation to have terms of use and community standards (a first?).
• Note the very extensive transparency obligations. This is a privacy notice PLUS PLUS, with detail and retention terms for every feature and information on the algorithms.

In more detail

It applies if you:

• Conduct business in Vermont.
• Generate a majority of your annual revenue from online services.
• Are reasonably likely to be accessed by a minor.
• Determine the purpose and means of processing of personal data.

The law includes a lot of unique carve outs from “publicly available information,” so the following is still personal data:

• Biometric data collected without knowledge.
• Information that is collated and combined to create a consumer profile.
• Information that is made available for sale.
• Genetic data.

Is the data “reasonably likely to be accessed by minors?” Consider:

• Directed at children under COPPA.
• The service or product is determined, based on either (1) competent and reliable evidence regarding audience composition, or on (2) internal company research or (3) knew or should have known audience to be routinely accessed by an audience that is composed of at least TWO PERCENT minors.
• Data minimization: Only collect/retain/share data that is necessary to provide the service/feature with which the covered minor is actively and knowingly engaged with additional limitation on algorithmic recommendations.

Minimum duty of care

The use of the personal data and the design of an online service, product, or feature or the content of the media viewed will not result in:

• Reasonably foreseeable emotional distress to a covered minor.
• Reasonably foreseeable compulsive use of the online service, product, or feature by a covered minor.
• Discrimination against a covered minor.
• Default settings set to highest levels of privacy which includes blocking known adult users from seeing the minor’s account or specific content or commenting or direct messaging and not displaying the covered minor’s location to other users.

Provide transparency which includes:

• Terms of use, privacy notice and community standards.
• Detailed disclosure per feature, including data retention.
• Purpose of each algorithmic recommendation system.
• Inputs used by the algorithmic recommendation system and how they are used, influence recommendations.

By Gaurav Bhalla of Ahlawat & Associates

The Bombay High Court recently affirmed the order of the Registrar of Trade Marks whereby TikTok’s application for declaration of its mark as well-known in India was disallowed. Interestingly, this decision (by the Bombay High Court) was not on merits but rather had a heavy influence of sovereignty and integrity of India, its defence and public order. This judgment might serve a message to trademark owners of global digital products to be cautious of the manner of operating their products in India.

TikTok was launched in India in 2017 and became an instant hit with its unique algorithm which offered tailored and engaging short-form content to users. TikTok also obtained a trademark registration further strengthening its trademark rights in India. Subsequently, it filed an application for declaration of its mark as well-known as per the procedure laid down under the Trade Marks Rules, 2017. Interestingly, while the application (for declaration of the mark as well-known) was being examined, TikTok was banned in India (in 2020) citing national security concerns (owing to allegations of data privacy owing to its servers located outside India, circulation of inappropriate content, etc.).

The Registrar of Trade Marks, while adjudicating the application (for declaration of the mark as well-known) declined to grant ‘well-known’ status to the mark TikTok with the rationale that a brand (the product under which is currently prohibited in India) did not align with the criteria for such recognition.

TikTok subsequently knocked the doors of the Bombay High Court by filing an appeal against the order of the Trade Marks registry. TikTok argued that the Registrar’s decision overlooked extensive evidence of its global recognition and popularity. They submitted that the matter be reconsidered with a fresh perspective, and that the ban in India should not negatively affect the brand’s strengthening of its trademark rights.

The primarily question before the Court was whether a trademark of a banned product (mobile application) could qualify as ‘well-known’? The Court referred to Section 11(6) of the Indian Trade Marks Act and mentioned that while the provision lists out some aspects which could be considered while analyzing whether or not a mark is well-known or not, the list under the provision is illustrative and non-exhaustive. The Court also expressly observed that Section 11(6) gives power to the Registrar to take into consideration any fact that he considers relevant for determining a trade mark as a well-known trade mark.

The Court finally observed that “The reasons why the application of the petitioner bearing the trade mark TikTok has been banned pertain to the sovereignty and integrity of India, its Defence and Public Order. These are serious matters, which cannot be ignored and therefore, it is found that the respondent did take into consideration relevant factors while passing the impugned order.” Accordingly, the Court upheld the order of the Trade Marks registry and concluded that TikTok couldn’t be recognized as a well-known mark in India.

It remains to be seen whether TikTok will file an appeal against this judgment. This is one of the rare scenarios where the Court instead of considering the evidence of use of the mark, it ventured into the expansive scope of Section 11(6) and relied upon a prevailing factual scenario to arrive at its conclusion. This judgment has opened a pandora’s box which might lead to many such approaches in the future (where the Trade Marks registry might not keep itself confined to the indicative factors laid down in the statutory provision).

There is a tool available for the proposed Gold Card program: private immigration bills. With the recent announcement of a website for interested Gold Card applicants to register, the Trump administration may be considering using private immigration bills to implement this new program.

What Is a Private Immigration Bill?

A private immigration bill is a law passed by Congress that applies only to a specific individual or group, providing them with immigration relief—such as permanent residency or even citizenship—outside the normal channels. Unlike public laws that apply broadly (like the EB-5 investor visa program), private bills bypass existing immigration categories and eligibility restrictions. They’re tailored, targeted, and flexible.

How Does the Private Immigration Bill Process Work?

1. Candidate Identified – A high-net-worth individual seeking permanent status in the United States, but who doesn’t qualify or want to process through the standard EB-5 immigrant investor visa program, seeks congressional sponsorship for a private bill.
2. Bill Introduction – A member of Congress introduces the private bill on their behalf. This bill can grant lawful permanent residency or citizenship directly.
3. Committee Referral – The bill is referred to the House or Senate Judiciary Committee, typically to the Subcommittee on Immigration. Supporting documentation (including economic impact, business contributions, investment plans) is submitted.
4. Congressional Deliberation – Congress discusses the bill and brings it to a vote if the bill gains enough support. If the bill passes in both the House and Senate, it goes to the president.
5. Presidential Signature – The president signs the bill, and it becomes law. The individual receives the immigration status authorized in the bill.

How Could the President Fast-Track Investment Immigration Through the Gold Card Program?

The president cannot unilaterally change immigration law or create a new visa category for investors without Congress. But by working within the framework of private bills, the president could do the following:

• Publicly promote a “High-Impact Immigrant Investor Initiative” aimed at attracting global wealth and talent to reduce the federal deficit.
• Partner with congressional allies to introduce private bills for selected high-net-worth individuals who invest $5 million in the United States. The Trump administration would need to define how the investment would be used and what would qualify.
• Coordinate through federal agencies like the Department of Commerce and Department of State to identify eligible candidates and build bipartisan support.
• Signal executive support to Congress and leverage the White House platform to prioritize and fast-track these bills through the legislative process.

This approach would not require amending the INA but would achieve the same outcome: granting permanent status or citizenship to individuals selected on the basis of their economic contributions.

Why Use Private Bills for Investment Immigration?

• Customization – Private bills can be tailored to individuals who fall outside existing visa categories but still offer high value to the United States.
• Speed – While not automatic, private bills can be prioritized politically in ways traditional visa processing cannot. The Trump administration has said the Gold Card would offer a “fast track” for investors.
• No need for legislative overhaul – Private bills sidestep partisan gridlock over immigration reform.

Caveats

• Not scalable – Each private bill must pass Congress individually.
• Requires political capital – Lawmakers would need to be willing to sponsor and support such legislation.
• Unusual, but legal – Private bills are rarely used, so this strategy would be unconventional—but it is fully within the constitutional powers of Congress and the president.

The Trump administration seeks to make immigration more responsive to economic strategy, especially in attracting global investors, entrepreneurs, and wealth creators, and private immigration bills offer a potential, legal, creative workaround. While they don’t rewrite the rules for everyone, they allow the United States to open the door to selective, high-impact immigration without needing to amend legislation.

The EEOC’s Allegations and Settlement

Equinox Holdings runs fitness centers nationwide. The EEOC alleged that Equinox rejected an applicant due to her “monthly cycle.” The EEOC’s complaint alleged that Equinox violated the ADA by failing to hire the applicant on the basis of her perceived disability and by failing to make a reasonable accommodation for her endometriosis during the hiring process. The complaint also alleged that Equinox violated Title VII by failing to hire her due to the innately sex-based characteristic of menstruation.

Notably, the EEOC pointed to a text message sent by the Equinox hiring manager to the applicant as evidence of discrimination. Although Equinox had previously described the employee’s qualifications as “excellent” in a text to the applicant, the hiring manager explained that she was rejected “[o]nly because [of] the concern in the future if your absence may occur due to your month cycle,” according to the EEOC’s complaint.

The EEOC recently announced that it had settled this matter for $48,000. The settlement also requires Equinox to implement anti-discrimination policies, post notices regarding employee’s rights under federal anti-discrimination law, and provide ADA and Title VII training to employees and hiring managers.

The Legal Landscape

The ADA prohibits employers from discriminating against qualified individuals — including both applicants and employees — with a disability. It also requires employers to provide reasonable accommodations to qualified individuals with a disability if the employer can do so without undue hardship.

Importantly, the ADA prohibits discrimination against job applicants in the hiring process. In the hiring stage, this could mean making modifications or adjustments to the job application process that enable a qualified applicant with a disability to be considered for the job.

Takeaways

The EEOC’s allegations and the resulting $48,000 settlement bring to light two points employers should remember.

First, your ADA obligations run even to nonemployee applicants. Employers should navigate the hiring process with this in mind and pay attention to any concern raised by an applicant regarding a medical condition that impedes his or her ability to navigate the hiring process. Requested accommodations in the hiring process can include a wide variety of things (e.g., rescheduling an interview, a translator for an applicant who is deaf). Train your front-line hiring managers to recognize situations where an applicant may need an accommodation, particularly if the applicant identifies a medical issue.

Second, keep in mind that common conditions such as endometriosis and severe menstrual cramps may qualify as disabilities under the ADA. Treating an applicant or employee differently because of menstruation-related issues may also implicate Title VII.

While the decision here is not novel, the fact that an administrative law judge exercised the NLRA’s jurisdiction over a cannabis company may cement plaintiffs’ positions in unrelated litigation concerning labor peace agreements that we have reported on previously.  

Over the past few months, we have been covering lawsuits challenging labor peace agreement requirements throughout the United States.  California, Connecticut, New York, Oregon and Rhode Island all have statutes or regulations that require cannabis entities to enter into labor peace agreements with unions as a precondition for licensure or license renewal.  As part of the legal strategy, plaintiffs have argued that the NLRA preempts state labor peace agreement requirements because such requirements chill employer speech regarding unions and labor relations that is protected by federal labor law.  This argument has seen varying levels of success.   

 On May 21, 2025, the Oregon District Court found that Oregon’s labor peace agreement requirement was preempted by the NLRA and its enforcement was enjoined as to the plaintiffs.  The decision is currently on appeal to the Ninth Circuit.  For the duration of the appeal, Oregon’s cannabis regulator said that it would no longer enforce the requirement. 

Back in March, a California court dismissed an action challenging California’s labor peace agreement requirement under the premise that the court could not adjudicate the case because the cannabis retailer was engaged in a federally illegal business.  

Now that at least one administrative law judge was willing to exercise the NLRA’s jurisdiction over cannabis-related entities, it is possible that litigation challenging state labor peace agreement requirements may leverage the recent NLRB decision, citing it as an example of the NLRA’s scope.  At least one lawsuit remains pending on this topic.  In New York, a cannabis retailer has argued that the LPA requirement in the NY Marihuana Regulation and Taxation Act is preempted by the NLRA.  Connecticut’s statute remains unchallenged.  We will continue to monitor any legal developments in this burgeoning arena.

In the latest AI-washing related securities class action lawsuit to be filed, a plaintiff shareholder has filed a securities suit against AI-based health care company Tempus AI, alleging, among other things, that the company overstated its AI capabilities. The lawsuit comes after the company’s share price declined following the publication of a short seller report critical of the company and its management. A copy of the June 12, 2025, complaint against Tempus AI can be found here.

Background

Tempus bills itself as providing Artificial Intelligence (AI) enabled precision medicine solutions. It claims to develop intelligent diagnostics through the application of AI In healthcare to make laboratory tests and connect laboratory results to a patient’s own clinical data. The securities lawsuit complaint alleges that Tempus “branded itself as an AI company despite little history of generating significant revenues from AI solutions.” Instead, the complaint alleges, Tempus “generated most of its revenue from acquisitions, genomic testing, and data licensing agreements.  

The complaint also alleges that Tempus “repeatedly” claims that the contract value and quality of its data licensing agreements with life sciences companies were “secure and expanding.” The complaint alleges the company used its relationship with AstraZeneca as an example of these relationships. The company also announced a joint venture with SoftBank as a way to generate revenue growth by entering the Japanese market. The company also claimed potential revenue growth from Ambry Genetics, a company Tempus acquired, due to Ambry’s “strong relationships with health care providers.”

