Library › Customer Support & Success AI › Customer success managers
Recalculate health scores under new weights and flag band changes
- For Customer success managers
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Intermediate
About this exercise
Recalculate the four health scores with the new weights and compare to the old ones. Output a table with the header "Account | Old | New | Band" and four rows, then one last line starting "Moved:" that lists only the accounts that changed band. Band is the new band. Show whole numbers only. Plain text, under 80 words.
Common mistakes when you ask AI for this
- Skipping the weights. The AI averages the four factors or reuses the old weights. Try: Say: "Old = 50/20/15/15, new = 40/20/20/20. Multiply each factor."
- Trusting the lead's note. The note says Fir is Yellow either way; the AI believes it. Try: Say: "Do the math for every account. Ignore the note."
- Listing unchanged accounts. The AI lists all four as moved or adds commentary. Try: Say: "Moved: only accounts whose band changed."
- 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
- Gives both weight sets
- Sets the header and last line
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)