Library › Customer Support & Success AI › Customer support teams

Mark which tickets breached their first-response SLA

  • For Customer support teams
  • You practice Catching mistakes and made-up facts
  • Time about 5 minutes
  • Level Intermediate

About this exercise

Build a plain-text table with the header row exactly "Ticket | Priority | Response time | Breach?" and one row per ticket in the order given. Response time is shown like 1h00. A ticket meets its SLA if the first response is within the limit, and exactly at the limit meets it. Finish with one line "Breaches: N". Plain text, under 90 words.

Common mistakes when you ask AI for this

  • Treating the limit as a breach. The AI marks 1h00 and 8h00 as breaches. Try: Say: "Exactly at the limit meets the SLA."
  • Wrong header or order. The AI re-sorts by priority. Try: Say: "Header exactly ...; rows in the order given."
  • Ignoring the helper times. The AI recalculates and slips on minutes. Try: Say: "Use the response times given in the helper."
  • 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. The AI runs long and cannot count its own words. Try: Cap each part ("each line under 12 words") and add "under N words in total".

What a strong prompt includes

  • Gives the header
  • States the boundary
  • Asks for the final count
  • Keeps order
  • Asks for plain text
  • Sets a word cap

Practice this now ↑

Related exercises