Library › Customer Support & Success AI › Business analysts

Total refunds by reason after removing test refunds

  • For Business analysts
  • You practice Catching mistakes and made-up facts
  • Time about 5 minutes
  • Level Intermediate

About this exercise

Output a table with the header "Reason | Count | Total" with one row per reason, sorted by total from highest to lowest, then a last line "All: N refunds, $T". Exclude refunds marked as tests. Plain text, under 60 words.

Common mistakes when you ask AI for this

  • Including the test refunds. The AI counts R5 and R8. Try: Say: "Exclude refunds marked as tests."
  • Not sorting. The AI keeps the log order. Try: Say: "Sort by total, highest first."
  • Missing the summary line. The AI stops at the table. Try: Give the last-line format.
  • 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

  • Gives the header
  • Excludes tests
  • Sorts by total
  • Asks for plain text
  • Sets a length limit

Practice this now ↑

Related exercises