Library › AI Evals › Product managers
Sort 13 failing AI meeting-note traces into 3 failure types
Practice: Asking for a format you can use. About 5 minutes.
About this exercise
You reviewed 13 failing outputs from your AI meeting-notes feature and noted what went wrong in each. Group them into exactly 3 numbered failure types, each line 'Type: #ids = count', then one last line 'Total: N'. Leave out any trace where the recording itself was broken. Plain text, under 70 words.
Common mistakes when you ask AI for this
- Too many types. The AI splits wrong owners, wrong credit and swapped roles into separate groups. Try: Say: "Exactly 3 failure types."
- No ids or counts. The AI describes the problems without showing which traces belong where. Try: Show the shape: "Type: #1, #4 = 2".
- Counting the broken recording. The AI counts #5, which failed because of the audio, not the AI. Try: Add: "Leave out traces where the recording was broken, 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 the broken recording
- Asks for a total
- Asks for plain text
Related exercises
- Adapt one ad image to 3 sizes with Midjourney (Image & Video AI · Marketing and content)
- 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)