Library › Customer Support & Success AI › Customer support teams
Count ticket tags into the top three themes
- For Customer support teams
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Intermediate
About this exercise
Count the tickets by theme using the tag mapping, and output exactly 3 numbered lines like "1. Login: 5 tickets", for the three themes with the most tickets, highest first. Break ties alphabetically. Ignore tickets tagged "spam". Then a last line "Total counted: N". Plain text, nothing else.
Common mistakes when you ask AI for this
- Counting spam. The AI counts the 22 on the dashboard. Try: Say: "Ignore tickets tagged spam."
- Not merging tags. The AI treats login and sso as separate themes. Try: Say: "Merge tags using the mapping."
- Wrong tie order. The AI puts Login first. Try: Say: "Break ties alphabetically."
- 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".
- Leaving the item count open. The AI adds or drops items to feel complete. Try: Say "exactly N numbered lines, nothing else".
- Trusting the AI to count words. The AI runs long and cannot count its own words. Try: Cap each part ("each line under 12 words") and add "under N words in total".
- Leaving a requirement unstated. The AI follows its own defaults unless the prompt spells this out. Try: State it plainly in your prompt: the output has exactly 3 numbered lines in the format 'N. Theme: X tickets' followed by a last line starting 'Total counted:'.
What a strong prompt includes
- Line format
- Uses the mapping
- Tie rule
- Ignore spam
- Asks for plain text
- Sets the exact item count
- Sets a word cap
Related exercises
- Accrue unpaid wages for the working days after the last pay period (Finance AI · Accountants)
- Acknowledge a cancellation request without a save attempt (Customer Support & Success AI · Customer success managers)
- Acknowledge an accessibility bug without a promised date (Customer Support & Success AI · Customer support teams)
- Acknowledge an executive escalation within the hour (Customer Support & Success AI · Executives)
- Age a returns queue in business days and flag the ones over the limit (Customer Support & Success AI · Customer support teams)