#20 Legal Prompt Engineering

This week, I share some takeaways from a course on legal prompt engineering—an essential skill for all lawyers to develop.

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

I recently enrolled in a free online course about legal prompt engineering. The course gives prompting techniques that legal professionals can use to assist in their work.

You can find this course here

Here are my takeaways from the first half of the class:

The first part of the course focuses on how prompting evolved. It states that we’ve moved from the quest for the “right prompt” (I like to call this the “one-and-done” prompt) to understanding how to “converse” with chatbots. Conversational prompting may be necessary to get the best results because AI is a prediction machine. For instance, to generate unique contract language, continuously refining a prompt can help the model “predict” the unique language.

Here are a few examples of “one-and-done” prompts that may assist in legal tasks:

• Simplification: “Make this text simpler—so that a law student can understand what is being conveyed.”

• Consistency in Style: “Make sure that my style is consistent throughout this text: [insert text].”

• Textual Comparison: “Compare these two texts and present differences in tabular format.” This is known in the M&A world as “redlining,” but AI promises to enhance the basic redlining software currently used in most law firms. More on that in a future post.

Conversational strategies are useful because the user can tailor the model’s response to extract a better output. These include:

• Interrupting: Continuously prompt the model to improve the output, such as “don’t use emojis,” “make it more readable,” or “use shorter sentences.” It is interesting to see how the output evolves with each prompt.

• Rating the Output: This involves asking AI to rate its output and identify and improve on the weak points.

• Reverse Priming: Start by giving the model the context of the task, like “I am drafting an NDA.” Then ask the model to provide all relevant questions that should be considered when completing the task. This helps the user either craft a prompt to extract a relevant output or it can act as a sounding board for considerations when drafting the relevant document.

Prompt engineering will be an essential skill for all people in the near future. I think it is important to start thinking about best AI practices so that we can use AI more effectively. “One-and-done” prompts are good but they limit the model’s output. Conversational prompts can help extract the desired result with little complications—just like conversing with another human. Perhaps the most important thing to remember is that prompting is a skill that can be developed through practice. So get prompting!

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!