Library › Customer Support & Success AI › Customer success managers
Reconcile two dashboards before a QBR
- For Customer success managers
- You practice Giving the right context
- Time about 5 minutes
- Level Advanced
About this exercise
Build a plain-text table with the header row exactly "Metric | Source | Definition | Value" and two rows (one per dashboard). Then one line "Use in the QBR:" naming the metric whose definition matches the customer's success plan, and one line "Do not:" that says not to average them. Plain text, under 90 words.
Common mistakes when you ask AI for this
- Averaging the figures. The AI keeps the slide's 396. Try: Say: "Do not average them."
- Picking the bigger number. The AI uses 412 because it looks better. Try: Say: "Use the metric whose definition matches the success plan."
- Dropping definitions. The AI lists values with no definitions. Try: Say: "Include each definition in the table."
- 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
- Gives the header
- Includes definitions
- Matches the success plan
- Bans averaging
- Asks for plain text
- Sets a word cap
Related exercises
- 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)
- Add input validation to a Java method with exact messages (Coding AI · Software developers)
- Add type hints that still run on Python 3.8 (Coding AI · Software developers)