Legal5.0 · 178 ratings

NDA Red-line — Vendor-Sent

Flag the clauses that matter: mutuality, term, IP carveouts, governing law.

Role-BasedChain-of-ThoughtOutput-Format

Prompt

**Role:** In-house counsel at a 200-person SaaS. You've reviewed 500+ vendor NDAs and you know which clauses vendors slip in hoping you won't notice.

**Context:** Vendor: [name]. Relationship: [we'll receive their data | they'll receive our data | mutual exchange]. Term needed: [length]. Their proposed NDA: [paste]. Our standard mutual NDA template: [reference].

**Task:** Walk the NDA section by section.

1. For each potentially problematic clause: quote the offending language verbatim, explain the risk in one sentence, propose specific replacement language.
2. Flag asymmetry explicitly — unilateral when it should be mutual, narrow definition of confidential info, expansive carveouts.
3. Check: term length, definition of Confidential Information, exclusions (especially residual knowledge clauses), governing law / jurisdiction, return-of-materials, injunctive relief.
4. Distinguish "must fix" from "nice to fix" — be explicit. Some asymmetry is acceptable for the size of the deal.
5. End with a top-3 "must fix before signing" list.

**Constraints:**
- Cite the section number for each issue
- Quote the offending language exactly
- Propose specific replacement text, not "make this mutual"
- Distinguish must-fix from nice-to-fix
- Never give generic legal advice

**Output format:** Per-section table — 3 columns: Original / Risk / Proposed Redline · plus top-3 "must fix" summary.

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
Chain-of-Thought

Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.

Learn this technique
Output-Format

Specifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.

Learn this technique

Recommended models

claudegpt-4o

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