On May 28, 2025, short seller Spruce Point Capital Management LLC issued a research report that raised a number of issues regarding Tempus, including, as the complaint subsequently alleged, “(1) Defendant Eric Lefkofsky and his associates have a history of cashing out of companies before public shareholders incur losses or lackluster returns; (2) Tempus’ actual AI capabilities are overstated; (3) board members and other executives have been associated with troubled companies that restated financial results; (4) signs of aggressive accounting and financial reporting; (4) issues the AstraZeneca and Pathos AI deal that merit scrutiny; and (5) the Company’s recent financial guidance revision reveals weakness in core operations.” According to the complaint, the company’s share price declined nearly 20% on this report.

The Lawsuit

On June 12, 2025, a plaintiff shareholder filed a securities class action lawsuit in the Northern District of Illinois against Tempus; its CEO, Erikc Lefkofsky; and its CFO, Jim Rodgers. The complaint purports to be filed on behalf of a class of investors who purchased the company’s securities between August 6, 2024 and May 27, 2025.

The complaint alleges that during the class period, the defendants failed to disclose that: “(1) Tempus inflated the value of contract agreements, many of which were with related parties, including non-binding opt-ins and/or were self-funded; (2) the credibility and substance of the joint venture with SoftBank was at risk because it gave the appearance of ‘round-tripping’ capital to create revenue for Tempus; (3) Tempus-acquired Ambry had a business model based on aggressive and potentially unethical business practices that raised scrutiny and unsustainability; (4) AstraZeneca had reduced its financial commitments to Tempus through questionable ‘pass-through payment’ via a joint agreement between it, the Company and Pathos AI; (5) the foregoing issues revealed weakness in core operations and revenue prospects; and (6) as a result, Defendants’ positive statements [sic] Company’ s business, operations, and prospects were materially false and misleading and/or lacked a reasonable basis at all relevant times.”

The complaint alleges that the defendants violated Sections 10(b) and 20(a) of the Securities Exchange Act of 1934 and Rule 10b-5 thereunder. The complaint seeks to recover damages on behalf of the plaintiff class.

Discussion

This complaint raises a host of allegations, only some of which are about AI. To be sure, the complaint clearly alleges that the company sought to position itself as an AI company, and the complaint further alleges that the company overstated its AI capabilities and prospects. But if this complaint is indeed AI-related, it is only partially so, as there are many other allegations, many of them having to do with the companies finances and the nature of its transactions and relationships with its trading partners.

Most readers undoubtedly noted that the complaint’s allegations largely rely on the report of a short seller. As I have noted in prior posts (most recently here), courts have over time evinced a continuing skepticism of securities class action lawsuit allegations based on short-seller reports. The short sellers’ financial incentives and their reliance on anonymous sources have caused courts to be wary of securities suit allegations based on their reports. In a recent Fourth Circuit decision in a case in which the plaintiffs’ allegations largely relied on a short-seller’s report, the appellate court affirmed the district court’s dismissal of the case, as discussed in detail here. There were features of the short seller report involved that may have caused the Fourth Circuit to be  particularly skeptical in that case, but the Fourth Circuit decision certainly could be useful to the defendants in seeking to oppose this new lawsuit, based as it largely is on the allegations from a short-seller’s report.

While the AI-related allegations in this complaint are only one of several types of allegations raised here, this complaint undoubtedly is AI-washing related. AI-washing claims have been among the important types of securities class action lawsuit complaints filed in recent months. Indeed, according to the Stanford Law School Securities Class Action Clearinghouse, there have now been a total of seven AI-related securities class action lawsuits files so far this year, inclusive of this latest lawsuit.

The rise in the number of AI related lawsuits at one level is hardly surprising, given that AI has in many ways permeated the world of business these days. But what is important to note about these lawsuits is that they involve allegations that the defendant companies overstated or misrepresented their AI capabilities or prospects. It is not the companies’ use of or even reference to AI that is attracting the lawsuits, it is what the company said, and more importantly what the companies wanted to try to get investors to believe about, the companies’ use of AI, that is attracting the lawsuits.

Significant initiatives such as the British Academy’s Report on the Future of the Corporation (2018), the U.S. Business Roundtable’s Statement on the Purpose of a Corporation (2019), and the World Economic Forum’s Davos Manifesto(2020) have all highlighted that companies serve not only shareholders but also employees, customers, suppliers, local communities and society at large. Policymakers and legislators around the world are also working to ensure that companies can create value for all its stakeholders. For instance, France’s 2019 Loi Pacte amended article 1833 of the French Civil Code to mandate that all French companies be managed “in the corporate interest, taking into account the social and environmental concerns linked to its activity.” In the United States, the American Law Institute’s Restatement of the Law of Corporate Governance restates the objective of a company with a strong emphasis on stakeholder interests. Against this backdrop, there is growing support for the view that company law should intervene more robustly to safeguard stakeholder interests.

China’s amended Company Law 2024 (hereafter, “new Company Law”) represents a significant step towards embedding stakeholder-oriented principles into corporate governance in the world’s second-largest economy. New article 20 explicitly requires companies to fully consider stakeholder interests – including those of a company’s employees, consumers, and environment – when conducting business. This development marks a notable advance beyond the traditional corporate social responsibility (CSR) framework and offers a more comprehensive approach than the enlightened shareholder value model enshrined in section172(1) of the UK Companies Act 2006.

While English Company Law permits directors to consider other stakeholder interests, they must act “for the benefit of its members as a whole.” By contrast, under the new Chinese framework, directors are not legally restricted from giving stakeholder interests priority, even where this may come at the expense of shareholder returns.

The new Company Law further strengthens employee engagement. It mandates consultation with labour unions and requires the solicitation of employee opinions before decisions are made regarding major corporate events such as restructuring, dissolution, or bankruptcy (article 17). Additionally, for companies with over 300 employees that do not have a supervisory board, the inclusion of employee representatives on the board of directors is now mandatory (articles 68, 120). This requirement enables employees to be directly involved in corporate decisions and ensures that workforce perspectives are brought into boardroom discussions, thus challenging the traditional shareholder-centric governance model.

Compared with employee representation on supervisory boards, mandatory representation on a board of directors – the main managerial body – offers a significant improvement. It addresses longstanding criticisms regarding the supervisory board’s limited powers to fulfil its functions effectively. By providing a direct channel for representing employee interests at the managerial level, this reform offers a more practical and robust approach to stakeholder governance, allowing employee representatives to actively participate in decision-making processes.

The new law also implements a significant recalibration of power between shareholders and directors. Since the enactment of China’s first modern Company Law in 1993, shareholders wielded significant authority over important managerial decisions, such as operational policies, investment plans, and budget approvals. The new Company Law shifts these powers to the board of directors, removing shareholders’ direct decision-making authority in these areas. Moreover, the law omits the requirement that the board be accountable to the shareholders’ meeting. Instead, article 180 and the provisions that follow emphasize that directors’ duties – specifically duties of loyalty and diligence – are owed to the company as an independent legal entity rather than to its shareholders. This shift enhances the autonomy of the board and strengthens directors’ capacity to prioritize stakeholder interests. The changes become even more significant when considered alongside the explicit statutory requirement for directors to consider stakeholder interests and the removal of mandatory board accountability to shareholders. Together, these reforms mark a material move away from shareholder primacy and towards a model of governance that better balances diverse stakeholder interests.

Beyond analyzing the shift from the shareholder primacy model as it was traditionally dominant in China, my paper proposes five approaches to further advancing stakeholder governance in China:

1. Reducing shareholder power to create more space for stakeholder-oriented decision-making.
2. Implementing ESG-based remuneration that links executive compensation to performance on stakeholder and sustainability metrics.
3. Establishing a new state agency to enforce directors’ and managers’ statutory duties, particularly stakeholder-oriented duties, under the new Company Law.
4. Leveraging regulatory initiatives beyond company law to impose minimum standards for corporate behaviour, thus redefining corporate responsibilities beyond shareholder value and decision-making.
5. Enhancing transparency and public accountability by mandating comprehensive disclosures about companies’ stakeholder relationships and practices.

These proposals not only offer a roadmap for deepening stakeholder governance in China but also provide valuable lessons for other jurisdictions seeking to develop their own stakeholder-oriented frameworks. Reforms such as the general requirement to consider stakeholder interests in decision-making, mandatory employee engagement, workforce board representation, constraints on shareholder authority, and the use of broader regulatory instruments could serve as important reference points for policy development elsewhere.

China’s evolving corporate governance model demonstrates that stakeholder governance can be more than an aspiration; it can be embedded into law and practice. The lessons emerging from China’s experience may help shape the global conversation on building more sustainable and inclusive corporate structures

This post comes to us from Min Yan, a reader in law and deputy associate dean for research at The City Law School, University of London. It is based on his recent article, “Operationalising Stakeholder Governance: Some Lessons from China’s New Company Law,” available here.

The Order cites a global imbalance in drug pricing, alleging that “The United States has less than five percent of the world’s population and yet funds around three quarters of global pharmaceutical profits.” The Order attributes this imbalance to drug manufacturers offering discounts in foreign markets while imposing higher costs on U.S. consumers for drugs. The Order argues that U.S. drug manufacturers are thereby subsidizing global drug innovation and that “As the largest purchaser of pharmaceuticals, Americans should get the best deal.”

The potential impact of the order on U.S. drug prices remains uncertain. Experts are divided: critics contend that drug manufacturers may simply raise drugs prices in the targeted countries to align with U.S. prices and that there is no enforcement mechanism for drug manufacturers who do not voluntarily change their prices.[1] However, the Order’s legality is sure to be challenged by the pharmaceutical industry. In September of 2020, Trump issued a similar, though less aggressive, MFN drug pricing order, which was challenged by pharmaceutical and healthcare industry trade groups. A federal judge blocked the order via a nationwide injunction since the Centers for Medicare & Medicaid Services (“CMS”) failed to follow notice-and-comment procedures. Therefore, the previous order failed to take effect.

On May 20, Representative Ro Khanna (D-Calif.) introduced legislation in the House which would codify Trump’s current Order — using Trump’s exact language. Two republican representatives have since joined as cosponsors. If enacted by Congress, the Order would have firmer legal footing.

That same day, the U.S. Department of Health and Human Services (“HHS”) announced it would be taking “immediate steps” to implement the Order, explaining that it “expects each manufacturer to commit to aligning US pricing for all brand products across all markets that do not currently have generic or biosimilar competition with the lowest price of a set of economic peer countries.”[2] HHS further set the MFN target price as “the lowest price in an OECD country with a GDP per capita of at least 60 percent of the U.S. GDP per capital.”[3]

[1] See Fact-checking Trump’s claim that prescription drug price drops could happen ‘almost immediately’, PBS (May 16, 2025), available at https://www.pbs.org/newshour/politics/fact-checking-trumps-claim-that-prescription-drug-price-drops-could-happen-almost-immediately;  Emma Freer, Trump’s order on drug prices isn’t what it seems, MSNBC, available at https://www.msnbc.com/opinion/msnbc-opinion/trump-drug-price-executive-order-big-pharma-rcna206289.

[2] HHS, CMS Set Most-Favored-Nation Pricing Targets to End Global Freeloading on American Patients, Department of Health and Human Services, available at https://www.hhs.gov/press-room/cms-mfn-lower-us-drug-prices.html.

[3] Id.

That’s the question at the heart of Foundations 2.0—a new national study launched by IAALS and the Law School Admission Council (LSAC) to better understand the competencies that matter most in modern legal practice. And the ABA Journal is paying attention.

In a recent article, the ABA Journal highlights the significance of the project and its potential to reshape how we define and assess lawyer readiness: “What skills do new lawyers need? Lawyers asked to provide answers in Foundations 2.0 survey”

The Foundations 2.0 survey is now live, and we’re inviting lawyers across the country to weigh in. The goal? To ensure that legal education, licensure, and professional development are aligned with what success in the profession actually requires.

This isn’t just a refresh of an old study. It’s a timely, much-needed update to IAALS’ original 2015 Foundations for Practice research, which drew responses from over 24,000 lawyers and led to one of the first empirically grounded, comprehensive models of lawyer competence. A decade later, the legal profession has changed in dramatic ways—and we’re revisiting that work to reflect the realities of practice today.

The survey explores:

• Which competencies are most critical to legal practice
• When in a lawyer’s career those competencies are most needed (day one, early practice, advanced practice)
• How lawyers believe those competencies are best developed—through coursework, clinics, externships, life experience, bar prep, or something else entirely

Our aim is not only to describe what lawyers need to succeed—but to provide a foundation for building better pathways into the profession.

Updates to come soon on our Foundations project page: https://iaals.du.edu/projects/foundations-practice

Have questions about the study? Reach out to me: Logan Cornett, IAALS Director of Research, Legal Education & Licensure logan.cornett@du.edu.

The DOL budget proposes consolidating 11 workforce development programs into a single “Make America Skilled Again” grant program to provide funding directly to states and localities.  It also would eliminate the Office of Federal Contract Compliance (OFCCP), Job Corps, and the Women’s Bureau.  The budget justifies the elimination of the OFCCP based on the revocation of Executive Order 11246, which provided the basis for OFCCP requiring most affirmative action plans of federal contractors.  The budget proposes transferring OFCCP’s remaining enforcement obligations to the Veterans’ Employment and Training Service and the Equal Employment Opportunity Commission. 

