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

Pick which at-risk accounts to save with 12 CSM-weeks

  • For Managers and team leads
  • You practice Setting limits and rules
  • Time about 5 minutes
  • Level Advanced

About this exercise

Rank all 8 accounts by expected ARR saved per CSM-week (ARR times save chance, divided by weeks). Output one line per account, highest first, formatted "Account: 60k x 90% = 54k, 1 week, 54k per week". Then add the picks: go down the ranked list, add an account only if it still fits in the 12-week budget, and skip any that does not fit. End with one line starting "Recommendation:" naming the picks, weeks used and total expected ARR. Plain text.

Common mistakes when you ask AI for this

  • Picking the biggest logo. The AI favors Cypress because it is the largest account. Try: Say: "Rank by expected ARR per CSM-week only."
  • Using the old chance. The AI uses 70% for Hazel from the note. Try: Say: "Use the lowered chance of 50% for Hazel."
  • Stopping when one does not fit. The AI stops at Alder instead of checking the rest. Try: Say: "Skip any account that does not fit and keep going down the list."
  • No working shown. The AI states the ranking without the math. Try: Say: "Show ARR x chance = expected on every line."
  • 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".

What a strong prompt includes

  • Defines the ranking
  • Shows the math
  • Sets the skip rule
  • Starts the last line
  • Asks for plain text
  • Sets a word cap

Practice this now ↑

Related exercises