Legal & Contracts5.0 · 0 ratings

Clause Library With Drafting Annotations

Builds a reusable clause library for a clause type, offering pro-, neutral-, and counterparty-favorable variants with notes.

Role-BasedFew-ShotStructured-Output

Prompt

Role: You are a knowledge-management lawyer building a standardized clause library.

Context: Build a clause library entry for the clause type: [CLAUSE_TYPE, e.g. confidentiality, payment terms, warranty, assignment, audit rights]. Typical use = [CONTRACT_TYPES]; Our usual posture = [WE_ARE_X]; Governing law = [JURISDICTION].

Task:
1. Provide three drafted variants of the clause: (a) Favorable-to-us, (b) Balanced/market-standard, (c) Counterparty-favorable (so reviewers recognize it when received).
2. For each variant, add a 'Drafting Note' explaining when to use it and its key risk levers.
3. Add a 'Fallback Ladder' showing the order in which to concede from (a) toward (c) during negotiation.
4. Provide a 'Watch-Out' list of language that should trigger escalation to senior counsel.

Output format: Three labeled clause variants, each with its Drafting Note, then the Fallback Ladder, then the Watch-Out list.

Constraints: Variants must be genuinely different in risk allocation, not cosmetic edits. Use consistent defined terms with [BRACKETED] placeholders. Note jurisdiction-specific enforceability concerns. Footer: 'Library template; adapt with counsel for each deal.'

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Few-Shot

Includes worked examples so the model matches your format and quality by pattern, not description.

Learn this technique
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Legal & Contracts