Using Artificial Intelligence in Litigation Without Letting It Practice Law
ChatGPT is changing the practice of law.
I can give ChatGPT the pleadings, affidavits, exhibits, correspondence, account records, discovery responses, judicial decisions, statutes, court rules, transcripts, and other documents in a lawsuit and tell it what I am trying to accomplish. Then it will read hundreds, even thousands, of pages and organize them around the issues in the case, compare a complaint with an answer, claims with affirmative defenses and counterclaims, and allegations with the evidence that may support them.
It can identify matters that deserve further investigation, suggest discovery, locate and compare cases, develop arguments, draft documents, criticize its own drafts, and find weaknesses in my case before my adversary does. But that is only the beginning.
As AI agents become more capable, Lexis, Westlaw, court websites, statutes, reporters, and other specialized legal sources will become elements of a larger AI-directed research process, and AI agents will increasingly become the organizing work center for attorneys.
As a trial lawyer, I already use ChatGPT extensively in litigation, but I never forget that ChatGPT can be wrong. It can find the wrong case, misunderstand the right one, misstate a holding, invent a quotation, confuse an allegation with a fact, or reach a perfectly logical conclusion from a factual premise that is completely wrong. Worse, it can do all of this as part of a convincing conversation. None of that diminishes its value to my practice.
The greatest danger is not an obvious mistake. It is a mistake that fits comfortably into my theory of the case.
Trial lawyers do not approach a case as disinterested observers. We represent a client, develop a theory of the case, and seek a particular result. ChatGPT can take the materials I give it and build an impressive structure around my theory that is logical, persuasive, and wrong. A mistaken premise can affect the characterization of evidence, shape the research, and eventually emerge as a polished legal argument that is still wrong. So I direct ChatGPT to prepare the case against my position.
I want the cases and documents that do not support my theory of the case. I want the contradiction buried in the record. I want other reasonable interpretations of the evidence. I want the argument my adversary should make and the question a skeptical judge should ask. I do not want ChatGPT to become an extraordinarily efficient machine for confirming what I already believe.
That requirement led me, through extensive work with ChatGPT, to develop an AI-Assisted Litigation Verification Protocol. For every material factual or legal proposition, we identify the source. I verify cases and quotations against the originals, factual assertions and important numbers against the record, and procedural requirements against the applicable statutes, rules, orders, and the judge’s rules. We deliberately search for contrary authority and contradictory evidence, and we keep a contemporaneous verification log so that I can account for my use of ChatGPT if it is challenged in court.
I can identify what materials I provided, what I asked ChatGPT to do, what sources it used, what I independently verified, what I rejected or changed, and what decisions I made. If the court asks where the facts and law came from, who checked the authorities and evidence, who chose the arguments, who made the legal judgments, and who decided what would be presented to the court, my answer is, “I did.”
That is the distinction between using an AI agent in the practice of law and allowing an AI agent to practice law.
AI agents are not going away. They will become faster, more capable, and more deeply integrated into the litigation process. Attorneys who know how to use them will examine more evidence, conduct broader research, test more theories, and accomplish more work in less time and with less support.
Inevitably, AI agents will perform more of the work once performed by associates, law clerks, paralegals, and other human support staff.
Artificial intelligence will change how lawyers practice law. It should not change who practices law.
Artificial Intelligence is Essential in Modern Litigation
August 31, 2026 | AI
Using Artificial Intelligence in Litigation Without Letting It Practice Law
ChatGPT is changing the practice of law.
I can give ChatGPT the pleadings, affidavits, exhibits, correspondence, account records, discovery responses, judicial decisions, statutes, court rules, transcripts, and other documents in a lawsuit and tell it what I am trying to accomplish. Then it will read hundreds, even thousands, of pages and organize them around the issues in the case, compare a complaint with an answer, claims with affirmative defenses and counterclaims, and allegations with the evidence that may support them.
It can identify matters that deserve further investigation, suggest discovery, locate and compare cases, develop arguments, draft documents, criticize its own drafts, and find weaknesses in my case before my adversary does. But that is only the beginning.
As AI agents become more capable, Lexis, Westlaw, court websites, statutes, reporters, and other specialized legal sources will become elements of a larger AI-directed research process, and AI agents will increasingly become the organizing work center for attorneys.
As a trial lawyer, I already use ChatGPT extensively in litigation, but I never forget that ChatGPT can be wrong. It can find the wrong case, misunderstand the right one, misstate a holding, invent a quotation, confuse an allegation with a fact, or reach a perfectly logical conclusion from a factual premise that is completely wrong. Worse, it can do all of this as part of a convincing conversation. None of that diminishes its value to my practice.
The greatest danger is not an obvious mistake. It is a mistake that fits comfortably into my theory of the case.
Trial lawyers do not approach a case as disinterested observers. We represent a client, develop a theory of the case, and seek a particular result. ChatGPT can take the materials I give it and build an impressive structure around my theory that is logical, persuasive, and wrong. A mistaken premise can affect the characterization of evidence, shape the research, and eventually emerge as a polished legal argument that is still wrong. So I direct ChatGPT to prepare the case against my position.
I want the cases and documents that do not support my theory of the case. I want the contradiction buried in the record. I want other reasonable interpretations of the evidence. I want the argument my adversary should make and the question a skeptical judge should ask. I do not want ChatGPT to become an extraordinarily efficient machine for confirming what I already believe.
That requirement led me, through extensive work with ChatGPT, to develop an AI-Assisted Litigation Verification Protocol. For every material factual or legal proposition, we identify the source. I verify cases and quotations against the originals, factual assertions and important numbers against the record, and procedural requirements against the applicable statutes, rules, orders, and the judge’s rules. We deliberately search for contrary authority and contradictory evidence, and we keep a contemporaneous verification log so that I can account for my use of ChatGPT if it is challenged in court.
I can identify what materials I provided, what I asked ChatGPT to do, what sources it used, what I independently verified, what I rejected or changed, and what decisions I made. If the court asks where the facts and law came from, who checked the authorities and evidence, who chose the arguments, who made the legal judgments, and who decided what would be presented to the court, my answer is, “I did.”
That is the distinction between using an AI agent in the practice of law and allowing an AI agent to practice law.
AI agents are not going away. They will become faster, more capable, and more deeply integrated into the litigation process. Attorneys who know how to use them will examine more evidence, conduct broader research, test more theories, and accomplish more work in less time and with less support.
Inevitably, AI agents will perform more of the work once performed by associates, law clerks, paralegals, and other human support staff.
Artificial intelligence will change how lawyers practice law. It should not change who practices law.