Library › Data AI › Customer support teams
Rank agent CSAT while flagging tiny samples
Practice: Giving the right context. About 5 minutes.
About this exercise
You're posting October CSAT by agent. Your team rule: under 20 survey responses is "not enough data," with no score. CSAT = positive ÷ responses. Write exactly 4 numbered lines in export order, each as Name: positive ÷ responses = X% (or not enough data), then one unnumbered last line: Top: [agent with enough data]. Plain text, under 60 words.
Common mistakes when you ask AI for this
- Not giving the minimum. The AI scores Cy at 90% from 10 surveys. Try: Add: "Under 20 responses = not enough data."
- Not asking to see the work. Agents will ask how their number was figured. Try: Add a line to copy: "1. Ana Reyes: 45 ÷ 50 = 90%"
- Leaving the ending open. The AI adds coaching advice for each agent. Try: Add: "Then one line: Top: [agent]. Nothing else."
- Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands over it. Try: Cap each line: "each line under 10 words."
- Forgetting where it goes. AI loves markdown tables and bold, which show up as clutter in a team channel. Try: Add: "Plain text, no bold, headings or tables."
What a strong prompt includes
- Gives the minimum
- Defines CSAT
- Asks to show the math
- Sets a word limit
- Asks for plain text
Related exercises
- Announce a hybrid work policy change with clear actions (Writing AI · HR and recruiting)
- Announce a new weekend rotation in three clear rules (Productivity AI · Managers and team leads)
- Announce a promotion with the right date and no pay details (Writing AI · HR and recruiting)
- Announce a team change and answer the first question (Writing AI · Managers and team leads)
- Answer a showing request for a home that's under contract (Writing AI · Real estate agents)