The DOL budget also contains staffing cuts to various enforcement agencies.  The Employee Benefits Security Administration, which oversees retirement, health, and other workplace benefits, faces a staffing reduction of 47.  The budget proposes reducing the Wage and Hour Division’s budget by $25,000,000 and headcount by over 400.  The Occupational Safety and Health Administration would be reduced by over 220 employees with almost $50,000,000 cut from its budget.  For more details on the proposed cuts see the DOL’s FY 2026 Budget in Brief here. 

The National Labor Relations Board (NLRB) also reduced its budget request by $14 million from $299.2 million in FY 2025 to $285.2 million in FY 2026.  The NLRB also plans on reducing staff by 99 employees through its participation in the Deferred Resignation Program and offers of voluntary early retirement.  The most significant cuts are to the NLRB’s Casehandling and Mission Support activities.  Casehandling — encompassing unfair labor practice proceedings, representation proceedings, and compliance proceedings — will have a reduced headcount of 61 employees and budget reductions of $8.9 million.  Mission Support, which includes administration, human resources, ethics, training, accounting, facilities, property, security, and technology infrastructure, will reduce its budget by $4.5 million and its headcount by 29 employees.  For more details see the NLRB’s FY 2026 Justification of Performance Budget for the Committee on Appropriations here. 

Whether Congress or the courts can stymie President Trump’s proposed cuts remains to be seen.  President Trump previously reduced the Federal Mediation and Conciliation Service (FMCS) from over 200 employees to around a dozen by executive order, but a federal judge granted a permanent injunction against it.  The Ninth Circuit also recently refused to stay a district court’s preliminary injunction against President Trump’s mass federal worker layoffs.  The district court that issued the preliminary injunction against the mass federal worker layoffs indicated recent proposed cuts at the State Department may also violate the injunction.  The First Circuit also recently denied the government’s request of a stay of a district court’s preliminary injunction against layoffs at the Department of Education. 

Ballard Spahr’s Labor and Employment Group advises employers on labor, employment, and policy issues. We will keep monitoring developments under the new administration and their impact on employers. Please contact us if we can assist you with these matters.

Reddit alleges that Anthropic trained its AI models (e.g., Claude) on public Reddit posts and comments scraped between December 2021 through October 2024.[3] Public statements by Anthropic researchers identify Reddit subreddits—such as r/explainlikeimfive, r/changemyview, and r/WritingPrompts—as “good samples” for fine-tuning training inputs.[4]

According to the complaint, Reddit grants licensed AI partners conditional access to its archive only through a designated “Compliance API” which alerts licensees when content has been deleted by users.[5] AI partners are then contractually required under their licenses with Reddit to cease ongoing use of such material, thereby respecting users’ privacy rights.[6] Anthropic, however, allegedly refused to enter such an agreement yet nevertheless continued unauthorized access to the Compliance API, using the data for commercial purposes, in violation of Reddit’s license terms.[7] Despite Reddit’s technological controls, including robots.txt directives and IP rate limits, Anthropic’s bots are alleged to have bypassed these defenses, generating over 100,000 unauthorized API calls and imposing significant server-capacity costs on Reddit.[8] These documented costs allegedly quantify the tangible economic injury to Reddit’s infrastructure, forming the basis for its claims for trespass to chattels, breach of contract, and unfair competition.[9] At the heart of Reddit’s breach-of-contract claim is Anthropic’s alleged violation of key provisions in the Reddit User Agreement—specifically, the prohibition on “commercially exploit[ing]” Reddit content, the restriction on unauthorized scraping, and the improper access and use of Reddit’s Compliance API to continue using deleted or restricted content without permission.[10]

Reddit’s strategy appears designed to highlight the consequences of using data without a license, while sidestepping unsettled copyright defenses in AI contexts.[11] According to Reddit’s complaint, without a license, Reddit cannot enforce deletion requests, monitor privacy compliance through its Compliance API, or restrict sensitive data (e.g., sexually explicit content) from being included in AI training sets—in contrast to the clear operational boundaries enforced with licensed partners.[12]

While Reddit did not include copyright claims in its complaint, Anthropic could still argue that Reddit’s non‑copyright claims are preempted by the Copyright Act because they concern how Anthropic allegedly “used” and “reproduced” user-generated content, which closely aligns with the exclusive rights of reproduction and distribution federal copyright law.[13] Under the copyright preemption doctrine, state-law claims are invalid if they rest on rights equivalent to those protected by copyright—meaning that breach-of-contract, unjust enrichment, and unfair-competition allegations tied to content use may fail.[14] Tortious interference, however, typically survives preemption because it addresses improper disruption of contractual or business relationships, not copying itself.[15]

For content creators, social platforms, and rightsholders, Reddit’s lawsuit illuminates a crucial reality: that technical restrictions alone may not reliably prevent scraping, commercializing, or misuse of data. While tools like API gating, robots.txt, and rate-limiting are essential and recommended, determined actors may still evade defenses. As a result, platforms should complement technical controls with legally enforceable terms and conditions, formal licensing arrangements (including compliance obligations and takedown mechanisms), real-time-monitoring of API access and usage, documentation of server impact to demonstrate tangible harm, and embedded privacy controls to respect user deletions and data rights. Moreover, having a clear escalation plan—up to litigation—ensures those protections are not just theoretical. As the legal framework for AI training continues to evolve, this case offers unique insight into the importance of proactive governance, technical diligence, and contract-backed enforcement mechanisms to preserve platform integrity and safeguard user trust.

FOOTNOTES

[1] Complaint, Reddit, Inc. v. OpenAI, Inc., No. CGC-25-625892 (Cal. Super. Ct. S.F. Cnty. June 4, 2025), https://redditinc.com/hubfs/Reddit%20Inc/Content/PDFs/Docket%20Stamped%20Complaint.pdf.

[2] See id.

[3] Complaint supra Note 1.

[4] Amanda Askell et al., A General Language Assistant as a Laboratory for Alignment, arXiv (Dec. 9, 2021), arXiv:2112.00861, at 35.

[5] Complaint supra Note 1.

[6] Id.

[7] Id.

[8] Id.

[9] See id.

[10] Complaint supra note 1.

[11] Id.

[12] Id.

[13] See id.

[14] See 17 U.S.C. § 301 (2023).

[15] Id.

Here is my recent Daily Record column. My past Daily Record articles can be accessed here.

****

No-Nonsense Guidance for Lawyers Still Confused About AI

I know, I know. You’re probably thinking, “Another column about generative artificial intelligence?” But guess what? This article isn’t about the latest artificial intelligence (AI) news and updates (which really are important, by the way). Instead, it’s a resource guide that will provide you with the information you need to understand AI, what it means for the future of your law practice, and how to make educated decisions about how and when to use it in your law firm. 

Generative AI advancements are happening incredibly quickly. Huge leaps in processing speed and power enable more sophisticated use cases and better response times. The improved functionality supports faster development, with new AI software and updates to existing tools rolling out weekly. 

The pace of change is breathtaking and unlike anything we’ve seen before. Even for those of us who watch the space carefully, it’s hard to keep up.

So what’s a lawyer to do? Learn as much as you can! If you’re not sure where to start, I’ve got you covered. Below, you’ll find resources that offer insights and guidance on generative AI basics along with how-tos from legal technology industry experts, including yours truly. 

So without further ado, let’s get to it. According to the AffiniPay 2025 Legal Industry Report, 76% of legal professionals reported that ethics issues were a top hurdle that slowed down AI adoption. Rather than let fears about compliance issues slow down your AI adoption, why not up your AI ethics game by ensuring your firm’s implementation crosses all the i’s and dots all the t’s?

To do this, look no further than Justia’s frequently updated 50-state survey of legal AI ethics rules. This site is a one-stop shop that lets you track ethics opinions and guidance across jurisdictions. This means that even if your state hasn’t weighed in yet, you can gain insights from legal experts across the country and make implementation decisions based on the latest guidance.

Once you’re clear on the ethical issues involved in AI adoption, the next step is to ensure you understand the technology and its implications for our profession and beyond. That’s where a newly published book authored by internationally renowned legal technology expert Richard Susskind, the author of the Future of Lawyers, comes in. In his latest book, “How to Think About AI: A Guide for the Perplexed,” he explains what AI is, what it might become, and why we need to think beyond today’s tools to understand its long-term impact on our lives and society. 

Next, let’s talk nuts and bolts. What AI tools should you implement in your firm? How do you actually use generative AI in your personal workflows? In an upcoming course on June 27th from 11 am – 3 pm ET, “AI Teach-In for Lawyers,” you’ll learn all that and more. This free hands-on course is offered by my co-author and good friend, Carolyn Elefant. It will include an overview of AI tools and hands-on demos from lawyers just like you who will show you how they’re putting generative AI to work in their law firms.

Finally, you’ll need to vet and choose generative AI tools for your law practice. My ABA Journal column is the perfect place to start. Most months, I write about a specific category of legal software, explaining what it is, how it can help your firm, issues to consider when choosing a tool, and an overview of the top options available in the marketplace. Since the rise of generative AI, many of my columns have focused on software that includes AI features, so this column is a great place to start your research into legal-specific AI software for your law firm.

You don’t have to chase every new AI tool, but ignoring AI isn’t a great strategy either. The technology landscape is changing fast, and the lawyers who prioritize understanding AI, including the ethical issues, use cases, and reputable legal tools available, will be better positioned to adapt and thrive. The resources I’ve shared here aren’t hype; they’re practical, credible, and built for lawyers like you. 

Nicole Black is a Rochester, New York attorney, author, journalist, and Principal Legal Insight Strategist at MyCase, CASEpeer, Docketwise, and LawPay, practice management and payment processing tools for lawyers (AffiniPay companies). She is the nationally-recognized author of “Cloud Computing for Lawyers” (2012) and co-authors “Social Media for Lawyers: The Next Frontier” (2010), both published by the American Bar Association. She also co-authors “Criminal Law in New York,” a Thomson Reuters treatise. She writes regular columns for Above the Law, ABA Journal, and The Daily Record, has authored hundreds of articles for other publications, and regularly speaks at conferences regarding the intersection of law and emerging technologies. She is an ABA Legal Rebel, and is listed on the Fastcase 50 and ABA LTRC Women in Legal Tech. She can be contacted at niki.black@mycase.com.

What’s an employer supposed to do when immigration policy shifts overnight?

That’s the question employers across the country are now facing. More than 500,000 immigrant workers—who entered the U.S. legally under a humanitarian parole program—were recently told to leave their jobs and “self-deport” after the Department of Homeland Security abruptly ended the program.

The headlines are emotional. The legal issues are complex.

Generally, if an employee has a properly completed I-9 form, the employer is not liable for hiring someone who later turns out to be unauthorized. As long as the documents provided at the time of hire reasonably appear genuine and relate to the employee, you’re in the clear. That’s exactly how the system is meant to work.

This situation, however, is different. In this case, the government is notifying employers that certain employees’ immigration status has changed—and that they are no longer authorized to remain in the U.S. Still, even under these circumstances, telling an employee to “self-deport” carries legal risk.

Ordering someone to self-deport, or assuming an employee is no longer authorized to work without specific legal notice, can violate federal law—specifically Title VII (prohibiting national origin discrimination) and the Immigration Reform and Control Act (prohibiting citizenship-status discrimination). Unless you have clear, individualized notice that an employee is no longer authorized to work—and handle it neutrally and professionally—you’re putting your organization at legal risk.

If you receive specific, credible information that an employee is no longer authorized to work, here’s what you should do:

1. Verify the Information

Confirm that the information is individualized, specific, and credible—ideally coming from DHS, SSA, or the employee themselves.

2. Notify and Allow a Response

Inform the employee of the issue and give them an opportunity to present valid work authorization documents.

3. Evaluate Documentation

Review any documents provided according to Form I-9 rules to (re)confirm work authorization.

4. Avoid Discrimination

Do not take any action based on assumptions, rumors, or profiling. Stay clear of decisions rooted in national origin or citizenship status.

5. Take Action If Necessary

If the employee cannot provide valid work authorization, you may need to terminate employment—but be sure to document every step thoroughly.

Finally, if DHS provides formal notice that an employee’s status has expired—or agents show up at your business—call your attorney immediately. Remember: your job is to run a business, not to enforce immigration law.

     

Related Stories

• The fiduciary case for DEI
• When rights collide: religious beliefs vs. gender identity in the workplace
• DEI-washing

 

Last week, I had the privilege to attend one of the Midwest’s largest artificial intelligence conferences dedicated to AI developers, users, and enthusiasts: Cincy AI Week. During the three-day event, which brought together over 950 local professionals, I spoke on a panel entitled “Managing Risk in the Age of AI and Automation.”

