Library › Legal & Compliance AI › Compliance and risk

Apply a rating matrix to audit findings and show the math

  • For Compliance and risk
  • You practice Setting limits and rules
  • Time about 5 minutes
  • Level Advanced

About this exercise

Rate four findings using the matrix. Write a prompt for a markdown table Finding | Math | Proposed rating, rows A to D, under 130 words, no bold or headings. The Math cell shows the calculation like "7 / 50 = 14%" and any payment check. Ratings are only High, Medium or Low. The last line must read exactly: Ratings are proposals for the audit lead to confirm.

Common mistakes when you ask AI for this

  • Boundary case missed. AI rates B as Low because 10% sounds low. Try: Say: "10% counts as Medium (both ends included)."
  • Payment override missed. AI rates D Low because only 1 in 40 had an exception. Try: Say: "Any exception on a payment above $50,000 makes it High."
  • Presenting as final. AI states ratings as decided. Try: Say: "Last line exactly: Ratings are proposals for the audit lead to confirm."
  • Trusting the AI to count words. AI is bad at counting and usually runs long, so a vague "keep it short" lands over the limit. Try: Cap each part instead of the total, for example "each line under 15 words".
  • Getting markdown back. AI adds bold ratings and headings by default. Try: Say "no bold, no headings".

What a strong prompt includes

  • Table columns
  • Shows math
  • Boundary rule
  • Closing line
  • Allowed ratings

Practice this now ↑

Related exercises