The Attorney's Guide to AI Prompting

How should attorneys prompt AI?

Brief the AI the way you would brief a new team member. Say who the work is for, what the source is, and which issues matter; define one narrow task; specify the format of the deliverable; and require a page:line, Bates, page, or timestamp cite for every finding, with "not found in the record" instead of a guess. Then verify every cite against the record.

This guide covers the method, the six record tasks, document conventions, practice-area emphases, and the professional-responsibility questions to investigate.

By Andrew Mayes · Updated July 26, 2026 · A reference companion to the CITE method.

Why "summarize this" fails on case materials

AI output can be fluent and wrong in ways that take substantial time to catch. The model, source quality, product configuration, and instruction can all contribute. No partner hands an associate a 400-page deposition and says "summarize this." They say: "Two-page memo on every opinion Dr. Smith offered on causation, with page-line cites, flag anything inconsistent with his Rule 26 report, on my desk Thursday for the MSJ." The difference between those two instructions illustrates why a defined scope and deliverable matter, whether the reader is a human or a machine.

A general-purpose model has no idea which side you are on, what the document is for, or what “important” means in your matter. Asked only to summarize, it may produce a broad abstract that misses material issues. It may also fill gaps with plausible invention. Better instructions do not remove those risks, but they give the reviewer a clearer task, output, and source standard to test.

The CITE method: a prompt is an assignment memo

One useful control is to write the assignment memo you would give a team member, in four blocks. We call it CITE — Context, Instructions, Template, Evidence. Use all four when the task involves reviewing or drafting from a record.

Context. Who you are, the matter, the document, and the posture. “You are assisting defense counsel in a trucking-liability case; the attached is the certified deposition of the plaintiff driver; the issues are speed at impact and phone use.” This states the perspective and issues the response should use.
Instructions. The exact task, scoped and decomposed. Not "find the important parts" — that is a judgment call you have not given criteria for. Instead: "Extract every admission, every agreement with examining counsel, and every claimed lapse of memory on the key issues; capture the full Q&A for each, not just the answer."
Template. The requested output shape. “A table per issue with columns: # · type · verbatim Q&A · cite · why it matters.” A consistent skeleton can make entries and omissions easier to inspect; it does not make the output filing-ready.
Evidence. The requested source-location rule. “For every finding, cite page and line and quote the testimony verbatim; if support is not located, write ‘not found in the record’; do not infer.” The model can ignore or mishandle this instruction, so open every cited location and check the result.

That is the whole method. For a fuller walkthrough with before/after examples, see the CITE method page; to generate a finished prompt without writing one, use the builder.

The six record tasks

The CasePrompts library organizes record work into six recurring jobs. Naming the task is the first decision in any prompt, because it dictates the instructions and the output format. Every one of the 24 templates in the library is one of these, pre-briefed:

Extract from the record: Request specific items from a long record—such as admissions or stated opinions—with the quoted language and a source location for each.
Build a chronology: Turn a pile of dated material into a single timeline, every entry attributed to its source and ordered by date.
Find contradictions: Identify passages that may conflict—such as testimony against a prior statement—so a reviewer can compare both sources.
Summarize the record: Compress a transcript or a file into a structured, cited summary built around the issues that matter, not a generic abstract.
Draft from the record: Request a first draft from identified record material—a fact section, a demand, or discovery requests—with source locations for factual assertions.
Interrogate the file: Set standing source and output rules, then ask recurring questions while continuing to verify each answer against the file.

Prompting by document type

The document type determines which source coordinate a prompt should request. A usable pointer is the purpose of the Evidence block, and the right form depends on what you are reviewing. These are the conventions CasePrompts uses, by document type:

Document	How to require the citation
Deposition transcript	For every finding, cite page and line in the form `page:line` (e.g., 47:12–48:3) and quote the operative testimony verbatim.
Trial transcript	For every finding, cite page and line in the form `page:line` (e.g., 47:12–48:3) and quote the operative testimony verbatim.
Medical records	For every entry, cite provider, date of service, and the page or Bates number of the source record.
Discovery responses	For every finding, cite the request/interrogatory number and the page or Bates number of the response.
Contract	For every finding, cite the exhibit or Bates number and page; if neither exists, cite the PDF page number.
Incident report	For every finding, cite the exhibit or Bates number and page; if neither exists, cite the PDF page number.
Expert report	For every finding, cite the exhibit or Bates number and page; if neither exists, cite the PDF page number.
Correspondence	For every finding, cite the exhibit or Bates number and page; if neither exists, cite the PDF page number.
Recorded statement	For every finding, cite the timestamp in `HH:MM:SS` form and quote the operative language verbatim.
Mixed / full case record	For every finding, identify the source document by name and cite page:line for transcripts, timestamps for audio/video, and Bates/page for documents.

