Library › Customer Support & Success AI › IT teams

Rank the help-center topics with the most failed searches

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

About this exercise

From the failed-search log, rank the top 3 topics by number of searches. Exactly three numbered lines formatted "1. Topic: N searches", then one last line starting "Write first:" naming the top topic. Count each log line once. Plain text, nothing else.

Common mistakes when you ask AI for this

  • Following the manager's guess. The manager says SSO and the AI agrees. Try: Say: "Rank from the log counts only."
  • Miscounting tags. The AI estimates instead of counting. Try: Say: "Count each tagged search once: refund 5, invoice 4, api 3."
  • Wrong format. The AI writes a paragraph or a fourth item. Try: Show the line format and the Write first line.
  • Leaving the list shape open. The AI picks its own number of items and its own layout. Try: Show the shape: "exactly N numbered lines like: 1. Label: detail".
  • 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".

What a strong prompt includes

  • Fixes the number of lines
  • Asks for plain text
  • Shows the line format
  • Counts from the log

Practice this now ↑

Related exercises