Library › Customer Support & Success AI › Customer success managers
Work out SLA credit bands from downtime minutes
- 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 "Customer | Counted downtime | Uptime % | Credit" and five rows in the order given. Counted downtime excludes scheduled maintenance. Uptime % is shown to two decimals, from a 43,200-minute month. Credit bands are inclusive at the lower edge. Then one last line: "Finance confirms before any credit is promised." Plain text.
Common mistakes when you ask AI for this
- Counting scheduled maintenance. The AI uses the total minutes. Try: Say: "Subtract scheduled maintenance from downtime."
- Misplacing the edge case. The AI puts Dune at 25% because it sits on a boundary. Try: Say: "Bands include their lower edge: 99.00% gets 10%."
- Skipping the closing line. The AI adds its own note or promise. Try: Say: "End with exactly: Finance confirms before any credit is promised."
- 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 exact header
- Excludes maintenance
- States the boundary rule
- Gives the 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)