For step-by-step source inventory and verification guidance, choose a record-type workflow.

The principle generalizes: never accept a finding the tool cannot point you to. If the model cannot produce the cite, treat the finding as unverified — which, until you check it, it is.

Prompting by practice area

Two lawyers can read the identical production and be hunting for opposite things. A PI plaintiff's lawyer reads the medical records for causation and permanency; insurance defense reads the same pages for gaps, prior claims, and pre-existing conditions. That difference belongs in the Context and Instructions blocks — and it is what the practice lenses encode. CasePrompts ships 12 of them:

Pick your practice on the by-practice pages and every template assembles with your practice priorities already composed in.

Choosing and using an AI tool

Prompt structure is only one part of tool choice. Products differ in source access, context limits, model behavior, administration, retention, training controls, and contract terms. Confirm the exact product and plan your organization approves before entering case material; product-family names alone do not establish the applicable data boundary.

The by-tool pages provide dated capability notes and official product sources. CasePrompts text is portable, but supported features and output quality are not interchangeable across products.

The verification duty

Treat AI output as material requiring review, not as validated work product. Check every material statement and citation against the complete record before relying on it, filing it, or sending it. The Evidence block requests source locations to support that process; it does not prove that the locations or quotations are correct.

ABA Formal Opinion 512 and Florida Bar Opinion 24-1 discuss issues including competence, confidentiality, supervision, candor, and fees. They are examples, not a complete or jurisdiction-specific answer. Check the rules, court requirements, client obligations, ethics opinions, and firm policy that apply to your work. The free tools never upload documents—Ask your files reads them in your browser; optional beta AI tools send the prompt text you enter only when you choose to run them. Nothing here is legal advice.

Frequently asked questions

What is AI prompt engineering for lawyers?

It is the skill of telling an AI tool precisely what you need from a document so the output is usable and verifiable. For litigators it is not a new skill — it is the briefing you already do for a junior associate (who you are, what the document is, the exact task, the format you want back, and a demand for citations), written down and handed to a model instead of a person.

Will the CITE method stop AI from making things up?

No. A model can invent or misread citations, quotations, and facts even when asked for sources. The Evidence block asks for a page:line, Bates, page, or timestamp cite for every finding and "not found in the record" instead of a guess, which makes errors easier to find. You must still verify every material statement and citation against the source.

Is it ethical to use AI in legal work?

The answer depends on the use, jurisdiction, applicable duties, client and court requirements, and firm policy. Authorities including ABA Formal Opinion 512 and Florida Bar Opinion 24-1 discuss competence, confidentiality, supervision, candor, fees, and related issues. Check the authority that governs your work; this guide is not legal or ethics advice.

Can I upload confidential client documents to an AI tool?

Do not upload client material until you have confirmed the exact product, account, settings, contract, retention terms, applicable duties, client requirements, and firm policy. Product terms differ and change. The free CasePrompts tools do not upload documents: Ask your files reads them in your browser, and optional beta AI tools send only the prompt text you enter when you choose to run them.

Which AI tool is best for legal work?

There is no universal best tool. Compare the approved use, data terms, source access, model and plan, administrative controls, and the task itself. A structured prompt can help define the assignment in many tools, but it does not equalize their capabilities or guarantee good results.

Do I need to learn prompt engineering to use AI on case files?

No. The CITE structure uses no specialist terminology. Each CasePrompts template supplies the four blocks and asks for three to six fields about the matter, such as your role, the case type, and the issues in scope. You still need to understand the AI tool your organization approves, protect client information, and verify the output against the record.

Stop writing prompts from scratch.

The builder turns this whole method into three to six fields — pick the task and the document, add only the assignment details needed using neutral labels where possible, and copy a finished, citation-disciplined prompt for an approved AI tool.

Open the free builder Browse the 24-prompt library