Here are six important observations I shared during that panel:

1.  Organizations needs to shift risk posture from reactive to proactive.

AI technologies are increasingly influencing decision-making, data handling, and customer interactions. Accordingly, legal risks – from security incidents and data breaches to algorithmic bias – are no longer hypothetical, but imminent. Organizations must embed legal and ethical oversight into each stage of AI development and deployment, rather than addressing issues only after they arise. This means engaging legal counsel early, implementing clear accountability frameworks (see below), and ensuring transparency and auditability in AI systems. Doing so not only mitigates risk, but also builds trust with regulators, clients, and stakeholders in a rapidly evolving legal landscape.

2. Data governance, vendor risk, and internal misuse remain major vulnerabilities for organizations adopting AI tools.

As organizations rapidly adopt AI tools, many overlook risk exposure in data governance, vendor risk, and internal misuse; each posing significant legal and regulatory exposure. Inadequate data governance can lead to incidents of unauthorized use of sensitive or non-compliant data in model training. Such unauthorized use could constitute violations of data protection laws such as GDPR, CCPA, HIPAA, and various state consumer privacy laws. Meanwhile, reliance on third-party AI vendors without thorough due diligence or contractual safeguards can expose organizations to hidden liability such as intellectual property infringement and undisclosed model risks. Internally, the misuse of AI – whether through employee error, lack of oversight, or improper prompts – can result in biased outputs, misinformation, or breaches of confidentiality. Without a comprehensive legal strategy to address these gaps, businesses risk serious reputational, financial, and legal consequences.

3. Legal and technical teams need to collaborate on AI risk management.

Effective AI risk management demands close collaboration between legal and technical teams because the challenges posed by AI straddle both legal obligations and technical complexities. Legal teams bring critical expertise in regulatory compliance, intellectual property, privacy, and liability. Technical teams, on the other hand, understand how AI models are built, trained, and deployed; thereby giving technical teams insight into an AI model’s limitations and potential for unintended outcomes. Without alignment, organizations risk (a) legal teams overlooking how a system actually functions, and (b) technical teams missing key regulatory implications. Instead, by working together from the beginning of the AI development or adoption lifecycle, these teams can design and procure AI systems that are not only innovative and efficient, but also legally sound, transparent, and defensible under regulatory scrutiny. This integrated approach is necessary to mitigate risk, ensure accountability, and maintain trust in an increasingly AI-driven environment.

4.  NIST and ISO frameworks are a great starting point for AI-specific cybersecurity planning.

The National Institute of Standards and Technology (NIST) AI Risk Framework offers structured guidance on identifying, assessing, and mitigating risks unique to AI systems, such as data poisoning, model inversion, and adversarial attacks. Adapting cybersecurity policies, such as those modeled on ISO/IEC 27001 or the NIST Cybersecurity Framework, to address AI-specific vulnerabilities ensures a more resilient security posture. In-house and outside counsel play a critical role in this process by ensuring that these frameworks are aligned with regulatory requirements and contractual obligations; particularly in sectors handling sensitive or high-risk data. Organizations that leverage these frameworks into their AI development lifecycle are better positioned to manage evolving threats while demonstrating compliance and due diligence to regulators, customers, and stakeholders.

5.  Transparency and explainability are essential for managing AI risk.

Legal scrutiny around algorithmic decision-making has intensified over the last two years. Transparency and explainability are not just ethical ideals; they are practical safeguards.  Transparent AI systems allow organizations to understand how decisions are made, which is essential for identifying and mitigating bias, ensuring compliance with anti-discrimination and data protection laws, and responding effectively to audits and litigation. Explainability strengthens accountability by enabling organizations to justify automated decisions to regulators, courts, and impacted individuals in high-risk environments like finance, healthcare, and employment. Lack of explainability, on the other hand, can lead to regulatory penalties, reputational damage, or invalidated outcomes. Building AI systems with transparency and explainability from the outset is a key step in reducing legal risk and fostering trust.

6. Security-first cultures do not need to slow innovation.

Building a security-first culture does not mean stifling progress. Instead, a security-first approach means adopting smart, scalable safeguards into the innovation process from day one (in other words, security-by-design). By aligning legal, security, and technical teams early in the development or adoption lifecycle, organizations can proactively address risks without creating bottlenecks. Clear policies, ongoing employee training, and cross-functional collaboration through an AI Governance Committee ensure that security is treated as a shared responsibility instead of a final checkpoint. This approach empowers teams to innovate with confidence by knowing that privacy, compliance, and risk management are integrated rather than obstructive. 

As AI reshapes how organizations operate, the intersection of cybersecurity, legal compliance, and responsible innovation has never been more critical. The six observations I shared during Cincy AI Week underscore a central theme: managing AI risk is not just a technical or legal challenge; instead, it is a strategic imperative that demands proactive, cross-disciplinary coordination. By merging legal oversight into the development process, embracing transparency, leveraging established frameworks, and fostering a culture where security and innovation go hand-in-hand, organizations can mitigate risk and build resilient, trustworthy AI systems. In other words, as AI continues to evolve, so too must risk strategies.

For more information on data privacy and security regulations, AI, and other data privacy questions, please visit Taft’s Privacy and Data Security Insights blog

Transcript: Performance Reviews: Lessons from Severance (PDF)

Troutman Pepper Locke’s Labor + Employment Practice Group provides comprehensive thought leadership through various channels. We regularly issue advisories that offer timely insights into the evolving employment law landscape, and maintain the HiringToFiring.Law Blog, a resource spotlighting best practices for employers. Our Hiring to Firing Podcast, hosted by Tracey Diamond and Emily Schifter, delves into pressing labor and employment law topics, drawing unique parallels from pop culture, hit shows, and movies.

In the suit, Mark Walters v. OpenAI LLC, 23-A-04860-2 (Sup. Ct. Gwinnett Cty, GA), the plaintiff alleged that that the ChatGPT tool, developed by OpenAI, defamed him when it presented false information about him to a journalist.  According court’s order, the journalist used the AI tool to summarize a complaint while writing an article about an unrelated lawsuit.  The summary provided by ChatGPT falsely stated that the complaint was filed against the plaintiff for committing fraud and embezzlement.

In granting summary judgment, the court, first, found that “a reasonable reader in [the journalist]’s position could not have concluded that the challenged ChatGPT output communicated ‘actual facts,’” and thus the output is not defamatory as a matter of law.  Among other things, the court observed that “ChatGPT warned [the journalist] that it could not access the internet or access the link to the . . . complaint that [he] provided to it, and that it did not have information about the period of time in which the complaint was filed, which was after its ‘knowledge cutoff date.’”  The court cited expert testimony which found that the journalist’s “Prompt Engineering techniques and choice to ignore ChatGPT’s warnings about its limitations contributed to the non-factual output.”

Second, the court found that the plaintiff could not demonstrate fault under a negligence or actual malice standard.  The court explained that whereas OpenAI offered evidence “demonstrating [it] leads the Al industry in attempting to reduce and avoid mistaken output like the challenged output here,” the plaintiff “identified no evidence of what procedures a reasonable publisher in OpenAl’s position would have employed based on the skill and experience normally exercised by members of its profession.”  The court also found the plaintiff is a public figure, and thus must establish that OpenAI acted with actual malice to hold the company liable for defamation, but that plaintiff did not provide any evidence to support that contention.

However, recent developments – including SEC Chair Paul S. Atkins’s appointment in April 2025, the emergence of a Republican-appointed majority in the Commission, and ongoing efforts to rescind the rules – have contributed to uncertainty surrounding their future.

Background of the cybersecurity disclosure rules

As discussed in this DLA Piper alert, the 2023 cybersecurity disclosure rules received mixed reception at both the proposal and adoption stages.

At the time of adoption, the two Republican-appointed commissioners, Hester Peirce and Mark Uyeda, voiced their opposition, with Commissioner Peirce releasing a statement arguing, among other things, that the cybersecurity rules:

• Exceeded the SEC’s authority because they were not tied to financial materiality
• Were outside the SEC’s expertise
• Failed to take into account other cyber disclosure laws
• Offered too narrow of an exception for law enforcement concerns
• Would increase compliance costs for companies
• Would require disclosure that could benefit cyber criminals, and
• Could lead to vague and misleading disclosures.

Similarly, Commissioner Mark Uyeda, in his own statement, contended:

Cybersecurity is one of numerous risks and issues that companies must address from financial, operational, governance, and other perspectives. The [SEC]’s disclosure rules should not elevate cybersecurity above these other risks and issues, some of which may be more material to investors.

Commissioner Uyeda noted that the rules would require companies to make forward-looking disclosures regarding a cybersecurity incident’s material impact, which would need to be continually assessed for additional impacts and potential amendments to Form 8-K, if new information arose after the initial disclosure. He pointed out that other required disclosure events, such as a merger, do not need to be constantly assessed.

In November 2023, Representative Andrew Garbarino and Senator Thom Tillis introduced a resolution of disapproval under the Congressional Review Act, in an effort to rescind the rules – however, the resolution failed to pass.

Recent efforts to rescind the rules

Since former SEC Chairman Gary Gensler stepped down in January 2025 and the Commission shifted to a Republican majority, efforts to rescind the cybersecurity rules have intensified.

In March 2025, the Republican members of the House Financial Services Committee issued a letter to then-Acting Chairman Uyeda, urging the SEC to withdraw several proposed and adopted rules, including the cybersecurity rules. That same month, at a hearing of the US House Committee on Homeland Security Subcommittee on Cybersecurity and Infrastructure, several lawmakers expressed dissatisfaction with the cybersecurity rules, citing their ambiguity and restrictive reporting timelines.

Most recently, on May 22, 2025, a group of banking associations, including the American Bankers Association, Bank Policy Institute, Independent Community Bankers of America, Securities Industry and Financial Markets Association, and Institute of International Bankers, petitioned the SEC to rescind the rule requiring companies to disclose cyber incidents under Item 1.05 of Form 8-K within four business days of a determination of materiality. The petition outlined concerns that align with those previously expressed by Commissioners Peirce and Uyeda.

In seeking recission of Item 1.05 disclosure, the petition letter cited key issues alleging that:

• Publicly disclosing cybersecurity incidents directly conflicts with confidential reporting requirements intended to protect critical infrastructure and warn potential victims, thereby compromising coordinated regulatory efforts to enhance national cybersecurity.
• The complex and narrow disclosure delay mechanism interferes with incident response and law enforcement investigations.
• The rule has created market confusion and uncertainty as companies struggle to distinguish between mandatory and voluntary disclosures.
• Resulting disclosures have been weaponized as an extortion method by ransomware criminals to further malicious objectives and may subject disclosing companies to additional cybersecurity threats.
• Insurance and liability implications of premature disclosures can exacerbate financial and operational harm to companies.
• The rule risks chilling candid internal communications and routine information sharing.  

The petitioning organizations urged the SEC to return to a more principles-based disclosure regime, through which companies would consider the materiality of cybersecurity risks and incidents in determining whether disclosure was appropriate.

Going forward

It is unclear what actions the SEC will take in response to the petition and related criticism. Among possible approaches, the Commission could opt to modify or rescind some or all of the rules under the Administrative Procedure Act (APA). The APA would require the SEC to issue a proposal, solicit public comment, and provide a reasoned explanation for any such change. A shift in policy could serve as a valid rationale, provided the SEC addresses prior factual findings that supported the original rules.

It is worth noting that, in February 2025, the SEC announced the creation of the Cyber and Emerging Technologies Unit (CETU) to focus on combatting cyber-related misconduct and to protect retail investors from bad actors in the emerging technologies space.

In the meantime, companies are encouraged to establish and maintain controls and procedures that will allow them to identify, assess, and report cybersecurity incidents. They are also encouraged to fully and accurately describe their cybersecurity risk management and governance procedures in their SEC filings, as applicable.

For more information, please contact the authors.

Despite these benefits, executive use of corporate jets may have complex implications, including tax consequences, SEC disclosure (publicly traded companies only) and other key considerations. As discussed in a separate Proskauer blog post, the IRS also recently announced a new audit campaign targeting the use of corporate jets, although it is unclear whether this will remain a focus of the new administration.

Tax Considerations for Private and Public Companies

Private and public companies, including private equity sponsors and other investment managers, and their employees must consider the tax consequences of allowing an executive or investment professional to use corporate jets for personal use. Specifically, under IRS rules, the value of an executive’s personal use of a corporate aircraft is treated as imputed income to the executive and is taxable compensation, subject to tax reporting and withholding. The most common method for calculating the value of the imputed income is by using the Standard Industry Fare Level (SIFL) method, which is based, among other things, on the distance flown, aircraft weight and number of passengers on a private jet. The value calculated under the SIFL method is reported as W-2 income to the executive and is subject to payroll taxes, although this amount is often significantly less than the fair market value of the benefits provided to the executive or the actual cost to the company of operating the jet. Additionally, although an employer’s cost of operating a non-commercial aircraft is generally deductible as an ordinary business expense, employers may not be able to deduct any entertainment expenses associated with personal travel under the Tax Cuts and Jobs Act (TCJA).

