Discovery-to-decision: step 2 (impact rank)

Last tested 2026-04-26 Part of AI Prompts for Product Managers

Add to PromptPaste Download PromptPaste for MacDownload PromptPaste for iPhoneDownload PromptPaste for iPadDownload PromptPaste for Mac & iPhone

the prompt

This is step 2 of a four-step chain. Below is the themed output from step 1. Re-rank the themes by addressable impact - that is, by:
- Cohort size affected (% of users)
- Signal strength (how consistently the pattern appears)
- Addressability (can we actually do something about it?)

For each theme, produce:
- Mention count (carry over from step 1).
- Impact rationale: one paragraph weighing the three factors above.
- 'What we could do': a first-pass response, not a full solution.

Keep all themes from step 1 - do not drop any. Just re-order.

End with a marker: '--- End of step 2. Paste this output into Discovery-to-decision: step 3 (solution candidates) along with the top theme to explore. ---'

The themed output from step 1:
{{step1_output}}

Why it works

Step 2 of the chain. Takes the themed output from step 1 and ranks themes by addressable impact - that is, by the size of the user cohort affected times the strength of the signal times your ability to actually do something about it. Most PMs do this ranking implicitly and badly; this prompt makes it explicit. The output is the same themes from step 1, re-ordered, with a one-line 'impact rationale' per theme and a 'what we could do' first-pass response. Step 3 takes the top theme and generates solution candidates. Tested cleanest on Claude Opus 4.7.

Example output

Themes ranked by addressable impact:

1. Setup friction (14 mentions, top of list)
Impact rationale: Hits 100% of new users. Each setup-related abandonment is a permanent loss; we can't re-engage someone who quit before getting value. The cohort is the single biggest addressable lever.
What we could do: Reduce the permission flow from 4 screens to 1. Defer iCloud sync setup until after first use.

2. Sync visibility (11 mentions)
Impact rationale: Hits ~60% of users (the ones with multiple devices). Strong signal because users describe the failure mode in similar language - that's a UX problem we can fix, not a fundamental capability limit.
What we could do: Add an explicit sync-status indicator in the menubar/app. Surface 'last synced' timestamp.

3. Bug: menubar disappears after sleep (5 mentions)
Impact rationale: Lower count but high severity per affected user (totally blocks them). Easy to fix once diagnosed.
What we could do: Engineering investigation, likely a launch-agent retry on system wake.

4. Pricing skepticism (9 mentions)
Impact rationale: Real signal but harder to address - requires changing pricing model, not product. Defer to a separate decision process.
What we could do: Note for the next pricing review. Not a near-term product fix.

5. Team / sharing requests (8 mentions, scattered)
Impact rationale: Lower-confidence theme - the 'specifics scattered' note from step 1 means it's not yet a coherent ask. Need more interviews before sizing.
What we could do: Add to discovery backlog for next cycle.

--- End of step 2. Paste this output into 'Discovery-to-decision: step 3 (solution candidates)' along with the top theme you want to explore further. ---

Common mistakes

Don't let the model rank purely by mention count - the highest-mention theme is not always the highest-impact theme. The prompt is designed to weigh count, signal strength, AND addressability. Also: don't drop themes from step 1 just because they ranked low here. Lower-ranked themes still get logged - they may rank higher next cycle as more evidence accumulates. The chain is iterative; this is one snapshot, not a final answer.

Discovery-to-decision: step 2 (impact rank)

Why it works

Example output

Common mistakes

More from AI Prompts for Product Managers

PRD draft from a one-line problem

Customer interview synthesis

Stakeholder weekly update