Library › Customer Support & Success AI › Managers and team leads
Build a weighted renewal forecast with the latest probabilities
- For Managers and team leads
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Intermediate
About this exercise
Build a weighted renewal forecast. Output a table with the header row exactly "Account | ARR | Prob | Expected" and five rows, where Expected = ARR x Prob. Then two last lines: "Total expected:" with the sum, and "At risk:" listing accounts with a probability of 50% or lower. Use the latest probability for each account. Plain text, under 100 words.
Common mistakes when you ask AI for this
- Using the old probability. The AI keeps Birch at 60% from the main table. Try: Say: "Use the latest probability, including the Nov 3 update."
- Trusting the sales note. The AI uses 90% for Cedar. Try: Say: "Use the CSM's confirmed probability; ignore unconfirmed sales notes."
- Wrong total or at-risk list. The AI sums the wrong values or lists only Elm. Try: Say: "Total = sum of Expected. At risk = probability 50% or lower."
- Wrong table. The AI adds columns or paragraphs. Try: Give the exact header row.
- 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".
What a strong prompt includes
- Asks for plain text
- Sets a length limit
- Gives the header
- Uses latest probabilities
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)