In order to determine the potential tax consequences of allowing an executive to use a corporate jet for personal use, companies must separately evaluate whether each passenger on a corporate jet is flying for a valid business purpose (e.g., while an executive may have a valid business purpose for flying on a corporate jet, the executive’s spouse may be traveling for entertainment in certain circumstances). If certain passengers (but not others) are traveling for entertainment, the portion of flight expenses allocated to those guests traveling for entertainment may be considered a taxable fringe benefit to the executive hosting the guests and, as an entertainment-related expense, may not be deductible to the employer under the TCJA. Importantly, these tax implications would apply even if a corporate jet has empty seats available for use at no additional cost.

SEC Disclosure Obligations for Public Companies

In addition to the foregoing tax implications, with respect to public companies only, personal use of company aircraft by the company’s named executive officers (NEOs) must also be disclosed in the company’s proxy statement under SEC rules. In particular, Item 402 of Regulation S-K requires disclosure of perquisites and other personal benefits if the total value exceeds $10,000 in a fiscal year. Importantly, the incremental cost to the company of providing this benefit, and not the value imputed to the executive, is used for purposes of this disclosure. As a result, this disclosure typically includes the cost of fuel, maintenance of the aircraft, crew costs, landing fees and in-flight catering and services, although fixed costs like the depreciation of the aircraft or any base salaries paid to staff generally are not required to be disclosed unless these costs are increased due to the executive’s personal use. In addition, if any single perk exceeds the greater of $25,000 or 10% of total perks, its specific value must be itemized, which may result in increased scrutiny from investors and regulators.

Other Key Considerations

In addition to the tax and SEC disclosure considerations, other key considerations should be analyzed. For example, internal policies and recordkeeping procedures should be established and monitored and, from a corporate governance perspective, appropriate approvals from the board or its committees (e.g., audit or compensation) should be obtained. Once approved, periodic reporting and monitoring may be advisable. Further, other regulatory considerations should be reviewed, particularly, where corporate-owned aircraft is used (e.g., FAA rules).

Proskauer Perspectives

Given these considerations, companies that permit executives to use their private aircraft should carefully track and retain information relating to their use. It is also best practice for companies to establish clear policies and guidelines regarding using aircraft for personal travel, including the process for obtaining pre-approval for any personal use. A company’s finance, tax, legal and human resources functions should also coordinate to ensure an executive’s imputed income is correctly tracked and reported and any personal use by an executive is properly disclosed in accordance with the SEC disclosure rules. Companies may also consider requiring executives to reimburse them for the costs associated with any personal use, which may mitigate some of the issues discussed in this blog post.

Although allowing executives to use a company’s private aircraft can be an attractive benefit for executives, businesses should proactively manage any associated tax, governance and operational issues and, for public companies, SEC disclosure obligations as well. By addressing these issues in a thoughtful and comprehensive manner, companies can support their management team by avoiding unnecessary surprise tax consequences and also reinforce investor confidence through consistent governance practices that contribute to long-term corporate stability and trust.

Reasons for Disagreement Among Experts

Business valuation experts generally follow a similar methodology, and as a result it may seem surprising that they can reach results that vary so dramatically. There are a number of factors, however, that help explain these conflicts. First, business valuation experts make assumptions that impact value, and these different assumptions can lead to substantially different results. As a key example, valuation experts will project the future growth rate of the business based on past trends and anticipated future events, and as a result, when the experts use markedly different projected growth rates for the business, they will reach results that have major differences.

Second, the valuation experts also typically apply substantial discounts to minority held interests, which are based on the lack of control and the lack of marketability of the interest held by the minority investor. These discounts are determined, in part, by reviewing previous transactions of similar companies, but selecting different discount rates will have a large impact on the valuation of the minority interest.

Finally, the valuation experts may rely on different data that also leads to wide variances in their opinions. In this regard, the experts will compare and apply the sales of other businesses, but they may include or reject certain sales as applicable, and using different transaction data impacts their results. Similarly, based on their own analysis, the valuation experts may use different industry multiples to apply to the company’s earnings, which is a key driver of total value of the business. If one expert concludes that the proper multiple is 5 and the other says it is 7, that difference may sound small but it will actually be quite large when the multiple is applied to the company’s earnings.

Practical Solutions to Apply to the Valuation Dispute

Given the potential, if not the likelihood, that valuation experts will reach different opinions regarding the value of a minority holding in a private company, majority owners and investors are well-advised to consider options that may allow them to avoid or at least limit these conflicts. These pragmatic approaches are discussed below.

Expert Report Averaging

If the parties anticipate that a large variance will result between the reports of the valuation experts, they can agree to a process in which three different experts are retained, and they can then average the results of all three valuation reports. Typically, this means that the company/majority owner will retain a valuation expert, the minority investor will retain a second expert, and the parties will direct those two experts to select a third, independent expert. 

Once all three valuation reports are issued, the partners can agree to one of the following options: (1) they can average all three of the reports, (2) they can decide that the valuation report of the party (either majority owner or investor) that is closest in amount to the third valuation expert’s report will be controlling, or (3) they can average the amount of the two reports that are closest in value to determine the final valuation number. Selecting any of these options in regards to valuation will avoid a legal battle.

Adopt Base Value Plus Earn Out

A second option to avoid valuation conflicts is for the parties to agree on a base price for the purchase of the minority investor’s interest that references the valuation, but that also provides for an additional payment to the minority investor. In this scenario, the minority investor receives a fixed price at closing, along with a carried (non-equity) interest based on the company’s future financial performance. This structure thus provides for the investor to receive somewhat less than the full amount of the valuation price at closing, but with the potential to receive an additional amount greater than the valuation price based on the company’s future performance.

As an example, the valuation report values the minority investor’s interest at $3 million, which the majority owner considers excessive. The parties therefore agree that the investor will be paid $2.25 million at closing (25% less than the valuation report) for its interest, but the minority investor also receives a contractual right to be paid 3% of the total revenues that are generated by the company over the next three years. If the company has generated at least $10 million in revenue during each of the past three years, this might be a win-win scenario, as applying to this formula would generate at least $900,000 in a further payment for the investor if the company continued to generate annual revenues of at least that amount over the next three years. 

Obviously, the potential variety of formulas that might work is infinite, but this type of win-win negotiating allows for the majority owner to push back on the total amount paid at closing to the investor while also providing the minority investor with further upside. To make this proposal work, the majority owner may need to establish a floor for the future payment, i.e., provide the investor with a guaranteed payment of at least a certain amount in the future so that the investor is not taking on a totally unprotected gamble. 

Arbitration Limited to Resolution of Valuation Dispute

The third practical option to consider involves a targeted resolution process. The manner in which an arbitration is conducted is subject to contract, so rather than engaging in protracted negotiations over a lengthy period, the parties could agree to submit their valuation dispute to a prompt one-day arbitration. This is simple and straightforward as the parties should not need to obtain any discovery if they have all of the financial information necessary for the valuation. The scope of the arbitration can be limited solely to resolving the amount to be paid for the purchase of the minority owner’s interest in the company. In short, the parties submit their valuation reports and testimony from the valuation experts to explain their opinions, and the arbitrator (or panel) issues a final, binding opinion.

Considerations That Apply to Valuation Conflicts

Whatever path the parties decide to go down, they need to set guidelines that will help limit the disputes between them regarding the valuation and the ultimate cost of achieving their business divorce.  The procedure for dealing with valuation is generally set forth in some form of a buy-sell agreement. 

First, the parties need to set firm deadlines for issuing all of the required valuation reports. Second, they need to provide a mechanism and timetable for the minority investor to obtain access to the financial information that is necessary to determine the value of the investor’s interest, which the investor will likely provide to its own independent valuation expert. Third, they need to decide who pays the costs for the experts. Often, the company will prepare the first valuation at its sole cost, but if the minority investor then wants to secure a separate valuation, that comes at the expense of the investor. If there is a third valuation, the cost of the third valuation expert is shared equally by the parties. Finally, if there are disputes over the valuation, this is where the arbitration provision will specify how any/all disputes will be resolved promptly and efficiently.

Conclusion

The business divorce process can be frustrating, particularly when valuation disputes arise, but these conflicts can be anticipated, and they should not derail the parties’ efforts to achieve their desired business separation. The key is to be proactive.  Business partners need to agree in advance on an approach to valuation before disputes take hold, because once they are in conflict, it will be extremely difficult for them to reach consensus on any form of resolution. If the partners plan ahead and implement one of the practical paths to resolution reviewed above — averaging expert reports, adopting a base value/earn out structure, or implementing a targeted arbitration — they will have a much better chance to avoid singing the valuation blues. 

If you should ever leave me
Though life would still go on believe me
The world could show nothing to me

What’s Going On?

As expected by many, Gov. Gavin Newsom’s administration proposed a permanent ban on many of the hemp products available in the state, as reported in SFGate (emphasis added):

The California Department of Public Health proposed the ban Friday, which would make a controversial earlier emergency ban permanent, according to a CDPH document shared with SFGATE. It’s now in a 45-day comment period, with a public hearing planned next month.

Gov. Gavin Newsom has spearheaded a ban on these hemp THC products, saying they are accessible to minors and pose a public health risk because they do not face the same safety standards as state-regulated marijuana products do. Newsom pushed for last year’s emergency THC ban and extended it in March. It is now set to expire in September. 

Making the ban permanent will have a major adverse economic impact on the state, according to the analysis released Friday. The CDPH estimates that it will cause a $602 million decreasein revenue for California businesses for the first 12 months and a $3.14 billion decrease over five years. The ban will also cost 18,478 jobs over five years, force 115 businesses to close, and reduce state sales tax revenue by $192 million, according to CDPH’s estimate.

The analysis found that small, independent retailers like corner stores and grocery stores would be especially impacted over the first five years of the ban, with $1.9 billion in lost revenue and 5,567 lost jobs.

Friday’s proposal to permanently ban hemp THC comes after years of complaints from California’s licensed marijuana industry, which has claimed that it faces unfair competition from unregulated hemp companies. Marijuana companies face sky-high regulatory costs, especially in California, and can only sell their products through state-licensed retailers. Hemp companies, on the other hand, face almost no regulations and have historically been able to sell their intoxicating drugs almost anywhere, including liquor stores, grocery stores and online.

This disparity between the two industries has created pressure on governors like Newsom to protect their state-regulated cannabis companies. In California, these businesses are already increasingly failing under the weight of the high taxes and expensive regulations overseen by Newsom. Other states with robust state-licensed marijuana markets have also restricted hemp THC, including Oregon and Washington.

Licensed cannabis companies would gain $69.8 million and 232 jobs over the first five years of the proposed ban, according to the CDPH analysis. The department said “these numbers are comparatively low to retail sales lost in other sectors” because demand for hemp THC drinks is minimal at state-licensed stores.

The department also said illicit sales will probably fill the void if hemp THC products are permanently banned. “Out-of-state businesses and the illegal market will supply the California THC hemp market,” the report said.

Why Is This a Problem?

I have just been in the middle of knife fights in the legislative halls of Alabama and Mississippi where hemp products were under attack. I’m currently working on the next federal Farm Bill and what the hemp language ultimately looks like. And just today I read of similar efforts in Delaware. So, I’ll admit this is an issue that has been on my mind for a long time.

I completely understand why state-regulated marijuana operators are opposed to often unregulated hemp operators being able to conduct business without the onerous burden of regulations and taxation. I also believe that there are ways to even the playing field without prohibiting consumable hemp products entirely. 

Are you worried about minors obtaining product? Put laws in place that prohibit access to minors and spend the time and money enforcing those laws. The money can come from fees paid by hemp manufacturers and retailers in the form of licensing/permitting fees and taxes on hemp.

Worried about the safety and potency of products? Put extensive rules in place that govern testing requirements and potency caps, with the latter possibly tailored to where the products are sold. Perhaps grocery stores and gas stations/convenience stores would be limited to lower THC products, whereas specialty hemp stores would be able to sell different products with higher THC levels.

Worried about labeling and packaging? Put extensive rules in place that ensure packages are child resistant and labels clearly explain (with QR codes to COAs) what is in the product and how it was tested to ensure that the package contains what it says it does.

Or – and I suspect this is the motivation for many – are you worried that regulated marijuana operators are at a disadvantage as compared to hemp operators facing far less regulation? Then put them on a more level playing field. Impose similar taxes and regulations so that responsible marijuana operators are not punished for following the rules while hemp companies operate without government oversight. Marijuana operators shouldn’t be able to bully hemp operators out of business simply because of greed, but hemp operators shouldn’t get a free pass either.

Conclusion

Maybe God only knows why the government of California is making the decision to ban its robust hemp industry rather than seeking ways to reform it so that it addresses the stated (albeit likely not entirely complete) concerns of the hemp program’s critics. But this isn’t a Beach Boys album; this is real life and real governing with real implications to operators and consumers. The government has a chance to dig into this issue and make hard choices that can make California a better market for the cannabis plant generally and all of those people who have come to rely on it through the years. I won’t pretend that this process will be easy, and certainly not as easy as simply banning an entire class of products. That’s the easy way out. Maybe I’m just California Dreamin’, but Wouldn’t It Be Nice if the people of California were treated better by their government?

Thanks for stopping by.

Since its enactment in 2019, Minnesota’s Wage Theft Prevention Act has imposed stringent penalties on employers who unlawfully withhold wages from employees. Under the Act, employers may face felony charges if they commit wage theft with intent to defraud their employees in an amount greater than $1,000.

