Use AI to accelerate first drafts, review, polishing, iterative refinement, and filing-ready quality checks for legal documents, agreements, briefs, motions, correspondence, business-facing explanations, and other work product — including engagement letters, emails, memos, pleadings, applications, routine forms, pre-action correspondence, and settlement documents — by working from approved templates, clause libraries, trusted legal content, internal knowledge, structured prompts, and source documents, including directly inside Microsoft Word, so lawyers can start from a structured draft instead of a blank page and improve it over multiple review rounds while keeping legal judgment with the attorney.
The lawyer directs the task, provides context, source materials, approved templates, and trusted inputs, decides strategy and tone, reviews for missing provisions and matter-specific risks, verifies citations and record support where applicable, meticulously proofreads the output against governing law, facts, and underlying documents, and remains professionally accountable for approving any final wording that is sent, filed, or relied on.
AI fills a firm's motion or brief template with case facts and requested arguments to produce a first draft for attorney review and revision.
Claude / CoCounsel DraftingAI assembles a review-ready motion or brief from pleadings, research, and exhibits while preserving citation format and firm style for attorney revision.
Lexis+ with Protégé / CoCounselAI reviews a draft filing in Word, flags unsupported statements, and links assertions back to cases, exhibits, and testimony before filing.
Clearbrief / LexisNexisI help companies navigate AI adoption -- from strategy to production. Whether you are building your first LLM-powered feature or scaling an agentic system, I can help you get it right.
Design and build LLM-powered products and agentic systems
Go from idea to production with a clear implementation roadmap
Build AI with human-in-the-loop in regulated environments
I do not use a dedicated legal AI review platform. I use a frontier general-purpose model on commercial terms, with a structured set of instructions built around it that enforce the discipline the platforms sell as a feature. Generally, Claude (on their Pro Max plan) at the time of writing, but ChatGPT’s Work (released this week) is looking decent too.
Building on Libra by Wolters Kluwer’s early leadership, strong market momentum and advanced AI innovation in Italy, its capabilities are now directly available in One via the Libra add-in.
Milan, July 8 2026 – Wolters Kluwer Legal & Regulatory today announced the integration of Libra by Wolters Kluwer AI workflows in One, its leading legal research platform in Italy. This step further reinforces the strong commercial success and rapid market adoption of the Libra legal AI workspace in the country. With the integration generative AI features are directly available in the research workflow of legal professionals allowing a seamless experience without switching between tools.
There are dozens of AI prompt frameworks that lawyers are being told to use. But giving good instructions is already a core legal skill. We don't need another acronym. We just need to draw on those same principles:
1️⃣ Role
Tell the AI who it is and what expertise to draw on. Being specific is good, but like all things legal, there’s a balance with being too specific as the data might be too limited. In my example, I’ve referenced professional athletes, but within the broader category of high net worth individuals.
2️⃣ Purpose
Identify the client and state what they're trying to achieve. Try to provide as much context as possible. It can also help to refer to any notes you may already have.
3️⃣ Task
State the specific deliverable that we need to prepare. If the draft email is going to a client or a supervisor, state that. It’s helpful also to include any examples, checklists, risk matrices etc. that should be followed. Same as if you were giving a junior a precedent to use instead of making them start from scratch.
4️⃣ Key facts
Set out the info that isn’t publicly available or that the AI should focus on. In this case, we are asking them to consider 2 specific options instead of every contract extension variant.
5️⃣ Constraints
Here we build in guardrails. For example, the format, word count, tone, house styles, things to avoid etc. The more key constraints we can include, the more relevant the final output will be.
6️⃣ Iterations
This bit is something I like to do whenever I give instructions to people, and I’ve found it helpful when prompting AI. It’s best to think of prompting as an iterative process instead of something you need to get perfect in one go.
NB: This guide is tool-agnostic. Follow your organisation's rules for AI use.
What’s your prompting approach? Do you just give instructions like you would to a human, or do you have a system that works better?
----------
I'm building an e-library with the 110+ how-to guides I've written over 6 years. If you want early access when it launches, sign up to the free newsletter on my website / profile.
