Library › Customer Support & Success AI › Customer support teams
Score a chat against four criteria with line numbers as proof
- For Customer support teams
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Advanced
About this exercise
Score the chat on the four criteria. Output a table with the header row exactly "Criterion | Pass | Line" and four rows. Pass is Yes or No. Line is the number of the line that proves it (like L4) or "-" if no line applies. Judge only what the transcript shows. Plain text, table only, under 100 words.
Common mistakes when you ask AI for this
- Accepting the reviewer's draft. The draft says identity was verified; the AI agrees. Try: Say: "Both items are required. Ignore the draft."
- Missing the vague time. The AI passes 'soon' as a next step. Try: Say: "A specific time is required."
- Wrong table. The AI adds a comments column. Try: Give the exact header row.
- Getting markdown back. AI adds bold and headings by default, which show up as stray symbols where this is pasted. Try: Say "plain text, no bold, no headings, no asterisks".
- Trusting the AI to count words. AI is bad at counting and usually runs long, so a vague "keep it short" lands well over the limit. Try: Cap each part instead of the total, for example "each line under 15 words".
What a strong prompt includes
- Asks for plain text
- Sets a length limit
- Gives the header
- Asks for line evidence
Related exercises
- Acknowledge an executive escalation within the hour (Customer Support & Success AI · Executives)
- 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 feature sunset with the notice period worked out (Customer Support & Success AI · Customer success managers)
- Announce a feature to admins without hype (Customer Support & Success AI · Customer success managers)