Library › Customer Support & Success AI › Product managers

Rank four bugs by unique customers times severity weight

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

About this exercise

Score each bug as unique customers multiplied by its severity weight (High 3, Medium 2, Low 1). Output a table with the header "Bug | Customers | Weight | Score" sorted by score from highest to lowest, then a last line "Fix first: B#". Use unique customers, not ticket counts. Plain text, under 60 words.

Common mistakes when you ask AI for this

  • Using ticket counts. The AI multiplies 22 tickets for B3. Try: Say: "Use unique customers."
  • Not sorting. The AI keeps B1 to B4 order. Try: Say: "Sort by score, highest first."
  • Letting the easy fix decide. The AI recommends B3 because it's quick. Try: Say: "Fix first is the highest score."
  • 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 table header
  • Says unique customers
  • Gives the weights
  • Asks for plain text
  • Sets a length limit

Practice this now ↑

Related exercises