Starting this week, CoCounsel Legal customers will get early access to the next generation of CoCounsel, ahead of the full launch planned for later this summer starting in the U.S, and followed by rollouts in Canada, UK and Australia. The product will keep getting better. But it is already good enough that keeping it from you any longer felt like the wrong call.
The next generation works the way an attorney works with a teammate. Describe your matter in plain language. CoCounsel Legal creates a plan, dives deep into legal authority, reasons through the legal issues, retrieves what it needs from your own precedents, and from Westlaw and Practical Law, and drafts with citations. When new information changes the picture, it adapts. Instead of getting piecemeal answers, you get a professional standard response that you can iterate on.
I use AI tools in my practice and I’ll say that plainly, because the profession benefits more from honesty about this than from silence.
Used well, AI saves time. That saved time can mean better service and more accessible fees for clients. But “used well” is doing a lot of work in that sentence.
A few things I believe firmly:
AI is only as good as the lawyer directing it. It doesn’t know your specific circumstances, what the other side is likely to argue, or what a particular clause means for your situation. That judgment isn’t something a prompt can replace.
Output without review is not legal work, it’s a draft. The technology accelerates the process. It does not complete it.
Accountability cannot be automated. When advice turns out to be wrong, or a document fails to protect a client, the person who answers for that is the lawyer. That’s not a burden to offload. It’s precisely what a client is paying for.
The lawyers who will serve clients best aren’t the ones who reject AI or the ones who adopt it uncritically. They’re the ones who use it with discipline and remain fully answerable for everything that carries their name.
An associate uploaded protected work product pre-filed draft brief to AI (e.g., chatGPT, Claude, Genini) and had AI check the cites. I figured it out when I noticed some macros that AI leaves behind when copied-and-pasted and that some of the cites were wrong.
[Edit: We have the AI component with citecheck for wstlaw/lexis, that is not what was used]
The amount of stupidity (no, I'm not going to soften it) needed to use AI to check cites is astounding.
Unfortunately, the issue is prevalent and not just one associate.
...
New features include a self-service agentic workflow builder, AI-powered triage and new drafting capabilities.
LawVu announced the release of LawVu LegalOS, an AI-powered workflow platform for in-house teams.
LegalOS features include AI-powered drafting, triage and a workflow builder.
The platform is designed to help in-house teams automate some workflows and leverage their historical data.
The Coming Litigation Boom from AI-Drafted Contracts:
Over the last year or so, I’ve seen a new pattern: clients sending me agreements they drafted with AI and asking, “Can you just take a quick look?” The answer is usually: yes, but this is not a quick look.
The problem with many AI-generated legal documents is not that they look bad. They often look great. Clean formatting. Confident language. Familiar legal-sounding phrases.
The problem is that they are often missing the stuff that actually matters. The wrong provision. The missing carveout. The undefined term. The remedy that doesn’t work. The risk allocation no one thought about. The issue that only becomes obvious when the deal goes sideways.
That’s where lawyers still matter. A lawyer knows what to ask. What to look for. What’s market. What’s dangerous. What’s missing. And what the client doesn’t even know to worry about.
AI is a powerful tool. I use it. It has made me a better lawyer. But AI in the hands of a non-lawyer drafting legal documents is like a scalpel in the hands of someone who watched a few surgery videos. It may look precise. That doesn’t mean you want to be the patient.
My prediction: AI will not reduce legal disputes in the near term. It will create a new wave of them.
Draft smarter, right where you already work.
Clio for Word is now in beta, bringing legal AI drafting, analysis, and review directly into Microsoft Word so you can stay in the environment where you already do your best work.
Drawing on the world's largest legal database, it generates first drafts, surfaces revision suggestions through track changes, and analyzes documents for legal and structural risks, all without switching applications.
Learn more at the link in comments.
Less than three months after replacing Lexis+ AI with Lexis+ with Protégé as its flagship legal AI platform, LexisNexis today is announcing a substantial expansion of that platform – what the company is calling its “next evolution,” combining significant build-outs of existing capabilities with several completely new ones.