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

Scan a reply for banned phrases and count each one

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

About this exercise

Output a table with the header "Phrase | Count" listing only the banned phrases found (case does not matter), sorted from highest count to lowest, then a last line "Total: N" with the sum of the counts. Plain text, under 40 words.

Common mistakes when you ask AI for this

  • Listing absent phrases. The AI lists all six banned phrases with 0. Try: Say: "List only phrases that appear."
  • Miscounting. The AI counts one of the Unfortunately lines as a separate phrase. Try: Say: "Count every occurrence, case-insensitive."
  • Missing the total. The AI stops at the table. Try: Give 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

  • Gives the header
  • Says only found phrases
  • Asks for sorting and total
  • Asks for plain text
  • Sets a length limit

Practice this now ↑

Related exercises