#23 Legal Prompt Engineering and AI Training in Law Firms

This week, I share the second half of the Legal Design School’s Legal Prompt Engineering Course and an article about law firms doing AI training for Summer Associates.

AI will change the world, but how will it change M&A? I want to focus on AI’s impact on M&A in this newsletter. I am not an expert on either M&A or AI, but I want to learn about both topics and how they intersect. I thought there might be others in my situation (or people who are experts in one field or the other) who would find information on M&A and AI helpful in their careers, so I created this newsletter to track and share what I learn.

Legal Prompt Engineering

This week, I share some takeaways from the second half of the Legal Design Schools course on legal prompt engineering plus a LinkedIn post on prompting. You can find my takeaways from the first half of the course, here.

Prompting Strategies

Roleplaying

Roleplaying is a prompting method where the user tells the AI model to provide an output as if it were a certain person. An M&A example would be: “You are an M&A lawyer and an expert in Delaware corporate law, [insert M&A question].”

These prompts tend to focus the AI model on a particular area, improving the accuracy of outputs.

Priming

Priming refers to the prompting strategy where the user provides the AI model context for its task. The course gives the example of copying and pasting a statute into a chatbot and asking the chatbot to interpret the statute.

The course identifies a helpful strategy for priming. The user splits up the prompt into three sections: context, prompt/instructions, and additional details. This strategy is useful for users to organize their thoughts while prompting and allows the AI to clearly identify the instructions.

For GPT plus users, you can create custom chatbots using a similar prompt style in the GPT creation studio.

In an M&A context, let’s say a user wishes to negotiate an agreement based on a particular precedent in the firm’s system. The user could copy and paste the precedent and the agreement being negotiated and ask the model to make changes to the negotiated agreement based on the precedent. Of course, the changes would have to be clearly laid out for the model in this case, but you get the point.

One limitation on this pointed out in the course is the context limits of today’s models. ChatGPT only allows for 15 pages of text at a time, which is good for most things, but likely insufficient for complex M&A agreements.

Fine-tuning

Finetuning refers to training an AI model on your own data. Choosing the data that the AI is trained on allows the creator to craft the expertise of the model. In the M&A context, this would likely mean training an AI model on your firm’s precedent database so that the model could “act like a lawyer.”

There are several positive aspects of this technique. The model can run locally on a firm’s servers or cloud infrastructure, lessening the risk of exposing privileged information. Additionally, the model can be customized to always provide accurate and relevant responses by fine-tuning the model’s response to several questions.

The downside is that this technique is advanced and time-consuming, so it may not be feasible for most people.

Summarization Prompt

I stumbled across an example of an advanced prompt on frequent AI commentator, Sam Burrett’s LinkedIn page. He’s a great follow for those interested in using AI in law practice!

Here is the prompt, copied and pasted from his post linked above:

Read the attached article in detail. Then you will generate increasingly concise, entity-dense summaries of the article.

Repeat the following 2 steps 5 times.

Step 1. Identify 1-3 informative entities (";" delimited) from the article which are missing from the previously generated summary.

Step 2. Write a new, denser summary of identical length which covers every entity and detail from the previous summary plus the missing entities.

A missing entity is:

- relevant to the main story,

- specific yet concise (5 words or fewer),

- novel (not in the previous summary),

- faithful (present in the article),

- anywhere (can be located anywhere in the article).

Guidelines:

- The first summary should be long (6-7 sentences, 100+ words) yet highly non-specific, containing little information beyond the entities marked as missing. Use overly verbose language and fillers (e.g., "this article discusses").

- Make every word count: rewrite the previous summary to improve flow and make space for additional entities.

- Make space with fusion, compression, and removal of uninformative phrases like "the article discusses".

- The summaries should become highly dense and concise yet self-contained, i.e., easily understood without the article.

- Missing entities can appear anywhere in the new summary.

- Never drop entities from the previous summary. If space cannot be made, add fewer new entities.

Remember, use the exact same number of words for each summary.

Take a deep breath and proceed step by step

Sam states that this prompt is good for gaining background knowledge on a subject before diving in further. I am going to try it on the news story below.

Bloomberg Law Article on Summer Associate AI Training

Here is a link to a Bloomberg Law story on BigLaw firms giving Summer Associates AI training.

Here is the response I got using the summarization prompt, above:

Summary 1:

This article discusses the integration of artificial intelligence (AI) into the legal profession, with a focus on the training of summer associates in the use of generative AI. Law firms such as K&L Gates, Dechert, and Orrick Herrington & Sutcliffe are incorporating this technology into their training programs, teaching associates how to use research and chatbot tools. The article suggests that while AI will automate many tasks, it will also open up new lines of legal practice. However, most firms are still in an experimentation phase with this technology. The article also highlights the importance of lawyers being tech-savvy and the potential marketing benefits for firms that adopt this technology.

Missing Entities:

• Brendan McDonnell; K&L Gates partner

• Alex Su; Latitude Legal’s chief revenue officer

• AltaClaro; tech learning platform

Summary 2:

Incorporating generative AI into legal training, law firms K&L Gates, Dechert, and Orrick Herrington & Sutcliffe are teaching summer associates to use research and chatbot tools. Brendan McDonnell, a K&L Gates partner, suggests AI will not replace lawyers but will change the profession, automating tasks and opening new practice areas. However, Alex Su, chief revenue officer at Latitude Legal, notes that most firms are still experimenting with this technology. The article emphasizes the necessity for tech-savvy lawyers and the marketing advantages for firms adopting AI, with training provided through tech learning platform AltaClaro.

I’d say that is pretty good!

Anyway, I think it is a good idea for firms to give Summer Associates a taste of AI, even if the firms do not regularly use it in their practice.

About me

My name is Parker Lawter, and I am a law student pursuing a career as an M&A lawyer. I am in my last semester of law school, and with some extra time on my hands, I decided to create this newsletter. I hope it is informative and helpful to anyone who reads it! I am not an expert at either M&A or AI, but I am actively pursuing knowledge in both areas, and this newsletter is a part of that pursuit. I hope you’ll join me!

Follow me on LinkedIn: www.linkedin.com/in/parker-w-lawter-58a6a41b

All views expressed are my own!