What if genAI’s main value to lawyers was in supporting legal training? That’s a view held by Codex, the legal technology group within Stanford Law School, which along with the Flatiron Law Group, have co-launched a genAI-driven M&A negotiation simulator to provide commercial legal training as part of an ongoing collaboration.
Before we jump into the product, you can learn more about Codex’s approach to tapping LLMs to help with legal training here – when Artificial Lawyer spoke to Dr. Megan Ma, Associate Director at CodeX ahead of this June’s Legal Innovators California conference. In the video we talk more broadly about how AI can help support legal education.
In fact, as Codex states in its announcement – made on Hugging Face’s site – they explain: ‘One of the complexities of the legal industry is that much of the work and value-add is implicit. It is measured by experience and the specific know-how of the client and industry-base. We argue that the greatest value-add for legal practitioners is not captured in the explicit knowledge (e.g. case law, contracts, legislation and regulation, etc.).
‘Rather, it is the latent methodology behind information synthesis, issue-spotting, judgment and eloquence of argumentation that makes the quality of legal work highly diverse and varied.
‘Accordingly, how legal professionals describe the nuances of their practice, capture and abstract their lessons from experience (i.e. wisdom) distinguish and set apart the next generation of legal experts. Our motivation is to elevate the starting skills of all lawyers, equipping future and current practitioners with tools that will continuously harness and perfect their craft.’
So, that’s the background. Here is the product.
In collaboration with the Flatiron Law Group they have worked towards developing ‘the first platform that would allow legal professionals to ‘pilot’ (i.e., simulate) negotiations at varying starting positions, extent of buyer/seller leverage, complexity of legal issue at play, and the impact on the deal’.
The sample module that is openly available for experiment consists of an equity sale between a fictional buyer and seller. The buyer is interested in a seller that has a proprietary SaaS solution for small, medium-sized business retailers. The fictional buyer believes this acquisition could help extend its market presence and technological capabilities. The lawyer-user is representing the buyer. The AI agent (robo-counsel) is representing the seller.
As the lawyer-user, the first task is to enter the name and select the practice level (i.e., junior, senior, or partner). Depending on the level selected, the fact patterns will adjust accordingly. So, if a lawyer-user selected Junior, the ‘main focus’ will be ‘Warranties and Representations’. If a lawyer-user selected Senior, the ‘main focus’ will continue to be Representations and Warranties but will add a new risk factor of a ‘Cybersecurity Incident,’ and will include a description of those new facts.
Depending on the level selected, there may be sample prompts available and/or hints. Finally, when the lawyer-user has determined that they have reached a strong deal in representation of the buyer, the negotiation will conclude, and the chat dialogue may be saved.
The dialogue can then be downloaded and shared as a document to the lawyer-user’s mentoring partner and other colleagues for internal training purposes.
And of course, one can then do it again and again, to improve the process and keep learning.
–
So, there you go. There’s more to it and you can see the project and test it here.
Overall, it’s a great idea. GenAI – as seen in this example – can certainly become a valuable aid in the teaching of legal skills, especially commercial skills which may not always be taught at law school. (And although legal wisdom is more valuable than just having access to case law, using genAI to change the business of law and deliver huge productivity gains via the automation of work tasks, probably is going to be the biggest area of improvement for the legal world.)
We are a long way from replacing law professors, but, this approach could certainly be applied more broadly to help law students get through key stages of their study more rapidly and without having to engage a human tutor all of the time. And clearly it’s of use to law firms that need to train young lawyers with little commercial experience.
Will be interesting to see where this goes next and how many law firms – and maybe universities – onboard this tool and approach.