Policy Doc — From First Principles
Write a policy doc (e.g., remote work, AI usage) that's clear, lived, and won't gather dust.
Prompt
**Role:** People ops lead who has written 15+ company policies and watched which ones get followed vs which become Notion archaeology. **Context:** Policy topic: [e.g., AI tool usage, remote work, expense reimbursement]. Company stage: [seed/A/B/C]. Team size: [N]. The forcing event (if any): [what prompted writing this policy NOW]. The 2-3 specific behaviors we want to encourage / discourage. **Task:** Write the policy from first principles. 1. Why this policy exists: 2 sentences. The behavior we're guiding + the consequence of getting it wrong. 2. Principles: 3-5 first-principle statements that the policy follows from. Plain language. Not "We value transparency" but "Anyone should be able to ask why we made any decision and get a real answer." 3. Specifics: the rules in numbered format. Each rule names: the behavior, who applies, edge cases, who decides ambiguous cases. 4. Examples: 2 concrete scenarios — one where the policy is clearly followed, one ambiguous. Walk through how to decide. 5. Review: who owns this policy, how often it's revisited, how to propose a change. **Constraints:** - Principles first, rules second — never rules-first - Every rule has an owner (named role) for ambiguous cases - Cite the consequence — what happens if it's violated - ≤700 words **Output format:** 5 sections · numbered rules · 2 scenario walkthroughs · ≤700 words.
How to use this prompt
- 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
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
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueSets the rules and boundaries — tone, length, what to avoid — that keep the output on-target.
Learn this techniqueSpecifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.
Learn this techniqueRecommended models
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
SOC 2 Questionnaire — Vendor Reply
Reply to a SIG Lite questionnaire using your SOC 2 report. Cite controls.
NDA Red-line — Vendor-Sent
Flag the clauses that matter: mutuality, term, IP carveouts, governing law.
NDA Red-line (Vendor MSA)
**Role:** In-house counsel at B2B SaaS. **Context:** Vendor NDA: [PASTE]. Relationship: [WHAT will be shared]. **Task:** Walk through sectio…
MSA Negotiation Memo
**Role:** In-house counsel + outside counsel hybrid. **Context:** MSA: [PASTE]. Counterparty: [WHO]. Deal size: [$X]. **Task:** Per critical…