Library › People & HR AI › HR and recruiting
Fix leading survey questions into neutral ones
- For HR and recruiting
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Intermediate
About this exercise
Review the five draft survey questions and return a table with the header # | Problem | Neutral question. Problem is exactly one of: Leading, Double-barreled, Loaded, Fine. Neutral question rewrites it in under 18 words with a 5-point agree-disagree scale in mind, or "No change" for Fine. Keep each question about one topic. Do not add new questions. Plain text, no bold.
Common mistakes when you ask AI for this
- Changing standard items. The AI rewrites questions 3 and 5. Try: Say: "Mark Fine questions as No change."
- Still leading. The AI keeps 'excellent leadership'. Try: Say: "Rewrite to a neutral statement on one topic."
- Table. The AI adds columns or questions. Try: Say: "Header exactly # | Problem | Neutral question, five rows."
- 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
- Header
- Allowed labels
- No change
- Length
- No new questions
Related exercises
- Accrue unpaid wages for the working days after the last pay period (Finance AI · Accountants)
- Acknowledge an employee's concern without promising outcomes (People & HR AI · HR and recruiting)
- Age a returns queue in business days and flag the ones over the limit (Customer Support & Success AI · Customer support teams)
- Alert sales to a competitor's price change, facts only (Research & AI Search · Product managers)
- Announce a colleague's departure neutrally to the team (People & HR AI · Managers and team leads)