Feature Prioritization Board
How it works
Feature Prioritization Board runs your backlog item through a three-phase adversarial review process instead of a single gut-check:
Phase 1 — Three independent reviewers, blind. User Value Skeptic, Effort Realist, and Strategic Fit Pragmatist each evaluate the same request without seeing each other's notes.
Phase 2 — Cross-examination. Every finding gets challenged or corroborated by the other two lenses — false positives get contested with a concrete reason, and issues that multiple lenses independently flag get marked as a stronger signal.
Phase 3 — Board verdict. Every finding is tagged CONFIRMED / CORROBORATED / DISPUTED, followed by one prioritization recommendation you can actually act on.
Sample output
Phase 3 — Board verdict
- [CORROBORATED] Only one enterprise account requested this, no usage data cited — User Value Skeptic and Strategic Fit Pragmatist both flagged it independently. Fix: check request volume before committing a sprint.
- [DISPUTED] "Quick add" effort estimate — Effort Realist flagged missing edge-case handling, User Value Skeptic countered the core case is genuinely simple. Human call needed.
Prioritization recommendation: Defer — 1 CORROBORATED finding (thin, single-customer value case), revisit if usage data changes.
Use cases
Get a rigorous second opinion on a backlog item before committing a sprint to it
Catch the specific pattern of building for the loudest request instead of the most common one
Use inside Claude Code, Codex, or OpenClaw sessions directly — paste the request and go
FAQ
Does this replace a product manager's judgment? No — it's a structured reasoning pass that surfaces gaps and disagreements, not a substitute for someone who owns the roadmap and the tradeoffs.
What if I don't have an effort estimate yet? The Effort Realist lens will note that its finding is best-effort and ask for one — the review still runs, just with a flagged confidence gap.
Can I use this for engineering-only estimates, without the value/strategy angle? Yes — run it as-is and simply weight the Effort Realist section more heavily; the other two lenses still catch real gaps worth knowing about.
