Library › Data AI › Product managers
Normalize feature request counts by active users
Practice: Giving the right context. About 5 minutes.
About this exercise
Your lead says calendar sync requests are "up 12.5%." Active users grew from 8,000 to 10,000, so compare requests per 1,000 active users instead. Write exactly 3 numbered lines: 1) last month's rate, 2) this month's rate, each as requests ÷ (users ÷ 1,000) = X per 1,000, 3) the change, up or down. Plain text, under 50 words.
Common mistakes when you ask AI for this
- Not normalizing. The AI compares raw counts and agrees requests went up. Try: Add: "Compare per 1,000 active users."
- Not asking to see the work. The lead will push back on a bare number. Try: Add a line to copy: "1. Sep: 40 ÷ 8 = 5 per 1,000"
- 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 reply in Slack. Try: Add: "Plain text, no bold, headings or tables."
What a strong prompt includes
- Normalizes by users
- Asks to show the math
- Asks for the change
- 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)