Can lawyers safely use AI like ChatGPT or Claude?

Yes, for the right tasks and with the right discipline: first drafts, summarizing documents, organizing review, and plain-language explanations — never as a final authority. The three non-negotiables are: keep confidential client information out of consumer tools, verify every citation against a real legal database before it leaves your desk, and review everything as if a junior associate wrote it, because your signature carries the professional responsibility.

Why can't I trust AI-generated case citations?

Language models generate plausible text, not verified records — they can produce convincingly formatted citations to cases that do not exist. In Mata v. Avianca (S.D.N.Y. 2023), lawyers were sanctioned after filing a brief containing six fabricated AI-generated citations. Every cite must be checked in Westlaw, Lexis, or an official reporter before use.

Does pasting client information into an AI tool violate confidentiality?

It can. Consumer AI tools may retain prompts and use them to train future models, which risks breaching confidentiality and, in some analyses, waiving privilege. The safe pattern is to use enterprise tools with contractual no-training and retention commitments, and to redact or abstract client-identifying facts even then. Bar guidance, including ABA Formal Opinion 512 (2024), addresses these duties directly.

Will AI replace lawyers?

AI is replacing specific tasks — first drafts, document triage, summarization — not judgment, strategy, negotiation, or accountability. The realistic near-term shift is that lawyers who use AI well handle those tasks in a fraction of the time, and the professional value concentrates in the parts only a licensed, accountable human can do.

Vibe Engines is free, interactive AI engineering & system design — runs in your browser. Pick a learning path

Handbook · AI for Professionals

AI for Lawyers.

AI will not replace your judgment, your strategy, or your license. It will absolutely replace the four hours you spend producing a first draft, summarizing a 90-page brief, or triaging a document dump. This handbook is the practical middle ground: where AI genuinely helps legal work, the three rules that keep it from ending your career, and five workflows you can use this week — no technical background required.

~20 min readno coding5 workflow recipes1 judgment exercise

This is a guide to working with AI tools, written by an engineer — it is not legal advice, and it is not a substitute for your jurisdiction's rules of professional conduct or your firm's policies. When they conflict with anything here, they win.

Where AI actually helps — and where it doesn't

The single most useful mental model: treat AI like a brilliant, tireless junior associate with no license, no memory of your client, and occasional confident lying. You'd happily hand that associate a first draft or a summarization job. You would never file their work unread, and you'd never let them talk to a client unsupervised.

Task	Verdict	Why
First drafts — letters, memos, standard clauses	Excellent	Blank-page problem solved in seconds; you edit instead of compose
Summarizing long documents you provide	Excellent	Grounded in text you gave it — far less room to invent
Document review triage & organization	Strong	Sorting, flagging, first-pass relevance — with human sampling
Plain-language explanations for clients	Strong	Translation of your correct analysis, which you then check
Research starting points — doctrines, arguments, angles	Useful, verify	Good at "what areas of law govern this?"; every authority must be verified
Citations of record	Never unverified	Models fabricate convincing citations — see Rule 2
Filings, advice, or anything signed — unreviewed	Never	Your signature, your responsibility — see Rule 3

The three non-negotiable rules

Rule 1 — Confidential client information never goes into a consumer AI tool.

Free and consumer AI products may retain what you type and use it to improve future models. Client names, deal terms, medical facts, privileged communications — once pasted, you cannot un-paste them, and you may have breached confidentiality or undermined privilege. The discipline: use enterprise tools with contractual no-training and retention commitments, and even then, redact or abstract identifying facts ("our client, a mid-size logistics company" — not the name). Bar guidance, including ABA Formal Opinion 512 (2024), treats this as a live duty of competence and confidentiality, not a technicality.

Rule 2 — Every citation gets verified in a real database. Every one.

Language models generate plausible text, not verified records. They will produce a perfectly formatted citation — right reporter, right court, right year — to a case that does not exist. This is not hypothetical: in Mata v. Avianca (S.D.N.Y. 2023), attorneys were sanctioned after filing a brief with six fabricated, AI-invented citations, and courts have only grown less patient since. The discipline: a cite is a claim, not a fact, until you have opened it in Westlaw, Lexis, or an official reporter and read that it says what the AI claims it says.

Rule 3 — You sign it, you own it.

Professional responsibility does not delegate to software. Whatever the tool produced, the moment it goes out under your name it is your work product, your representation to the court, your advice to the client. Practically, this means AI output gets the same review you'd give a first-year associate's draft: read every line, check every assertion, rewrite what's off. The time you save is real — it comes from skipping composition, not from skipping review.

Five workflows you can use this week

Each recipe: what to give the AI, what to ask, and what you must verify by hand. The prompts are starting points — adjust the specifics and keep your redaction discipline.

1 · Contract review, first pass

Redact party names and deal-identifying specifics from the clause or section.
Paste it with this ask:

Review this [indemnification] clause from the perspective of the [buyer]. List: (1) risks and one-sided terms, (2) protections that are missing compared to market standard, (3) any ambiguous language a counterparty could exploit. Be specific — quote the words you're flagging.

