Library › Legal & Compliance AI › Legal teams

Draft a messaging policy from a provided outline

  • For Legal teams
  • You practice Setting limits and rules
  • Time about 5 minutes
  • Level Advanced

About this exercise

Turn the outline into a first-draft policy for Legal to review. Plain text, under 230 words. The first line is exactly: DRAFT FOR LEGAL REVIEW. Then five numbered section headings in the outline's order (for example "1. Purpose"), each followed by one to three plain sentences. Use only what the outline says. Where the outline gives no content, write exactly: [Legal to confirm]. Do not add penalties, deadlines, tool names or references to any law.

Common mistakes when you ask AI for this

  • Penalties invented. The AI adds discipline language. Try: Say: "Where the outline gives no content, write exactly: [Legal to confirm]."
  • Law cited. The AI adds a legal reference from the notes. Try: Say: "Do not reference any law."
  • Extra tools or detail. The AI pads sections with examples. Try: Say: "Use only what the outline says."
  • Headings drift. The AI renames or reorders sections. Try: Say: "Five numbered headings in the outline's order."
  • Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands over it. Try: Cap each part instead, for example: "each line under 15 words."
  • Markdown. The AI bolds words or adds headings. Try: Say: "Plain text, no bold, no headings."

What a strong prompt includes

  • Exact first line
  • Headings in order
  • Placeholder text
  • No penalties or law
  • Outline only

Practice this now ↑

Related exercises