Synthesize customer feedback into a ranked table for product

About this exercise

You lead a CS team and owe the product director a feedback summary. Group the notes into exactly 3 themes in one markdown table with columns Theme, Accounts, ARR at stake, Customer quote. Count each account once per theme, add up ARR, sort by ARR highest first, and use only verbatim quotes from customers (not from your CSMs). Under 150 words, nothing after the table.

Common mistakes when you ask AI for this

• Double counting. The AI adds Norland twice because it appears twice. Try: Say: "Count each account once per theme."
• Treating CSM opinions as customer voice. The AI quotes your own team as if customers said it, and counts their guesses. Try: Add: "Only count and quote what customers said, not CSMs."
• Not sorting by money. The AI lists themes in the order it found them. Try: Ask: "Sort rows by ARR at stake, highest first, and show the ARR sum."
• Paraphrasing quotes. The AI tidies quotes, so product can't trace them. Try: Say: "Quotes must be verbatim from the log."
• Trusting the AI to count words. The AI adds a summary paragraph after the table. Try: Say: "Output only the table, each cell under 15 words."

What a strong prompt includes

• Names the columns
• Prevents double counting
• Separates customer from CSM
• Asks for sorting
• Sets the theme count

Practice this now ↑

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)