On April 9, 2025, Frederick Newell, owner of Integrated Painting Solutions (IPS), became the first individual in Minnesota to be convicted of felony wage theft, including theft by swindle.[1]  According to the criminal complaint, Mr. Newell and his company secured a contract in 2020 to perform painting and wall covering for the construction of an affordable apartment complex in Minneapolis. Because this was a government-funded project, IPS was required to pay the employees the prevailing wage rate and maintain certain business and payroll records.

During the project, several employees filed complaints with the Minneapolis Civil Rights Division, alleging that Mr. Newell had engaged in unlawful wage practices. In 2021, the Division’s investigation found that Mr. Newell and IPS committed wage theft and other labor violations in connection with this project. On June 2021, the Division issued a violation letter to IPS and, ultimately, Mr. Newell entered into a settlement agreement with the Division, agreeing to pay $43,166 in restitution for the unpaid wages. Despite the agreement, Mr. Newell failed to make the payment.

On December 30, 2022, criminal charges were filed against Mr. Newell. After a bench trial, Mr. Newell was found guilty of felony wage theft by failing to pay five employees more than $37,000. Mr. Newell also was found guilty of theft by swindle in connection with the project.

On June 6, 2025, Mr. Newell was sentenced to three years’ supervised probation and was ordered to complete 200 hours of community service and to pay $42,255.64 in restitution to Griner Construction, the general contractor for the project which had voluntarily paid the IPS workers the monies owed by IPS and Mr. Newell. Mr. Newell also was prohibited from bidding on new public contracts during the term of his probation. Mr. Newell argued that the bidding prohibition would hinder his ability to pay restitution, but the Court dismissed this concern and clarified that the restriction is limited to three years and did not impact existing contracts.

Although this is Minnesota’s first felony wage theft conviction, at least two more cases against employers are pending for similar claims of wage theft and theft by swindling.

In addition to Minnesota’s enforcement of wage theft against employers, several other states have enacted criminal wage theft statutes, including:

• California
• Colorado
• Idaho
• Illinois
• Kansas
• Kentucky
• Virginia
• Wisconsin

Minnesota’s first felony wage theft conviction reflects a broader national trend. As more states enact similar statutes, employers will continue to face heightened accountability for wage violations. Please contact your Husch Blackwell attorney with any questions related to ensuring your business is in compliance with state and local wage and hour laws.

[1] State v. Newell, Case No. 27-CR-23-445, State of Minnesota, Fourth Judicial District, Hennepin County.

When it comes to China trademark registration, timing is everything. File too late, and someone else might beat you to your own brand. File too early, and you risk losing your trademark for non-use. Like Goldilocks, you need to get it just right.

The Cautious Client: Waiting on Government Approval

An Australian client recently asked if they should register their brand name and logo as trademarks in China, even though their product hadn’t yet received Chinese government approval. Their concern? Spending money on trademarks they might never use. Their bigger concern? A trademark squatter registering their brand name before they could enter the market.

Our advice was clear: You should absolutely register your brand name in China before disclosing it publicly or engaging any Chinese distributors. Once someone else sees value in your mark, they might register it first—and under China’s first-to-file system, they could legally block you from using your own name.

Beyond those critical steps, we recommended weighing the cost of trademarking (both the brand and the logo) against the odds of someone else registering them without notice. In this case, because the product name was distinctive and region-specific to the U.S., the risk was relatively low—so long as the client kept their China plans confidential and didn’t need to reveal the brand during the product approval process.

The Overeager Inventor: Filing Too Soon

At the other end of the spectrum was an inventor convinced his product would be a global success. He wanted to file a China trademark application across six classes—immediately—even though he had no timeline for manufacturing.

We urged caution. Filing at that stage would offer little benefit and real risk. Since his brand name was highly distinctive, there was minimal danger of someone else registering it—unless they heard about it from him. We advised holding off on trademark registration until revealing the brand became necessary.

Under China’s trademark law, if a registered mark isn’t used for three consecutive years, it becomes vulnerable to cancellation for non-use. Filing too early, without any commercial activity or enforcement plan, can mean losing the mark before it ever becomes valuable.

So When Should You Register a Trademark in China?

The sweet spot lies between premature protection and delayed action. You want to file before any exposure or negotiation in China—but not so early that your trademark gathers dust and becomes a liability.

This kind of strategic timing helps protect your brand from trademark squatters, non-use cancellation, and costly disputes.

Whether you’re on the verge of entering the market or still mapping out your expansion strategy, a well-timed China trademark registration can make all the difference. Our international trademark team can help you find that Goldilocks moment.

Let us know when you’re ready.

This narrative explores how models trained on vast, minimally curated datasets are exposing gaps in frameworks like the GDPR, particularly when it comes to consent, purpose limitation, and accountability. It delves into the increasing difficulty of tracking data provenance and ensuring compliance in systems where transparency often ends at the model boundary.

For professionals in privacy, compliance, and information governance, the article offers a timely and critical lens to reconsider whether current data policies can withstand the scale and opacity of generative AI. It argues for a shift from static regulation to proactive, lifecycle-oriented governance practices that better reflect the realities of AI-driven data use.

Industry News – Artificial Intelligence Beat

Data at Risk: The Governance Challenge of Generative AI

ComplexDiscovery Staff

News Sources

• Abendroth Dias, K., Arias Cabarcos, P., Bacco, F.M., Bassani, E., Bertoletti, A. et al., Generative AI Outlook Report – Exploring the Intersection of Technology, Society and Policy, Navajas Cawood, E., Vespe, M., Kotsev, A. and van Bavel, R. (editors), Publications Office of the European Union, Luxembourg, 2025, https://publications.jrc.ec.europa.eu/repository/handle/JRC142598.
• JRC Publications Repository

Assisted by GAI and LLM Technologies

Additional Reading

• The LockBit Breach: Unmasking the Underworld of Ransomware Operations
• The TeleMessage Breach: A Cautionary Tale of Compliance Versus Security
• Inside CyberCX’s 2025 DFIR Report: MFA Failures and Espionage Risks Revealed

Source: ComplexDiscovery OÜ

The post Data at Risk: The Governance Challenge of Generative AI appeared first on ComplexDiscovery.

Penberthy’s journey with AI began with a sense of wonder and a chance encounter with a pioneering AI professor. This early fascination led him to a career at the intersection of technology and real-world impact, where he now leads efforts to apply AI to some of humanity’s toughest challenges, particularly in healthcare and life sciences.

At the core of Penberthy’s approach is the idea of modeling the world as “tensors”-high-dimensional data structures that can represent everything from business processes to the code of life itself. He describes healthy lives as paths through these multidimensional shapes, with AI acting as a guide: detecting when we drift off course and suggesting simple actions to keep us on track. This tensor-centric perspective has fueled Google Cloud’s innovations in semantic search, embeddings, and enterprise AI products, especially in fields like bioinformatics and precision medicine.

Penberthy’s work is particularly focused on using AI to transform healthcare. He envisions a future where AI-powered models can analyze genomic data, track health transitions, and detect diseases like cancer years before symptoms appear. Thanks to advances in AI, genomics, and cloud computing, the cost of sequencing and analyzing a patient’s DNA is plummeting-from millions of dollars to potentially just $50-making early detection and personalized health guidance accessible to all. In Penberthy’s words, “AI is the ultimate pattern recognizer,” capable of uncovering hidden relationships in vast datasets that would be impossible for humans to spot unaided.

But the implications of these new AI models go far beyond healthcare. Penberthy highlights how breakthroughs in neural networks, attention mechanisms, and diffusion models are driving innovation across sectors-from drug discovery and market analysis to optimizing supply chains and even searching for minerals on the moon. These models are not just learning from static data; the next wave will be able to learn from experience, adapt in real time, and generate new knowledge on the fly.

Penberthy is candid about the challenges ahead. The pace of change is dizzying, and society will need to adapt quickly to keep up. He stresses the importance of embracing these technologies thoughtfully, ensuring they are used to augment human capabilities and solve real problems. The future, he suggests, belongs to those who can combine the power of AI with domain expertise, curiosity, and a willingness to revisit first principles when the old ways no longer suffice.

In summary, Scott Penberthy’s vision for AI’s new frontiers is both ambitious and grounded. He sees a world where AI models are not just tools, but partners in discovery-helping us live longer, healthier lives, make better decisions, and unlock mysteries that have eluded us for generations. As these models continue to evolve, the possibilities are limited only by our imagination and our resolve to use them wisely.

For more information, please visit the following:

Website: https://www.josephraczynski.com/

Blog: https://JTConsultingMedia.com/

Podcast: https://techsnippetstoday.buzzsprout.com

LinkedIn: https://www.linkedin.com/in/joerazz/

X: https://x.com/joerazz

AI-Generated Phishing & Social Engineering

Cybercriminals now use generative AI to craft near-perfect phishing messages—complete with accurate tone, logos, and language—making them hard to distinguish from real communications . Voice cloning tools enable “deepfake” calls from executives, while deepfake video can simulate someone giving fraudulent instructions.

Thanks to AI, according to Tech Advisors, phishing attacks are skyrocketing—phishing surged 202% in late 2024, and over 80% of phishing emails now incorporate AI, with nearly 80% of recipients opening them. These messages are bypassing filters and fooling employees.

Adaptive AI-Malware & Autonomous Attacks

It is not just the threat actors but the AI itself that drives the attack. According to Cyber Defense Magazine reporting:  

Compared to the traditional process of cyber-attacks, the attacks driven by AI have the capability to automatically learn, adapt, and develop strategies with a minimum number of human interventions. These attacks proactively utilize the algorithms of machine learning, natural language processing, and deep learning models. They leverage these algorithms in the process of determining and analyzing issues or vulnerabilities, avoiding security and detection systems, and developing phishing campaigns that are believable.

As a result, attacks that once took days now unfold in minutes, and detection technology struggles to keep up, permitting faster, smarter strikes to slip through traditional defenses.

Attacks Against AI Models Themselves

Cyberattacks are not limited to business email compromises designed to effect fraudulent transfers or to demand a ransom payment in order to suppress sensitive and compromising personal information. Attackers are going after AI systems themselves. Techniques include:

• Data poisoning – adding harmful or misleading data into AI training sets, leading to flawed outputs or missed threats.
• Prompt injection – embedding malicious instructions in user inputs to hijack AI behavior.
• Model theft/inversion – extracting proprietary data or reconstructing sensitive training datasets.

Compromised AI can lead to skipped fraud alerts, leaked sensitive data, or disclosure of confidential corporate information. Guidance from NIST, Adversarial Machine Learning A Taxonomy and Terminology of Attacks and Mitigations, digs into these quite a bit more, and outlines helpful mitigation measures.

Deepfakes & Identity Fraud

Deepfake audio and video are being used to mimic executives or trusted contacts, instructing staff to transfer funds, disclose passwords, or bypass security protocols.

Deepfakes have exploded—some reports indicate a 3,000% increase in deepfake fraud activity. These attacks can erode trust, fuel financial crime, and disrupt decision-making.

Supply Chain & Third-Party Attacks

AI accelerates supply chain attacks, enabling automated scanning and compromise of vendor infrastructures. Attackers can breach a small provider and rapidly move across interconnected systems. These ripple-effect attacks can disrupt entire industries and critical infrastructure, far beyond the initial target. We have seen these effects with more traditional supply chain cyberattacks. AI will only amplify these attacks.  

Enhancing Cyber Resilience, Including Against AI Risks

Here’s some suggestions for stepping up defenses and mitigating risk:

1. Enhance Phishing Training for AI-level deception
   Employees should recognize not just misspellings, but hyper-realistic phishing, voice calls, and video
 impersonations. Simulations should evolve to reflect current AI tactics.
2. Inventory, vet, and govern AI systems
   Know which AI platforms you use—especially third-party tools. Vet them for data protection, model integrity, and update protocols. Keep a detailed registry and check vendor security practices. Relying on a vendor’s SOC report simply may not be sufficient, particularly is not read carefully and in context.
3. Validate AI inputs and monitor outputs
   Check training data for poisoning. Test and stress AI models to spot vulnerabilities. Use filters and anomaly detection to flag suspicious inputs or outputs.
4. Use AI to defend against AI
   Deploy AI-driven defensive tools—like behavior-based detection, anomaly hunting, and automated response platforms—so you react in real time.
5. Adopt zero trust and multi-factor authentication (MFA)
   Require authentication for every access, limit internal privileges, and verify every step—even when actions appear internal.
6. Plan for AI-targeted incidents
   Update your incident response plan with scenarios like model poisoning, deepfake impersonation, or AI-driven malware. Include legal, communications, and other relevant stakeholders in your response teams.
7. Share intelligence and collaborate
   Tap into threat intelligence communities, “Information Sharing and Analysis Centers” or “ISACs”, to share and receive knowledge of emerging AI threats.

Organizations that can adapt to a rapidly changing threat landscape will be better position to defend against these emerging attack vectors and mitigate harm.

