Library › Customer Support & Success AI › Customer support teams
Show how the SLA clock pause keeps a ticket within target
- For Customer support teams
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Intermediate
About this exercise
A customer claims a breach because the ticket took "over a day". Write exactly three lines starting "Running:", "Paused:" and "Result:". Running adds the minutes the clock was running, with the sum shown like "60 + 90 = 150 minutes". Result compares it with the target in minutes. Plain text, under 70 words.
Common mistakes when you ask AI for this
- Using wall-clock time. The AI counts Mon 10:00 to Tue 3:30 and agrees with Fiona. Try: Say: "The clock pauses while waiting for the customer."
- Wrong arithmetic. The AI rounds in hours and gets the sum wrong. Try: Say: "Work in minutes and show the sum."
- Skipping the pause window. The AI doesn't say when the clock paused. Try: Add: "Paused: give the start and end of the pause."
- 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
- Names the labels
- Asks for the sum in minutes
Related exercises
- 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)
- Announce a feature sunset with the notice period worked out (Customer Support & Success AI · Customer success managers)
- Announce a feature to admins without hype (Customer Support & Success AI · Customer success managers)