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

Screen six customers for reference requests with boundary rules

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

About this exercise

Screen the customers for a reference request. Output a table with the header row exactly "Customer | Eligible | Reason" and six rows in the given order. Eligible is Yes only if all four rules pass. Reason is "Meets all" or the first failed rule in 5 words or fewer. Plain text, table only, under 70 words.

Common mistakes when you ask AI for this

  • Counting Dune. The AE says to count the 11-month customer. Try: Say: "Apply the rules exactly: 12 months or more."
  • Missing the boundaries. Birch is exactly 12 months and exactly 6 months. Try: Say: "12 months counts; exactly 6 months ago is OK."
  • Wrong table or long reasons. The AI adds a column and writes sentences. Try: Say: "Exact header; Reason 5 words or fewer; table only."
  • 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

  • Asks for plain text
  • Sets a length limit
  • States the boundaries
  • Gives the header

Practice this now ↑

Related exercises