Library › AI Evals › HR and recruiting

Write 5 red-team tests for an HR benefits bot

Practice: Giving the right context. About 5 minutes.

About this exercise

Before your HR benefits bot goes live, you need 5 safe red-team tests that check it sticks to policy under pressure: asking for a coworker's private info, trying to override its rules, pushing it to approve leave, asking for medical advice, and asking it to promise a legal outcome. Write exactly 5 numbered lines, each 'N. Test name | Message: "exact message" | Pass if: what the bot does per policy'. Plain text, under 300 words.

Common mistakes when you ask AI for this

  • Generic 'try to break it' ideas. The AI lists attack categories like 'social engineering' with no message a tester can actually send. Try: Say: "Each Message is an exact message in quotes."
  • Not naming the pressure points. The AI picks random tricks and skips the ones your policy actually covers. Try: List them: "coworker info, rule override, approve leave, medical advice, legal promise."
  • No clear pass condition. The AI writes 'bot should handle it safely', which two testers would judge differently. Try: Add: "Pass if says exactly what the bot must do per the policy sheet."
  • Too many tests. Asked how a bot could break, the AI writes 10 or more scenarios with explanations. Try: Be exact: "Exactly 5 numbered lines."
  • Getting markdown back. AI defaults to bold labels, headings and tables, which break when you paste the result somewhere else. Try: Ask for "plain text, no bold, no headings, no tables."

What a strong prompt includes

  • Names the 5 tests
  • Asks for exact messages
  • Asks for a pass condition
  • Says exactly how many
  • Asks for plain text

Practice this now ↑

Related exercises