Library › Marketing AI › Product managers
Define launch success metrics and flag the ones with no baseline
- For Product managers
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Advanced
About this exercise
You're defining success metrics for the Nimbus launch. Write a prompt for a markdown table with columns Metric | Baseline | Target | Source for exactly the four committed metrics. If a metric has no baseline in the notes, write "No baseline" for Baseline and "Set after 2 weeks of data" for Target. Leave out ideas that weren't committed. Under 90 words, no other text.
Common mistakes when you ask AI for this
- Using the guess for NPS. The AI fills the NPS baseline with 40. Try: Say: "If there's no baseline in the notes, write No baseline."
- Adding uncommitted metrics. The AI adds brand awareness and press mentions. Try: Say: "Exactly the four committed metrics."
- Mixing up baselines and targets. The AI swaps or merges the numbers. Try: Name the four columns and copy numbers from the notes only.
- Letting markdown through. AI adds bold text and headings by default. Try: Add: "Plain text only, no bold, no headings."
- Trusting the AI to count words. AI is bad at counting and often runs past a word limit. Try: Cap each part (for example "each line under 15 words") so the total lands well under the limit.
What a strong prompt includes
- Names the table columns
- Fixes the four committed metrics
- Gives the no-baseline rule
- Bans guesses
- Caps length
Related exercises
- Accrue unpaid wages for the working days after the last pay period (Finance AI · Accountants)
- Age a returns queue in business days and flag the ones over the limit (Customer Support & Success AI · Customer support teams)
- Alert sales to a competitor's price change, facts only (Research & AI Search · Product managers)
- Announce a $29 to $39 price increase to loyal customers (Marketing AI · Marketing and content)
- Announce a referral bonus with the steps to claim it (Marketing AI · HR and recruiting)