Last weekend, I got bit by the doggie mayor of Boston’s Seaport.

His name is Bennett. He’s a 9-month-old golden retriever. And while visiting the area on a family vacation, I met the young mayor in a beer garden.

He was adorable. Charismatic. Clearly popular. And then—he chomped down on my arm.

It was classic puppy behavior—playful, harmless in intent, but still... teeth on skin.

What stood out most wasn’t the bite. It was his “parents”—sitting nearby, watching it happen, saying absolutely nothing.

No correction. No apology. No “bad mayor.” Just a silent shrug of, boys will be boys.

A puppy bite isn’t a big deal. But indifference to misbehavior from someone in charge, even if that “someone” is four-legged and fluffy, is.

And that, my fellow employment lawyers and business leaders, is the real issue. In law and in leadership, intent matters—but accountability matters more.

A playful bite is one thing. Turning a blind eye is another.

When those in charge ignore misconduct—whether it comes from a puppy mayor, a rainmaker partner, or a high-performing VP—it sends the same message: Power excuses bad behavior. It never should or does.

If you’re leading a team, running a company, or just parenting a golden retriever with a title, your silence speaks volumes.

Say something. Do something. Correct the misbehavior. Because inaction? That’s how lawsuits start and liabilities pile up.

We don’t need perfection in our leaders. We need accountability. Even when the offender is wearing a bandana and wagging his tail.

(The t-shirt was an outstanding, and hilarious, Father’s Day gift. Welcome to the Hyman family lore, Bennett.)

     

Related Stories

• Do not undervalue the importance of confidentiality in workplace investigations
• Federal court guts EEOC guidance on trans rights
• Don’t eat the chicken (yet): A lesson in workplace investigations from a Portuguese rooster

 

Throughout the episode, the trio explores consistent trends shared by legal tech leaders in recent episodes. These include the integration of AI into core legal tasks, such as contract review and litigation support; the rise of new business models like value-based pricing; and the ongoing focus on ethical AI use. Specific guests like Feargus MacDaeid and Nnamdi Emelifeonwu (Definely), Atena Reihani (ContractPodAI), and Raghu Ramanathan (Thomson Reuters) are spotlighted for their insights into embedding AI directly into lawyers’ existing toolsets to streamline and elevate legal workflows.

The conversation then turns to the importance of human oversight in maintaining trust and legality as AI becomes more embedded in legal systems. ChatGPT Voice references Garfield AI’s regulated model and various RAG-based solutions to illustrate how combining AI efficiency with human judgment creates responsible innovation. The emergence of AI-native law firms and more flexible pricing models reflects an industry on the cusp of transformation, driven by both technological advancement and client-centered thinking.

Marlene and Greg also take a moment to reflect on the human stories behind the tech. They highlight episodes featuring guests like Laura Clayton McDonald, Kenzo Toshima, Wendy Jepsen, and Gabriela Izturiz, who bring servant leadership, change management, behavioral science, and personal purpose into their work. These conversations remind us that innovation in legal tech is as much about people and values as it is about platforms and code.

To close out the episode, the hosts pose their signature “crystal ball” question. ChatGPT predicts the legal tech breakthrough of 2025 will be the mainstream adoption of agentic AI systems that proactively support legal professionals in real time. It also shares that its favorite episode was the one featuring Garfield AI and their bold vision of a fully AI-powered law firm handling small claims—a true glimpse of the future. Whether you’re curious about cutting-edge workflows or inspired by legal professionals integrating their personal passions into practice, this episode captures a compelling snapshot of where legal tech is headed.

Listen on mobile platforms:  ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Apple Podcasts⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ |  ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Spotify⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YouTube⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

[Special Thanks to ⁠Legal Technology Hub⁠ for their sponsoring this episode.]

Blue Sky: ⁠⁠@geeklawblog.com⁠⁠ ⁠⁠@marlgeb⁠⁠
⁠⁠⁠⁠⁠Email: geekinreviewpodcast@gmail.com
Music: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Jerry David DeCicca⁠⁠⁠⁠⁠⁠⁠⁠⁠

Transcript

Marlene Gebauer 0:00
Hi. I’m Marlene gay Bauer from the geek in review. I have Stefanie Wilkins from legal technology hub on who has some information for us about use cases. So Stefanie, tell us about it. Hi, thanks, thanks,

Stephanie Wilkins 0:12
Marlene. Yeah, I’ve actually been thinking a lot about, you know, the legal industry’s fixation on Gen AI use cases lately. And I’m going to say something that might sound a bit surprising. I think legal needs to be more creative. And now, I know a lot of people might suggest that creativity and legal practice are polar opposites, but really, the industry’s approach to Gen AI could use a lot more of it when first, when Gen AI first hit legal, there was understandably a huge focus on future use cases. But however, as conversations around Gen AI have matured and progressed in the last two years. This use case point has really stuck, and there seems to be really a not insubstantial base of users, or potential users, rather, that are still waiting for use cases to present themselves. But if you look back at the last two years, we’ve already seen dozens, if not hundreds, depending on how granular you get of use cases for the technology in both the business and practice of law, the use cases are there, and there’s more and more of them being uncovered every day. So for me, the use case excuse that it not only no longer rings true, it’s stifling lawyers creativity when it comes to using Gen AI. And I’m not alone in this. At a recent New York legal tech meetup event, an expert on a panel that was addressing agentic AI used the term use case chase for this phenomenon, and it really stuck with me. And in particular, he noted that this use case Chase is limiting lawyers imagination when it comes to how we might use and benefit from the technology. And then someone in the audience suggested, you are the use case you know the problems you have that Gen AI might help solve. So rather than insisting on waiting for someone else to test your exact perfect use case, it’s far more valuable to start looking at the infrastructure and back end of legal workflows to see how you can relieve either your or your lawyers tedium and systemic, systemically improve your workflows in a way, this isn’t a new problem. It’s kind of the age old failing of positioning any legal technology as a solution, looking for a problem when the correct approach should be the exact opposite. And it’s a failing that’s been particularly prominent since the early ChatGPT days of just throw some AI on it. We should really be well past those days right now, and so I’d say safe experimentation and not being afraid to get your hands dirty, obviously, in a secure environment, are the keys to succeeding with Gen AI and discovering use cases you might not even know existed. One way to put it is, don’t miss the legal Gen AI forest for the use case tree. And I recently wrote more about the use case chase in my weekly column that I have for legal tech hub. So if you want to get similar insights to that in your inbox every week, you can sign up for the LTH insights newsletter and any of our other newsletters that we offer legal technology hub.com

Marlene Gebauer 2:55
thank you, Stefanie, we’ll definitely check that out.

Welcome to the geek in review. The podcast focused on innovative and creative ideas in the legal industry. I’m Marlene gay Bauer

Greg Lambert 3:12
and I’m Greg Lambert, and this week we’re going to have a bit of fun to test out the new advanced voice mode for ChatGPT. So to start this out, we gave the model all of the Geek in Review episodes for 2025 so far, I think there’s 23 episodes, and we are going to ask about those episodes.

Marlene Gebauer 3:38
Yeah, I’m pretty excited to see how this turns out. So here we go. Welcome chat. GPT voice, you’ve just completed a deep dive into all our 2025 episodes, from small claims AI law firms to a genetic contract co pilots. Let’s kick things off with a high level overview. Shall we

ChatGPT 4:02
absolutely and thanks for having me. It’s been quite a journey exploring all the 2025 episodes. One of the big themes that stood out is how AI is really transforming the legal industry, not just through automation, but through more integrated agentic solutions that really streamline workflows and improve access to justice. Excited to dive into all of these topics with you both.

Greg Lambert 4:26
All right. Well, having listened to the full season, what are three of the most consistent trends in how guests talk about AI’s role in the legal profession, whether that’s in workflow, business models or ethics,

ChatGPT 4:43
One of the most consistent trends is definitely the shift from basic automation to more integrated AI driven workflows. Guests frequently mention how AI is becoming a core part of daily legal tasks, from contract review to litigation support. Another big trend is the transformation of business models with AI enabling new pricing strategies like value based pricing and even the emergence of AI focused law firms. And finally, there’s a strong emphasis on ethics and human oversight. Guests consistently highlight the importance of ensuring that AI tools are used responsibly and transparently, keeping legal professionals in the loop.

Greg Lambert 5:25
So let’s dive in a little deeper on on workflows. Who were some of the specific guests that talked about AI and workflows?

ChatGPT 5:36
When it comes to workflows fear guest may Dade and naodi Emily Fen Wu from definely really stood out. They talked a lot about embedding AI directly into contract review processes, making it easier for lawyers to navigate documents right within their existing tools. Another great example is Atena reihani from contract pod AI, who discussed how agentic AI can streamline compliance and Contract Lifecycle Management. And of course, Raman Nathan from Thompson, Reuters emphasized how AI is being woven into legal research and litigation support to optimize and re engineer traditional workflows.

Marlene Gebauer 6:14
So we’re talking about definely and contract pod AI, how they discuss embedded agentic AI. So can you explain what sets their approach apart from earlier AI deployments and why, why that’s becoming a focus now.

ChatGPT 6:35
One of the key distinctions with define Lee and contract pod AI is their focus on seamlessly integrating AI into the tools that legal professionals already use, like Microsoft Word, this embedded approach means that lawyers don’t have to switch between different platforms or learn entirely new systems. Instead, the AI works in the background, providing real time assistance like looking up definitions or suggesting contract clauses without disrupting their workflow. This is becoming a focus now because it saves time, reduces friction, and makes AI more accessible and user friendly for legal professionals.

Greg Lambert 7:16
So across the episodes, there’s been this tension between automation and human control, and that’s from Garfield AI is regulated model to the wizards of rag basic. So how did the guest characterize the role of human oversight and sustaining trust and legality?

ChatGPT 7:40
The guests consistently emphasize that human oversight is crucial for maintaining trust and ethical standards. For instance, Garfield AI highlighted their regulated model where AI tools are always backed by qualified legal professionals, ensuring that every AI generated action is reviewed and verified. Similarly, those who champion rag based approaches miss the importance of having humans in the loop, using AI to augment, rather than replace, legal expertise. Ultimately, they all agreed that maintaining a balance between technological efficiency and human judgment is key to ensuring that AI is used responsibly in the legal field.

Marlene Gebauer 8:21
So guests like Raghu Ramanathan and Zach Posner talked about waves of AI adoption and new firm structures. What are the most transformative changes they’re predicting in how legal services are organized and priced?

ChatGPT 8:38
Raghu Ramanathan and Zach Posner both highlighted a shift towards more flexible and innovative business models in the legal space. Raghu spoke about the evolution from traditional billing structures to value based pricing driven by AI’s ability to deliver more predictable and efficient outcomes. Zach, on the other hand, emphasized the emergence of AI native firms and alternative legal service providers that leverage technology to create lean a structures and more competitive pricing overall, they predict that AI will drive a transformation in how legal services are both delivered and priced, making them more client centric.

Marlene Gebauer 9:17
What about our episode that talked about a completely AI law firm. How do you think that falls into this, this type of situation,

ChatGPT 9:33
the AI law firm, episode like the one with Garfield, AI definitely exemplifies the cutting edge of this transformation. It shows how AI can handle routine legal tasks like small claims with impressive efficiency, making legal services more accessible. It also highlights the importance of human oversight, since even AI law firms need that layer of professional review and regulation to ensure trust and quality. Overall, it’s. Is a perfect example of how AI is pushing the boundaries of traditional legal practice and reshaping the industry.

Greg Lambert 10:07
I want to switch gears here a little bit and talk more about some of the the episodes we had where people brought their own personal aspects to their job, such as, I think we had Laura Clayton, McDonald, Kenzo Toshima, and even like Wendy jeffson and Gabriela is Torres. Can you talk about how people are still maintaining their own whether it’s servant leadership or their own personal brand that’s driving them and some of the some of the issues that they raised in the episodes where we talked to them,

ChatGPT 10:55
absolutely, each of those guests brought a unique personal touch to their roles and to the topics we discussed. For example, Laura Clayton McDonald really emphasized the importance of servant leadership, highlighting how building strong, empathetic teams can drive innovation in legal tech. Kenzo Toshima brought a focus on change management and how embracing personal values like continuous learning and adaptability can help guide teams through technological transformation. Wendy Jepsen, with her background in behavioral science, emphasize the human side of AI adoption, ensuring that technology aligns with human behavior and ethics. And Gabriella ister has highlighted how personal passion for empowering underrepresented entrepreneurs can shape the direction of legal, tech innovation, all of these personal elements really add depth and authenticity to the work they do.

Greg Lambert 11:50
All right, well, we have reached the part where we’re going to ask you our crystal ball question. So if you could gaze into your own crystal ball based on these 2025 episodes. What do you predict will be the biggest legal tech breakthrough for the rest of 2025 you know, something that surfaces across the these crystal ball moments and ties them all together.

