Library › Customer Support & Success AI › Customer support teams

Decide which closed tickets get a survey and why not

  • For Customer support teams
  • You practice Setting limits and rules
  • Time about 5 minutes
  • Level Intermediate

About this exercise

Output a table with the header "Ticket | Survey | Reason" and six rows S1 to S6. Survey is Send or Skip. Reason is the letter of the first skip rule that applies (A, B, C or D) or "ok" for a Send. Today is Nov 6. Plain text, under 60 words.

Common mistakes when you ask AI for this

  • Wrong 30-day boundary. The AI skips S6. Try: Say: "Oct 7 counts, Oct 6 does not."
  • Giving all reasons. The AI lists several rules per ticket. Try: Say: "Only the first skip rule that applies."
  • No table. The AI explains in prose. Try: Give the header.
  • 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 first rule wins
  • States the boundary
  • Asks for plain text
  • Sets a length limit

Practice this now ↑

Related exercises