07/07/2026
In March of 2023, I wrote my first public post about artificial intelligence and the practice of law. At that time, the loudest question seemed to be whether AI would replace lawyers. My answer then, and my answer now, is that AI will not replace real lawyers doing real work for real people. The practice of law requires far more than the ability to generate words in a legally adjacent format. It requires judgment, context, strategy, ethics, lived experience, the ability to understand people and systems, and the ability to take messy, emotional, inconsistent, incomplete facts and organize them into something useful, persuasive, and true.
That said, after nearly four years of working with AI tools in my own practice, I am also convinced that lawyers who learn how to properly command these tools are going to have a serious and growing advantage. I do not mean asking a chatbot to “write a motion” and hoping for the best. I mean learning how to use different platforms for different purposes, how to structure information so the tool can assist without distorting the work, how to test and challenge the output, how to preserve confidentiality and professional judgment, and how to integrate AI into the actual workflow of litigation rather than treating it like a novelty.
The work I have been doing is not about replacing legal analysis. It is about expanding the lawyer’s capacity to manage complexity. In litigation, we are constantly dealing with too much information, too little time, competing narratives, incomplete records, clients who are suffering, frightened, or upset, difficult opposing parties, emergency deadlines, voluminous discovery, and the endless need to convert chaos into usable work product. AI, when properly directed and supervised, can help organize facts, identify patterns, refine arguments, prepare timelines, test themes, improve drafts, and make the lawyer’s own thinking sharper and more efficient.
There are, of course, risks. AI can be confidently wrong. It can flatten nuance. It can invent things. It can misunderstand the assignment in ways that are subtle enough to be dangerous. That is exactly why the lawyer’s role is not diminished by AI; it is heightened. The lawyer has to know what to ask, what to reject, what to verify, what to protect, and where human judgment must remain firmly in control.
That is the space I have been working in for some time now: not AI instead of lawyers, but lawyer-controlled AI as a serious litigation tool. The legal landscape is changing quickly, and I am moving with it — testing platforms, commandeering the tools that actually work, discarding the ones that do not, and building practical systems that improve efficiency, clarity, and results for clients.
I will be sharing more about what this looks like in real practice, because this is no longer a theoretical conversation about the future of law. It is already here. The question is not whether lawyers will use AI. The question is whether they will use it skillfully, ethically, and with enough command of both the technology and the law to make it genuinely useful.
Real lawyers. Real people. Better tools.
