Library › Customer Support & Success AI › Customer support teams

Settle a QA disagreement between two reviewers

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

About this exercise

Two QA reviewers scored the same reply. Using the criterion definitions and the policy, output a table with the header "Criterion | A | B | Correct" and three rows, then a last line in the form "Right: Accuracy=A or B or neither, Empathy=..., Next step=...". Plain text, under 100 words. Judge the reply, not the reviewers' reasons.

Common mistakes when you ask AI for this

  • Averaging the reviewers. The AI splits the difference instead of applying the definitions. Try: Say: "Score each criterion yourself from the definition."
  • Missing the wrong days. The reply sounds fine, so the AI passes Accuracy. Try: Say: "Check the days against the policy: 5 to 10."
  • Free-form feedback. The AI writes paragraphs about both reviewers. Try: Give the table header and 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

  • Asks for plain text
  • Sets a length limit
  • Gives the header and last line
  • Applies the definitions

Practice this now ↑

Related exercises