Library › Customer Support & Success AI › Managers and team leads
Map customer requests to what actually shipped
- For Managers and team leads
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Advanced
About this exercise
Map the four customer requests to the release notes. Output a table with the header row exactly "Request | Status | Shipped" and four rows. Status is exactly Yes, No or Partly. Shipped is the release date or "-". Use only the release notes, not the sales claims. Plain text, table only, under 50 words.
Common mistakes when you ask AI for this
- Believing the sales claim. Sales says dark mode shipped. Try: Say: "Use only the release notes."
- Calling R3 Yes. Email alerts shipped, but Slack alerts did not. Try: Say: "Partly = some of it shipped."
- Wrong table. The AI adds a notes column. Try: Give the exact header; table only.
- 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
- Defines statuses
- Uses only release notes
Related exercises
- Accrue unpaid wages for the working days after the last pay period (Finance AI · Accountants)
- Acknowledge an accessibility bug without a promised date (Customer Support & Success AI · Customer support teams)
- 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)