Library › Customer Support & Success AI › Product managers
Turn release notes into a support briefing with expected questions
- For Product managers
- You practice Saying who it's for
- Time about 5 minutes
- Level Intermediate
About this exercise
Write a briefing for the support team with exactly three lines starting "Changed:", "Q1:" and "Q2:" where Q1 and Q2 are the two questions customers will most likely ask, each followed by its answer after " - ". Mention only what is in the released version. Plain text, under 110 words.
Common mistakes when you ask AI for this
- Promising shared filters. The AI says shared filters arrive in 4.9. Try: Say: "4.9 is not committed; don't promise it."
- Picking the wrong questions. The AI invents questions instead of using the inbox counts. Try: Say: "Choose the two questions with the most tickets that the release answers."
- Wrong layout. The AI writes a long bulleted summary. Try: Name the three line labels and what Changed covers.
- 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
- Names the three labels
- Says to use the inbox counts
- Forbids promises about 4.9
- Asks for plain text
- Sets a length limit
Related exercises
- 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)
- Announce a delay to three audiences with different limits (Leadership AI · Communications and PR)
- Announce a feature sunset with the notice period worked out (Customer Support & Success AI · Customer success managers)