Library › Customer Support & Success AI › Managers and team leads
Rank onboarding accounts by risk points with tie-breaks
- For Managers and team leads
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Advanced
About this exercise
Rank the five accounts by risk points. Output a table with the header row exactly "Rank | Account | Points" and five rows. Points follow the rules in the notes, including their exact boundaries. Ties are broken by higher ARR first. Plain text, under 60 words, table only.
Common mistakes when you ask AI for this
- Miscounting the boundaries. Ember's 14 days and 50% do not score, but its 10 days silent does. Try: Say: "Apply the exact boundaries: MORE than 14, FEWER than 50%, 10 or MORE."
- Missing the tie-break. Cove and Alpine tie on 7; the AI lists them in table order. Try: Say: "Ties: higher ARR first."
- Extra text. The AI explains each score. Try: Give the header row and say table only.
- 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
- Asks for plain text
- Sets a length limit
- States the boundaries
- States the tie-break
Related exercises
- Alert sales to a competitor's price change, facts only (Research & AI Search · Product managers)
- Announce planned maintenance in four labeled lines (Customer Support & Success AI · IT teams)
- Answer a late-checkout request using the tiered policy (Customer Support & Success AI · Customer support teams)
- Answer a price-increase objection without discounting (Customer Support & Success AI · Customer success managers)
- Approve or return expense claims against the policy (Productivity AI · Finance and accounting)