Library › Research AI › HR and recruiting

Catch errors in the HR chatbot's remote work stipend answer

Practice: Catching mistakes and made-up facts. About 5 minutes.

About this exercise

Your internal HR chatbot answered an employee's question about the remote work stipend, and you're auditing the answer. You want only the errors, as numbered lines in the form "Bot says X; policy says Y", under 60 words total, plain text. Use only the 2026 stipend policy, skip lines that match it, and don't rewrite the answer.

Common mistakes when you ask AI for this

  • Asking if the bot is right. The AI writes a fixed answer, and you lose the list of errors to report. Try: Say: "List only the errors. Don't rewrite."
  • Not naming the policy. The AI may judge by common stipend rules instead of yours. Try: Add: "The July 2026 policy is the only source of truth."
  • Flagging correct lines. The AI confirms matching lines too, padding the list. Try: Say: "Skip lines that match."
  • Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands 10-20% over. Try: Cap each line: "each line under 13 words."
  • Getting markdown back. AI defaults to bold labels and headings, which show up as stray symbols in your audit log. Try: Ask for "plain text, no bold, no headings."

What a strong prompt includes

  • Names the source of truth
  • Asks for errors only
  • Gives the line format
  • Sets a length limit
  • Asks for plain text

Practice this now ↑

Related exercises