This is step 1 of a four-step chain. Read the raw customer feedback below (interviews, support tickets, NPS comments, app reviews, sales call notes). Produce:
1. The top 5-7 themes ranked by frequency (count of mentions).
2. Per theme: 2-3 verbatim quotes - exact words, not paraphrased.
3. End with a marker line so I remember to continue: '--- End of step 1. Paste this output into Discovery-to-decision: step 2 (impact rank). ---'
If I've pasted fewer than 20 raw items, refuse and ask for more.
The raw feedback:
{{raw_feedback}}
Discovery-to-decision: step 1 (theme cluster)
Add to PromptPaste
Download PromptPaste for MacDownload PromptPaste for iPhoneDownload PromptPaste for iPadDownload PromptPaste for Mac & iPhone
the prompt
Example output
Themes from 47 raw feedback items:
1. Setup friction (mentioned 14 times):
Quotes: 'I gave up after the third permission popup.' / 'Why does this need accessibility access?' / 'I came back two weeks later and forgot the setup.'
2. Sync visibility (11 mentions):
Quotes: 'My iPhone doesn't see what's on my Mac.' / 'How do I know iCloud is working?' / 'It saved on one device and I can't find it on the other.'
3. Pricing skepticism (9 mentions):
Quotes: 'Why is this not a one-time purchase?' / 'I won't pay monthly for a clipboard.' / '$59/yr feels high for what this does.'
4. Team / sharing requests (8 mentions, scattered specifics):
Quotes: 'Can I share a folder with my team?' / 'Make it work for my whole org.'
5. Bug: menubar disappears after sleep (5 mentions):
Quotes: 'Lost the icon again this morning.' / 'Have to relaunch every day.'
--- End of step 1. Paste this output into 'Discovery-to-decision: step 2 (impact rank)'. ---
Common mistakes
Don't paste fewer than 20 raw items - the model will pattern-match on noise. Also: don't paraphrase the quotes yourself before pasting into step 2. The verbatim quotes are what makes the chain work; paraphrasing collapses the signal. Third mistake: skipping the explicit 'paste this into step 2' marker. The chain is designed to be runnable in sequence; the marker reminds you to actually keep going to step 2 instead of stopping at theme extraction.
More from AI Prompts for Product Managers
PRD draft from a one-line problem
Act as a senior product manager. I'm going to give you a one-line problem statement. Before drafting any PRD, do this: 1. State the…
Customer interview synthesis
Read the raw customer interview transcripts below. Produce: 1. The top 5 themes ranked by frequency (number of interviews where the theme…
Stakeholder weekly update
Convert my raw bullets below into a weekly stakeholder update. Use exactly three sections: 1. Shipped: each item with a one-line outcome,…
Why it works
This is step 1 of the four-step Discovery-to-Decision chain - the headline differentiator no competing PM pack ships. Step 1 takes raw customer feedback (interview transcripts, support tickets, NPS comments, app reviews, sales call notes) and clusters it into themes with frequency counts and verbatim quotes. The output is the input to step 2 (impact ranking). Save this prompt's output as text, paste it into the next prompt in the chain. The chain is designed so you can run all four prompts in sequence and end up with a decision memo grounded in real customer evidence - not in your assumptions about what customers want. Tested cleanest on Claude Opus 4.7.