Library › Customer Support & Success AI › Customer success managers
Find the biggest onboarding drop by percent, not by count
- For Customer success managers
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Advanced
About this exercise
Build a plain-text table with the header row exactly "Step | From | To | Kept %" and three rows for the three steps, with Kept % to one decimal (like 62.5). Then one last line starting "Biggest drop:" naming the step with the highest percent lost and that percent. Rank by percent, not by the number of people. Plain text, under 90 words.
Common mistakes when you ask AI for this
- Ranking by headcount. The AI follows the CSM and picks the step losing 36 people. Try: Say: "Rank by percent lost, not number of people."
- Wrong percentages. The AI rounds 62.5 or reports percent lost in the Kept column. Try: Say: "Kept % to one decimal: kept divided by from."
- Missing the last line. The AI adds a recommendation paragraph. Try: Say: "Last line: Biggest drop: step and percent lost."
- 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
- Gives the header
- Defines Kept %
- Rank by percent
- Last line label
- 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)