Skip to main content
Legalai.guide

Legal AI Workflow Template Library

Copy-ready prompts, Codex briefs, Claude instructions, and review gates for supervised legal AI work.

Legal AI Workflow Template Library

Use these templates as starting points. Replace bracketed fields, remove client identifiers unless your environment is approved for them, and keep the lawyer review gate.

Templates are not legal advice. They are supervision patterns for educational and operational legal AI work.

Universal Matter-Safe Prompt

Role:
You are assisting a legal professional with a supervised workflow.

Task:
[Describe the document, issue, or operational goal.]

Allowed sources:
[List source documents, folders, URLs, or repositories.]

Rules:
- Do not invent facts, citations, parties, dates, or defined terms.
- If a point is unclear, mark it "Needs lawyer review."
- Keep jurisdiction assumptions explicit.
- Do not provide final legal advice.
- Preserve privilege and confidentiality.

Output:
[Table, checklist, memo outline, redline issues list, code diff, or test plan.]

Review gate:
End with the specific items a lawyer must verify before use.

Contract Review Triage

Review the provided agreement for [issue list].
Return a table with clause, source section, extracted language, risk flag, why it matters, and reviewer action.
Use only the agreement text and the playbook below.
Do not say a clause is acceptable or unacceptable. Use "review priority" labels only.

Acceptance checks:

  • Each flag links to source text.
  • Missing clauses are labeled as missing, not assumed.
  • Recommendations are phrased as reviewer actions.
  • The output avoids universal market-standard claims unless the playbook supplies them.

Litigation Timeline Builder

Build a chronology from the provided materials.
Return date, event, source document, quoted support, uncertainty, and follow-up question.
Do not infer dates from file names unless the document text supports them.
Flag contradictions and missing source support.

Acceptance checks:

  • Every event has source support.
  • Uncertain dates stay uncertain.
  • Contradictions are preserved for lawyer review.
  • The timeline does not rank legal significance unless requested by a lawyer.

Due Diligence Issue List

Review the approved data-room documents for [transaction topic].
Create an issue list with document, clause, extracted text, business/legal concern, and diligence follow-up.
Use "potential issue" language.
Do not draft final advice or negotiation positions.

Acceptance checks:

  • Extracted text can be checked against the source.
  • Each issue has a follow-up question.
  • The output separates business concern from legal conclusion.
Goal:
Implement [workflow feature] for [legal user].

Repository rules:
- Read existing schemas and loaders first.
- Preserve routes, locale prefixes, anchors, and source URLs.
- Do not weaken tests, source policies, or release gates.

Legal rules:
- This is educational workflow support, not legal advice.
- Product-sensitive claims need official sources.
- Add a human review checkpoint where the workflow affects legal output.

Verification:
Run [narrow command] and report the exact result.

Acceptance checks:

  • Changed files are scoped.
  • The implementation uses existing data loaders and UI patterns.
  • Legal workflow copy includes limits and review responsibility.
  • Verification covers the changed surface.
You support [team] on [workflow].
Use only approved materials added to this project.
Ask for clarification when facts, jurisdiction, or authority are missing.
Return structured outputs that separate source facts from analysis.
Never present generated text as final legal advice.
End each response with "Reviewer checks" for the responsible lawyer.

Acceptance checks:

  • The project instructions name the workflow and user.
  • Source limits are explicit.
  • The output format is predictable.
  • Review checks are mandatory.

Tool Selection Prompt

Given this legal workflow, recommend whether it belongs in Claude, ChatGPT/OpenAI, Codex, a legal research platform, or no AI workflow.
Assess: input sensitivity, need for legal authority, need for code changes, repeatability, review burden, and failure impact.
Return a recommendation, rejected options, and required safeguards.

Use this before buying or building. The answer should help decide the workflow surface, not crown a universal winner.

Next Steps

On this page