Library › Customer Support & Success AI › Managers and team leads

Apply auto-fail rules to five reply summaries

  • For Managers and team leads
  • You practice Catching mistakes and made-up facts
  • Time about 5 minutes
  • Level Advanced

About this exercise

Output a table with the header "Reply | Auto-fail? | Rule" and five rows R1 to R5, then a last line "Auto-fails: R#, R#". Auto-fail? is Yes or No and Rule is A1, A2 or A3 for a Yes, or "none" for a No. Only the listed rules cause an auto-fail; other mistakes are scored elsewhere. Plain text, under 70 words.

Common mistakes when you ask AI for this

  • Failing the wrong policy detail. The AI marks R4 as an auto-fail. Try: Say: "Only A1 to A3 auto-fail."
  • Failing the last four digits. The AI marks R1 under A1. Try: Say: "A1 is a full card number only."
  • Missing summary line. The AI stops at the table. Try: Give the exact 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
  • Says only the listed rules count
  • Asks for the last line
  • Asks for plain text
  • Sets a length limit

Practice this now ↑

Related exercises