Library › Customer Support & Success AI › Customer success managers
Check four deck quotes against the call transcript
- For Customer success managers
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Advanced
About this exercise
Check each quote in the draft deck against the transcript. Output four lines "Quote 1:" to "Quote 4:", each ending Exact, Altered or Not found. For Altered, add a dash and what changed. A quote is Exact only if the words appear in the transcript in that order; dropping a leading word is fine. Then a last line exactly: "Customer approval is needed before any quote is used." Plain text, under 100 words.
Common mistakes when you ask AI for this
- Accepting close enough. The AI follows the AE and marks Quote 2 as Exact. Try: Say: "Exact only if the words appear in order; ignore the AE's opinion."
- Missing the reversed meaning. The AI treats Quote 4 as a trim. Try: Say: "Flag changes that alter the meaning, such as dropping almost."
- Leaving out the closing line. The AI adds advice instead. Try: Say: "End with the exact closing line."
- 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. The AI runs long and cannot count its own words. Try: Cap each part ("each line under 12 words") and add "under N words in total".
What a strong prompt includes
- Names the labels
- Defines exact
- Shows what changed
- Closing line
- Asks for plain text
- Sets a word cap
Related exercises
- Accrue unpaid wages for the working days after the last pay period (Finance AI · Accountants)
- Acknowledge a cancellation request without a save attempt (Customer Support & Success AI · Customer success managers)
- 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)