Library › Customer Support & Success AI › Managers and team leads
Decide whether to involve an executive using a 2-of-4 rule
- For Managers and team leads
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Advanced
About this exercise
Apply the playbook rule to Ridgeway Foods. Output four lines labeled (a) to (d), each ending "Met" or "Not met" with the working shown after a dash, then a last line starting "Recommendation:" with Involve or Do not involve and the count of criteria met. Where sources disagree, use the newer one. Boundaries are inclusive. Plain text, under 130 words.
Common mistakes when you ask AI for this
- Using the stale CRM figures. The AI takes ARR 240,000 and the Oct 12 reply from the CRM. Try: Say: "Where sources disagree, use the newer one."
- Misreading the boundary. The AI treats 7 days as not enough. Try: Say: "Boundaries are inclusive: 7 days or more counts."
- Giving a verdict without working. The AI writes Met or Not met with no numbers. Try: Say: "Show the working after a dash on each 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
- Sets the line labels
- Says newer source wins
- States inclusive boundaries
- Asks for the recommendation line
- Asks for plain text
- 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)