Library › Customer Support & Success AI › Customer success managers

Count users per adoption segment and attach the right action

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

About this exercise

Build a plain-text table with the header row exactly "Segment | Users | Action" and three rows: Power, Occasional, Dormant, in that order. Service accounts (names starting "svc-") are not people, so leave them out. Use the action text from the playbook. Then a last line "Total: N" with the number of people counted. Plain text, under 90 words.

Common mistakes when you ask AI for this

  • Counting service accounts. The AI counts svc-sync and svc-export as Power. Try: Say: "Leave out service accounts (svc-)."
  • Putting 10 sessions in Occasional. The AI treats 10 as not enough for Power. Try: Say: "Power is 10 or more, so 10 counts."
  • Writing its own actions. The AI invents action text. Try: Say: "Use the playbook action text exactly."
  • 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. 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 header row is exactly 'Segment | Users | Action' with rows Power, Occasional and Dormant in that order, followed by a last line starting 'Total:'.

What a strong prompt includes

  • Gives the header
  • Excludes service accounts
  • Boundary rule
  • Total line
  • Asks for plain text
  • Sets a word cap

Practice this now ↑

Related exercises