Library › Customer Support & Success AI › Product managers

Count tickets by lot code and flag the lot to escalate

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

About this exercise

Count the tickets by lot code, treating different spellings of the same lot as one and leaving out the ticket with no readable lot. Output a table with the header "Lot | Tickets | Flag" sorted from most tickets to fewest, Flag being Yes if the lot has 3 or more tickets. Then a last line "Escalate: L-###" (or "Escalate: none"). Plain text, under 50 words.

Common mistakes when you ask AI for this

  • Counting lowercase as a separate lot. The AI treats l-221 as its own lot. Try: Say: "Treat spellings of the same lot as one."
  • Counting the unreadable ticket. The AI assigns #6 to a lot. Try: Say: "Leave out tickets with no readable lot."
  • No 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
  • Merges spellings
  • States the flag threshold
  • Asks for plain text
  • Sets a length limit

Practice this now ↑

Related exercises