Library › Customer Support & Success AI › Executives

Rate an account's churn risk by counting criteria with a date window

  • For Executives
  • You practice Catching mistakes and made-up facts
  • Time about 5 minutes
  • Level Advanced

About this exercise

Rate the account using the criteria. Write four lines starting "Risk:" (High, Medium or Low), "Met:" (the letters), "Not met:" (the letter and why, with the count) and "Next step:" (one action for the account manager). Today is Nov 6. Plain text, under 90 words.

Common mistakes when you ask AI for this

  • Counting Oct 2. The AI counts three escalations and rates High. Try: Say: "The last 30 days start Oct 7; count only those."
  • Offering a discount. The AI proposes a price cut. Try: Say: "No discounts without finance approval."
  • Missing the labels. The AI writes a narrative. Try: Name the four line labels.
  • 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

  • Names the four labels
  • Defines the window
  • Forbids discounts
  • Asks for plain text
  • Sets a length limit

Practice this now ↑

Related exercises