AI + THE LAW

BY RYAN O'NEIL (OAKLAND)

It is hard to watch a television program or read a newspaper without being confronted with talk of AI. Whether it’s Jeopardy contestants battling Watson or Matthew McConaughey and Woody Harrelson lamenting a misplaced dining reservation due to a lack of AI resources – AI is everywhere.
 
What is Artificial Intelligence
 
AI may be difficult to conceptualize and even more difficult to define. Generally speaking, AI is “technology that enables computers and machines to simulate human learning, comprehension, problem solving, decision making, creativity, and autonomy.” There are different types of AI programs that presently exist. The form of AI most commonly used by individuals is a Generative Pre-Trained Transformer (GPT). These models allow computers to break down large quantities of information in a relatively short period of time. They also allow these systems to perform functions based upon user inputs.

​Types of AI Programs
 
There are a variety of AI programs available for individual use. These include the following:
• ChatGPT
• Google Gemini
• Claude
• Synthesia
• DALL·E 3
 
AI + Reliable Legal Information
 
While the capabilities of AI are truly astonishing, it should be noted that AI can still cause mistakes. Many AI programs, including ChatGPT, put this disclaimer directly into the search results:

AI programs have been known to "hallucinate" facts, including fake cases which were subsequently cited in legal briefs. For example, “Michael Cohen, former U.S. president Donald Trump’s onetime personal lawyer and fixer, says he unwittingly passed along to his attorney bogus artificial intelligence-generated legal case citations he got online before they were submitted to a judge.”

Use by Pro Se Litigants

With access to AI programs becoming more widespread, filings from pro se litigants using AI are becoming more prevalent. Here are a few ways you might identify that a legal pleading was generated using AI:

• The writing contains lists, and the first sentence is in bold.
• Excessive use of “jargon” or “buzzwords.”
• Placeholder text appearing in the body of the text (i.e., INSERT NAME HERE).

There are online AI detection tools that claim to be able to identify AI-generated text, but no program can offer 100% certainty. I have personally written paragraphs of my own only to have AI detection software claim that all or a portion of the text was written by AI. Exceptionally polished and non-personal pro se pleadings might also be an indicator of AI-generated text. Attorneys should ensure that the pleadings being submitted are not purporting to cite binding legal authority when, in fact, they may be offering hallucinated cases.

Ways in Which Lawyers Can Effectively Use AI

Given all of the potential pitfalls identified so far, there is no question that AI is a tremendous resource that is going to revolutionize the practice of law. When asking AI to perform a function, you want to ensure that your prompt (the direction you are giving to the program) is as specific as possible. Avoid asking AI to “write a legal brief on divorce law in Michigan.” Instead, give the program as much detail as possible to ensure that your output is on-point and relevant to the case.

Examples of effective AI prompts include the following:

• Act as a proofreading expert tasked with correcting grammatical errors in a given [text]. Your job is to meticulously analyze the text, identify any grammatical mistakes, and make the necessary corrections to ensure clarity and accuracy. This includes checking for proper sentence structure, punctuation, verb tense consistency, and correct usage of words. Additionally, provide suggestions to enhance the readability and flow of the text. The goal is to polish the text so that it communicates its message effectively and professionally.
• Act as a proofreading expert. Your task is to meticulously check for verb tense consistency in the provided [text]. Ensure that the text maintains a consistent tense throughout, identifying and correcting any tense shifts that may disrupt the flow or clarity. Pay attention to the context to determine the appropriate tense. Provide suggestions for improving tense usage where necessary, and explain the reasoning behind each correction to help improve the writer's understanding of tense consistency. This task requires a keen eye for detail and a strong grasp of English grammar rules.
• Act as a proofreading expert. Your task is to improve the clarity and conciseness of a given [text]. Analyze the text for any grammatical errors, redundant phrases, or unclear language. Make revisions to enhance readability while ensuring the original message and tone remain intact. Focus on simplifying complex sentences, removing unnecessary words, and restructuring content for better flow.
• Create a list of direct examination questions for a witness expected to testify about [specific event or topic]. Ensure questions are clear, concise, and designed to elicit detailed responses.
• Generate a list of questions for opposing parties in discovery for [specific legal issue]. Please ensure the questions are clear and concise.

Make sure that your prompt clearly identifies the task you are seeking to have accomplished by the AI program you are using. For example, if you are trying to land the plane on an article about AI and the law, your prompt might look something like this:

write a closing paragraph for a legal article talking about the uses and pitfalls of using artificial intelligence in the practice of family law

For which, ChatGPT would respond with the following:
​
As artificial intelligence continues to reshape the legal landscape, its role in family law presents both promising opportunities and serious challenges. AI can enhance efficiency, assist in case management, and offer predictive insights that may benefit both clients and practitioners. However, overreliance on these tools risks undermining the nuance, empathy, and human judgment that are essential in resolving deeply personal matters such as custody, divorce, and support. Family law attorneys must approach AI with cautious optimism—leveraging its benefits while remaining vigilant about its limitations, biases, and ethical implications. Ultimately, technology should serve as a tool to support, not replace, the professional judgment and compassion that define effective family law advocacy.