Verified against Claude · 2026-08-06
Cut a feature wishlist down to the MVP that actually tests your riskiest assumption
Take a full feature wishlist and your riskiest assumption, and get back the smallest version that tests it — plus a visible cut list naming what got left out and why.
The prompt
Ready to copy — highlighted parts are example details you can swap.
You are helping scope an MVP down to the smallest thing that tests one specific assumption — not the smallest version of the full product vision. Context: - Full feature wishlist: Auto-generate claim forms, multi-clinic dashboard, claim status tracking, SMS notifications, analytics reporting, staff permission levels, white-label branding - Riskiest assumption to test: That clinic staff will trust an auto-generated claim form enough to submit it without manually re-checking it - Who will use this test version: One office manager at a single pilot clinic Task: 1. Restate That clinic staff will trust an auto-generated claim form enough to submit it without manually re-checking it as one testable hypothesis. 2. From Auto-generate claim forms, multi-clinic dashboard, claim status tracking, SMS notifications, analytics reporting, staff permission levels, white-label branding, select only the features One office manager at a single pilot clinic needs to genuinely put that hypothesis to the test — not features that would help a different, less risky assumption, and not features that make the product feel more complete but aren't load-bearing for this specific test. 3. List every feature you cut, next to the assumption it would actually test instead — so each cut is a visible decision with a reason, not a feature quietly dropped and forgotten. 4. Define, in advance, what a pass and a fail look like for this test — specific enough that you and a skeptical cofounder would agree on the result afterward without arguing about it. Format: three sections — Included (with the assumption each feature tests), Cut (with the assumption each cut feature would have tested instead), Pass/Fail definition.
Customize the highlighted detailsoptional — the prompt above already works
Why this works
This grounds MVP scoping in Lean Startup's actual definition — an MVP exists to test one hypothesis, it is not a stripped-down version of the entire roadmap — which is a distinction most feature-cutting exercises collapse by asking 'what's the smallest version of everything' instead of 'what's the smallest thing that tests the one thing I'm actually unsure about.' The paired cut-list format, where every removed feature sits next to the assumption it would have tested, is what stops scope creep in reverse: without a written reason, a cut feature has a way of quietly getting re-added mid-build because nobody remembers why it left, or because it's easy to justify as 'just one more thing' in isolation. Defining pass/fail before building removes the after-the-fact wiggle room that lets a team call a weak result a win because the bar was never actually written down.
What you get back
Hypothesis: Clinic staff will trust an auto-generated claim form enough to submit it without manually re-checking every field. Included: Auto-generate claim forms (the core test), claim status tracking (needed to see if they follow up manually anyway, which would signal distrust). Cut: Multi-clinic dashboard (tests a scaling assumption, not this one) — SMS notifications (tests engagement, not trust) — analytics reporting, staff permissions, white-label branding (all test later-stage assumptions about retention and expansion, not initial trust). Pass/fail: Pass if the office manager submits at least 8 of 10 auto-generated forms without manually re-verifying every field first. Fail if they re-check every field regardless, or revert to their old manual process within the first week.
Verified against
Claude Sonnet 5 · 2026-08-06
Gemini 3 Pro · 2026-07-30
Changelog
- 2026-08-06 — Initial publish.
Need this built into your business?
If a prompt isn't enough — custom software, built and maintained for you — that's Scult's day job.
EXPLORE CUSTOM SOFTWARE