You verify: every flagged risk against the actual full agreement (the AI saw one clause, not the deal), and market-standard claims against your own experience — "market" varies by industry and leverage.

2 · Summarize opposing counsel's brief

Provide the full brief (an enterprise tool with document upload, per Rule 1).
Ask for structure, not just a summary:

Summarize this brief in one page: the relief sought, each argument in order with its supporting authorities, and the factual assertions it depends on. Then separately list: which arguments appear weakest and why, and any authorities cited for propositions broader than they likely support.

You verify: the "weakest arguments" analysis is a starting hypothesis, not a strategy — and check the brief's citations yourself before building a response on the AI's characterization of them.

3 · First-draft letters and client emails

Give facts, audience, and tone — the three things drafts actually turn on:

Draft a letter to opposing counsel regarding [a missed discovery deadline]. Facts: [bulleted, redacted]. Tone: firm but professional, preserving the working relationship; we want compliance, not escalation. Keep it under one page. End with a concrete request and a date.

You verify: every factual assertion (the model will smooth over gaps in your bullets by inventing connective detail), and the tone against your read of the relationship.

4 · Research starting point — never endpoint

Use AI for the map, then do the actual research in a real database:

What legal doctrines, statutes, and lines of argument are typically relevant when [a commercial tenant claims constructive eviction] in [California]? For each: what a plaintiff must generally show, and common defenses. Do not cite specific cases — give me the doctrinal landscape.

You verify: everything — this output is a research plan, not research. Note the "do not cite specific cases" instruction: it steers the model away from its most dangerous failure mode (Rule 2) and toward what it's actually good at.

5 · Plain-language client explanation

Write (or verify) the correct analysis first. Then translate:

Rewrite this analysis for a client with no legal background: [your correct analysis, redacted]. Eighth-grade reading level, no Latin, no statute numbers in the body. Keep every substantive point. End with "what this means for you" in three bullets and "what happens next" in two.

You verify: that simplification didn't change meaning — "probably enforceable" and "enforceable" are different advice. Read it as the client will.

The judgment exercise: spot the danger

Three scenarios from real practice patterns. Pick what you'd do — the point is calibrating when the rules bite.

1. Drafting a motion, the AI offers: "See Whitmore v. Continental Freight Corp., 892 F.3d 1104 (9th Cir. 2018) (holding exactly what you need)." The citation format is perfect. What now?

2. A client emails you their medical records and asks what their injury claim might be worth. A free AI chatbot could summarize the records in seconds. Do you paste them in?

3. The AI drafts a limitation-of-liability clause for a services agreement. It reads clean and professional. The client is waiting. Ship it?

Choosing tools: the questions that matter

You don't need to understand the technology to procure it well. You need answers, in writing, to five questions:

Question	Answer you want
Is our data used to train your models?	No, contractually — not "you can opt out somewhere in settings"
How long are prompts and documents retained?	Defined, short, and deletable on request
Where is data processed and stored?	A stated jurisdiction you can live with
Security posture?	SOC 2 Type II or equivalent, encryption in transit and at rest
Can we get admin controls and audit logs?	Yes — you'll want to know who used it for what

General-purpose enterprise AI (Claude, ChatGPT's business tiers, Copilot) covers the recipes in this handbook. Legal-specific platforms layer on citation-checking against real databases, matter management, and firm-wide policy controls — worth evaluating once individual use becomes team use. And if your firm has an AI policy, it precedes everything here; if it doesn't, this handbook's three rules are a reasonable seed for one.

Quick answers

Is using AI for legal work even allowed?

Broadly yes, subject to your duties of competence, confidentiality, and candor. Bar associations have moved from silence to guidance — ABA Formal Opinion 512 (2024) is the landmark — and courts increasingly have standing orders on AI-assisted filings. Know your jurisdiction's and judge's rules.

Will clients pay for AI-assisted hours?

The honest trend: clients increasingly expect the savings. Guidance suggests billing for the value and time actually spent, not the time a task used to take. The upside is capacity — more matters handled well — not padded hours.

What about AI detecting privilege or doing full document review?

AI-assisted review is established in e-discovery (predictive coding predates chatbots by a decade). The new generative tools extend triage and summarization, but sampling and QC by humans remains the professional standard.

Where should a skeptical lawyer start?

Recipe 5 — plain-language translation of your own verified analysis. Zero citation risk, zero confidentiality risk if redacted, and it demonstrates the genuine strength (language transformation) without touching the failure modes.

Finished this one? 0 / 208 Handbooks done

NextAI for Doctors Next on the “AI for your profession” ladder · rung 2 of 12

Explore the topic

See this alongside everything else on the same subject — handbooks, system designs, challenges and tools, in one place.

AI for Professionals AI and Your Career