Library › Customer Support & Success AI › Customer support teams
Decide an annual-plan refund by the policy, showing the rule and math
- For Customer support teams
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Advanced
About this exercise
Decide this refund using your policy: if the first cancellation request came within 45 days of renewal, refund the unused months at $100 each, counting any month that has started as used; after 45 days, no refund. Output exactly four labeled lines: Rule:, Request date used:, Math:, Decision:. Show the arithmetic in the Math line and put the decision last. Plain text, under 110 words.
Common mistakes when you ask AI for this
- Trusting the latest ticket. The AI dates the request from the most recent email and the agent's note, so it denies a valid refund. Try: Say: "Use the date of the FIRST cancellation request."
- Hiding the math. The AI states a number with no working, so a reviewer can't check it. Try: Ask: "Show the math: months used, months left, x $100."
- Leaving the shape open. The AI writes an essay and buries the decision in the middle. Try: Give the labels: "Rule:, Request date used:, Math:, Decision: in that order."
- 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 110 words. Try: Cap each part instead of the total: "each line under 15 words".
What a strong prompt includes
- Says which date counts
- Asks to show the math
- Gives the labels
- Gives the policy
- Asks for plain text
Related exercises
- Alert sales to a competitor's price change, facts only (Research & AI Search · Product managers)
- Announce planned maintenance in four labeled lines (Customer Support & Success AI · IT teams)
- Answer a late-checkout request using the tiered policy (Customer Support & Success AI · Customer support teams)
- Answer a price-increase objection without discounting (Customer Support & Success AI · Customer success managers)
- Approve or return expense claims against the policy (Productivity AI · Finance and accounting)