Library › Research AI › HR and recruiting
Check a job posting's benefit claims against the benefits sheet
Practice: Catching mistakes and made-up facts. About 5 minutes.
About this exercise
A hiring manager wrote the benefits section of a job posting, and you need to check it against the official 2027 benefits sheet before it goes live. You want one numbered line per claim, under 60 words total, labeled Matches, Wrong, or Not on sheet, with the sheet's version after any Wrong label. Use only the benefits sheet, plain text, nothing else.
Common mistakes when you ask AI for this
- No fixed labels. The AI writes general feedback, so the manager can't tell what to change. Try: Give them: "Matches, Wrong, or Not on sheet."
- Calling unknowns wrong. The gym isn't on the sheet, so it needs checking, not a 'wrong' label. Try: Add: "If the sheet doesn't mention it, label it Not on sheet."
- Getting a rewrite. The AI rewrites the section, and the manager can't see what was off. Try: Say: "Label only, no rewrite."
- 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 10 words."
- Getting markdown back. AI defaults to bold labels and headings, which show up as stray symbols in a comment on the posting. Try: Ask for "plain text, no bold, no headings."
What a strong prompt includes
- Gives exact labels
- Names the source
- Asks for the sheet's version
- Sets a length limit
- Asks for plain text
Related exercises
- Alert sales to a competitor's price change, facts only (Research AI · Product managers)
- Answer a buyer's HOA questions from the bylaws (Research AI · Real estate agents)
- Answer a coworker's travel policy question in one Slack reply (Research AI · Office and admin)
- Answer a family's visiting questions from the current policy (Research AI · Nurses and healthcare workers)
- Answer winter break housing questions from the current policy (Research AI · College students)