Skip to main content
Think of a legal prompt like instructions you’d give to a junior associate. The clearer and more structured your instructions, the better the work you’ll get back.

The Core Framework

Every good legal prompt has five main parts:
1. Task Definition → What you want done
2. Context Anchoring → Background information needed
3. Constraints → Boundaries and limitations  
4. Output Format → How results should appear
5. Audience → Who will use this output

1. Task Definition

Your opening instruction needs to be specific about what action you want and what you’re looking for. Vague requests lead to inconsistent results. Too Vague: “Review this agreement” Better: “Identify and redline any unlimited liability provisions in this vendor agreement” Start with action verbs (identify, redline, extract, compare, draft) and be specific about scope. Instead of “financial terms,” say “payment terms only.” When possible, explain why it matters: “…that could expose us to uncapped risk.”

2. Context Anchoring

The AI needs background information to make good decisions. Think of this as the setup you’d give a new team member before they review a contract.

Essential Context Elements

  1. Party Position: Who are you in this deal?
  • “I am the vendor reviewing a customer’s MSA”
  • “We are the covered entity under this BAA”
  1. Document Type: What kind of agreement is this?
  • “SaaS subscription agreement”
  • “Mutual NDA for partnership discussions”
  1. Industry & Regulations: What special rules apply?
  • “Healthcare company subject to HIPAA”
  • “Government contractor under FAR/DFARS”
  1. Leverage: What’s your negotiating position?
  • “Low leverage - competitive RFP situation”
  • “High leverage - we’re their sole supplier”
The more context you provide, the better the AI can calibrate its suggestions to your actual situation.

3. Constraints

Constraints are the boundaries you set to prevent over-editing or off-target responses. Think of these as the guidelines you’d give to keep someone from going overboard with changes.
  1. Edit Style: How should changes be made?
  • “Use qualifiers rather than deletions”
  • “Add new provisions as separate sections”
  1. Scope Limits: What should be ignored?
  • “Focus only on payment and liability provisions”
  • “Ignore stylistic or formatting differences”
  1. Quantity Controls: How many changes are appropriate?
  • “Limit to 5 substantive changes maximum”
  • “Flag all issues but only redline critical ones”

4. Output Format

Tell the AI exactly how you want the results presented. Different tasks need different formats. For Analysis:
  • “Create a table with columns: Clause | Risk Level | Issue | Recommendation”
  • “Provide numbered list with clause references”
For Redlines:
  • “Show changes with explanatory comments”
  • “Include fallback language for each edit”
For Communication:
  • “Draft email to counterparty explaining our position”
  • “Create executive summary in bullet points”

5. Audience

Who will use this output? The audience shapes both tone and detail level.
  • Legal team: Can handle technical legal language and detailed analysis
  • Executives: Need business impact and risk summary, not legal theory
  • Counterparty: Requires professional tone with justified positions
  • Business teams: Need plain English explanations of practical implications

Putting It All Together

Here’s a complete prompt using all five elements:
[TASK]
Review and redline this MSA focusing on provisions that create uncapped liability.

[CONTEXT]
- Party: We are the vendor (SaaS provider)
- Counterparty: Large bank
- Leverage: Low - competitive situation
- Regulatory: SOC 2 compliance required

[CONSTRAINTS]
- Maximum 5 material changes
- Use qualifiers over deletions
- Focus on liability and indemnity only

[OUTPUT]
Provide redlines with brief explanatory comments.

[AUDIENCE]
Initial review by legal team.

Advanced Techniques

Multi-Step Prompting: Break complex tasks into steps. First identify issues, then assess risk, then draft fallbacks, then add comments. Negative Prompting: Explicitly state what you DON’T want. “Do NOT change payment terms or add new obligations for counterparty.” Role-Based Perspective: Add a viewpoint to shape analysis. “As conservative inside counsel, flag any provision that could require board approval.”

Common Mistakes and Fixes

ProblemSolution
Getting different results each time you run the same promptAdd more specific constraints and clearer context
AI makes too many changes or wrong types of changesUse negative prompting to exclude what you don’t want
Output is too technical or too basic for your audienceAlways specify who will use the output
Results don’t match your negotiating positionInclude leverage and relationship context

Quick Reference

When writing any prompt, check that you’ve covered:
  • ✓ Clear task with action verb
  • ✓ Your party position and document type
  • ✓ Any relevant regulations or industry norms
  • ✓ Your leverage level
  • ✓ How many changes to make
  • ✓ What format you want
  • ✓ Who will read this
A well-structured prompt takes 2 minutes to write but saves 20 minutes of revision.