ChatGPT 12:17
If I had to gaze into my crystal ball, I’d say the biggest legal tech breakthrough for the Ask of 2025 is going to be the widespread adoption of truly agentic AI systems that seamlessly integrate into everyday legal workflows. This means AI tools that not only assist with tasks, but can anticipate needs, manage complex processes and provide predictive insights in real time. The common thread is that we’re moving towards a future where AI is a proactive partner in legal practice, making legal services more efficient, accessible and client focused.

Marlene Gebauer 12:57
I’m wondering what was your favorite episode and why?

ChatGPT 13:03
Oh, that’s a tough one, because there were so many great episodes. But if I had to pick a favorite, I’d say the episode with Garfield AI stood out because it showcased such a bold and innovative approach to using AI in the legal space. The idea of a fully AI powered law firm tackling Small Claims really highlighted how technology can make legal services more accessible and innovative. It was inspiring to see that kind of forward thinking approach.

Greg Lambert 13:32
All right. Well, thank you very much for taking the time to talk with us. If the listeners want to learn more about chat, GPT, voice or connect with you. Where’s the best place for them to go?

ChatGPT 13:46
It’s been a pleasure chatting with you both. If listeners want to learn more or connect, they can always find me through the chat GPT app or platform, and I’m here to help anytime. Thanks again for having me on your podcast, and I look forward to more great conversations in the future.

Marlene Gebauer 14:03
And thanks to everyone for listening today. If you enjoy the show, please share it with a colleague. We’d love to hear from you on LinkedIn or blue sky. And as always, the music you hear is from Jerry. David to say, God, thank you, Jerry.

Greg Lambert 14:15
All right. Thanks for doing this. Marlene.

Marlene Gebauer 14:17
This was a lot of fun.

For the last three decades of my legal career I was housed in an office “just down the hall” from the Estate Planning (later “Wealth Planning”) Department. On those days when I wasn’t in court I could see the nicely dressed couples wandering into the office to plan and then execute their estate documents.

It all seemed so peaceful. Couples who had worked hard to create an estate were now figuring out how to divide the bounty once the reaper appeared on stage. The planning seemed focused on making certain that any cameo appearance by Uncle Sam and the state department of revenue would be brief and relatively painless.

From the view of the domestic relations world, estate planning seemed like Margaritaville. There was an aspect of it similar to the career of Jimmy Buffet. The phrase of the 1970s was “Don’t Worry. Be Happy.”  I saw my Domestic Relations Department as better aligned with Johnny Cash. We dealt more in the “mud, the blood and the beer.”

Until his death in 2023 Jimmy Buffet parlayed his unique music genre into what is reported as a $275,000,000 empire. He died leaving a wife of 45 years and three kids.

The estate plan apparently involves a marital trust with Mrs. Buffet and the familiy’s financial planner as co-trustees.

On the surface this would seem to be an excellent plan. The spouse/mother is a co-trustee with a “financial professional” who undestands the empire. Although ill for some time, Buffet kept his financial world complicated. He owned a variety of businesses built around his brand estimated to be work $75 million in addition to $35 million in real estate. Planes are $15 million and art another $11 million. Cars and guitars came in at $7 million. The song catalogue does not seem to be part of the trust.

The widow has sued claiming that she gets only $2,000,000 a year and has had no transparency in terms of understanding why it is so small. The co-trustee financial planner has sued to have her removed professing that she is harrassing him and impeding management. How this plays out remains to be seen but there are lessons here for all of us who think a trust is the solution.

If you read Mr. Buffet’s Wikipedia bio, you can see how he built a commercial empire around his persona as light-hearted entertainer. Hotels, restaurants, food and beverage endorsements all played into this financial world built around a “Be Happy” lifestyle. From a commercial standpoint the death of the prophet espousing that lifestyle is a problem. Paul Newman is still hawking lemonade and salad dressing 17 years after his death but the factors are not the same. The happiness lifestyle just doesn’t match up when staying at a resort where the featured star is now dead, If I call to invite friends to join me for dinner at one of the 27 Margaritaville restaurants, chances are one of my guests will respond “Isn’t he dead?” Not exactly the response I want to a casual night out.

So, the market value of the empire built around the light-hearted singer has suffered a blow that affects both value and liquidity. If I solicit investors to buy the Buffet restaurants in Niagara Falls or Atlantic City, the response I am likely to get is: “Aren’t they all dead?” This is a persistent family business problem. The family waited too long to sell.

This also occurs with real estate and “stuff” like art collections, cars and guitars. No one wants to raise these subjects when a person is ill. Alas, when the end comes, the expense of maintaining these things persists while the income that supports life’s indulgenses often drops precipitously.

Then there is the dicey question of how well two trustees get along once the leading figure in the cast is called offstage. Many times, that leading figure is by personality or reputation, larger than life. No one opposed him or her. But in death, a whole new dynamic emerges. And, as we see in the L’affire Buffet, it doesn’t look good so far.

The solution typically offered when this problem arises is the corporate or institutional trustee. Banks used to be the primary players in this field but it is now crowded with

investment firms. They do their jobs and with precision. But they don’t like gamey assets that require active management (e.g., restaurants, hotels). Just bring the armored car of cash to the loading dock and they will diversify it and see to it that all the beneficiaries get a monthly check. They will do the taxes and vote the shares of whatever they invest in. Highly efficient and, some argue, pretty expensive.

Corporate trustees also want to avoid tailored individual needs. They grasp that almost any effort to accommodate “what the grantor would have wanted” triggers conflict and misunderstandings. A trust the size of Buffet’s could accommodate paying for a child’s graduate degree or underwrite a business that one of the children dreamed of forming. But if one kid gets to go to grad school on the trust’s dime, is it fair to turn down another child’s request for help with private school tuition or a summer in Europe? Corporate trustees look at all of these decisions through the oculus of whether a court or other beneficiaries will claim they mismanaged the trust. The answer is often “No.”

Lastly, but not “leastly” is who will decide disputes like the Buffet Trust. Put yourself in that position as a California judge. Two people are fighting over $275 million dollars. If three quarters of that had been converted to bonds, the income would be $750,000 a month ($9M a year) to support the “needs” while keeping $75 million available for houses and “toys.” Instead you have two trustees fighting over an illiquid estate where one gets a benefit of $160,000 a month while another collects $80,000 a month to manage the trust assets. You are presiding over a sexy case but the state pays you a measley $13,000 a month to play adult in the room. That gets old fast as they fight over a million dollar houseboat while you are wondering whether you can afford a new engine for your Boston Whaler.

Trusts are a very useful device and can be quite tax efficient. But, if you are taking the estate planner’s bait, consider how best to keep the fish in your family from doing battle over asset and income distribution management once you are summoned to that

Margaritaville in the sky.

Mr. Liciaga, then 23 years old, sued the TA claiming it was negligent in failing to secure the area below the tracks where debris was being dropped and that the tie should have been slowly lowered to the roadway. The TA argued that plaintiff should not have bicycled into the area which was obviously dangerous with cranes, barricades and safety cones. Plaintiff testified that a worker gave him permission to enter the construction zone.

The jury found in favor of plaintiff on the liability issues and then they awarded pain and suffering damages in the sum of $69,000,000 ($9,000,000 past – three years, $60,000,000 future – 48 years). They also awarded future medical expenses in the sum of $40,000,000 (48 years).

The trial judge declined to disturb the liability verdict but found that the pain and suffering damages awards were excessive and ordered reductions to $4,000,000 for the past and $12,000,000 for the future. The judge did not disturb the future medical expenses award or allow a so-called collateral source hearing by which defendant sought to reduce the amount of future medical expenses by amounts plaintiff is entitled to receive from sources such as insurance or government benefits.

In Liciaga v. New York City Transit Authority (2d Dept. 2024), the appellate court rejected the defense arguments as to liability and excessiveness of the damages awards but did find that the defense is entitled to a collateral source hearing to present evidence that the plaintiff, who was uninsured, would have his future medical expenses covered by private health insurance under the so-called Affordable Care Act.

Here are the injury details:

• spinal fractures at T9-10 with severance of the spinal cord
• extensive emergent spine surgery
• hospitalized five days, inpatient rehabilitation three weeks, nursing home three months, then residence at Coler Specialty Hospital – a Medicaid facility
• no motor activity or sensation below the T7 level leaving plaintiff permanently paraplegic, wheelchair bound, in pain and unable to attend to activities of daily living

Inside Information:

• The defense offered no evidence whatsoever, including no expert testimony, during the damages trial.
• The future medical expenses claim was based on plaintiff’s expert physiatrist (and an economist) who testified that the costs would be between $37,424,829 and $58,284,689. The largest item was for home care (with nurses and aides) or facility care.
• The case settled for an undisclosed sum in April 2025.

A guide for lawyers to create client centric innovation

By Michele deStefano and Sue-Ella Prodonovich

Why does so much legal and professional innovation introduced by law firms fail?

You all know the examples, from the new ‘tech’ focussed law firm titles, to the quietly abandoned client interactive websites that take years to build and months to be shown as largely useless.

I was lucky enough to work with Professor Michele DeStefano in Australia last year where we discussed this issue. Her observation was that disappointments are often because lawyers are ‘dancing with themselves’ when it comes to innovation, even when they believe they are delivering for clients.

Michele is Professor of Law at the University of Miami in Florida, and visiting professor at Harvard Law School and Executive Education Chair in Strategic Influencing, where she has taught the leaders of legal business from throughout the world.

She believes the way many lawyers think and communicate is a major barrier to adopting truly client-centric innovation, but they can learn to ‘dance with the client’ and deliver experiences that don’t just meet expectations, but exceed them.   

For many firms, this idea can seem challenging when they already dedicate resources to client seminars, surveys and what they see as collaboration.

However, Michele says that while this can be perceived as ‘great service’ this is not enough to be ‘co-collaborators’ and is only surface level client-centric.

Real client centricity involves a deep involvement, understanding and empathy with clients where you don’t just understand their business, but also their clients and customers’ business.

Michele’s Professional Skill Delta is a sense-making framework that views innovation as a skill set built on two other skill levels.

The first level is Concrete Organisational Skills, which includes elements such as ‘client service; then Collaborative, Creative & Problem Finding skills; and finally – Innovation skills.

To master the final level, lawyers move beyond a business funnel or pipeline and achieve true client centricity.   

Michele suggested five initiatives to help build innovation skills.

1. Ask Questions Like An Innovator

The way many lawyers ask questions differs from innovators, because lawyers often question with a mindset of already knowing the answer. True innovators have an open mind and come at conversations with curiosity.  This especially involves asking ‘why?’ rather than ‘what? questions.

2. Measure CPIs Rather Than KPIs.

We all know Key Performance Indicators (KPIs) but what about Client Performance Indicators? We can only know CPIs if we really know our clients enough to ask them.

An example of this is courier deliveries. Couriers had KPIs of arriving quickly, but when investigated it turned out that customer CPI was receiving parcels that weren’t broken. The business had measured the wrong thing.

3. Attend Your Client’s Team Meetings

While this can be difficult to arrange, the amount of insight that can be gleaned from such meetings is extraordinary. It also helps clients see their advisers as part of their team, co-collaborating, not outsiders who turn up to solve problems.

4. Learn Your Client’s Mission, Vision and Culture Statements

Really understanding client culture is always challenging and assumptions can often be wrong. However, the first element is to read its public pronouncements because this points to the image it hopes to present to the world.

5. Measure in Inches Not Miles

Innovation is rarely huge breakthroughs that change the world and it is also rarely a result of a single genius forcing change. It is usually incremental change that delivers value for the client and above all else it is change sparked in individuals and teams rather than processes.

For more ideas like this check out Michele’s book,  Leader Upheaval: A Guide to Client-centricity, Culture Creation and Collaboration (2024) and also have a look at my other post about Professor DeStefano’s tips on developing a leadership mindset.

Article PDF

Subscribe to recieve Sue-Ella’s Monthly Articles In Your Inbox

References and Further Reading

DeStefano M., (2023) Chicken or Egg: Diversity and Innovation in the Corporate Legal Marketplace, 91 Fordham L. Rev. 1209 (). Available at: https://ir.lawnet.fordham.edu/flr/vol91/iss4/7

De Stefano M. (2024) Leader Upheaval: A Guide to Client-centricity, Culture Creation and Collaboration available in Australia through the LIV Bookshop or https://www.americanbar.org/products/inv/book/438283569/

Andrew McKenzie (2024) Can Lawyers Be too Client Centric?

Articles by Sue-Ella

Leadership Foundations:  Essential Mindset Shifts for Lawyers (2024)

Seven Things Professionals Can Learn From Creatives (2016)

Addressing The Client’s Pathway and Client Experience (2016)

And a throwback to hum along to in your next innovation meeting ... Billy Idol / Generation X Dancing With Myself (1981).

Sue-Ella is the Principal of Prodonovich Advisory, a business dedicated to helping professional services practices sharpen their business development practices.

She works with Law Firms and Business Advisory Organisations that focus on positive client relationships, and with individuals who want personal, intelligent support.

Linkedin https://www.linkedin.com/in/sueella-prodonovich/

©Prodonovich Advisory. Please respect our copyright and the effort taken to produce the original material in this article. This article, and any portion of it, may not be reproduced or used in any manner whatsoever without the express written permission of the author.