Library › AI Evals › College students
Sort 13 bad AI research answers into 3 failure types
Practice: Asking for a format you can use. About 5 minutes.
About this exercise
For your info-science class, you logged 13 bad answers from an AI research assistant and noted what went wrong. Group them into exactly 3 numbered failure types, each line 'Type: #ids = count', then one last line 'Total: N'. Leave out any note you later found was your own mistake. Plain text, under 70 words.
Common mistakes when you ask AI for this
- Too many types. The AI splits fake books, fake URLs and fake papers into separate groups. Try: Say: "Exactly 3 failure types."
- No ids or counts. The AI describes patterns but not which answers belong where. Try: Show the shape: "Type: #1, #4 = 2".
- Counting your own mistake. The AI counts every note, including the one where you typed the wrong question. Try: Add: "Leave out notes that were my mistake, and end with Total: N."
- Getting markdown back. AI defaults to bold headings and long bullets. Try: Ask for "plain text, no bold, no headings."
What a strong prompt includes
- Says exactly how many
- Asks for ids and counts
- Leaves out your mistake
- Asks for a total
- Asks for plain text
Related exercises
- Announce a referral bonus with the steps to claim it (Marketing AI · HR and recruiting)
- Announce a team meeting change people will actually follow (Writing AI · Managers and team leads)
- Answer a 'found an error' question in STAR order (Writing AI · Finance and accounting)
- Answer a wholesale inquiry with clear terms (Writing AI · Small business owners)
- Answer an RFP timeline question in exactly four phases (Writing AI · Sales and customer success)