Every finding visibly distinguishes FACT / USER COMPLAINT / TREND / ASSUMPTION / OPPORTUNITY and shows source, URL (if present), date, confidence and provenance. UNKNOWN or missing evidence never silently becomes HIGH confidence. Contradictions are shown as CONFLICTING EVIDENCE and are never auto-resolved. Opportunity level (LOW/MEDIUM/HIGH) considers: user pain, evidence strength, strategic relevance, implementation burden, differentiation potential. It remains an assessment, not mathematical truth.
A CONTINUOUS finding is escalated to Hermes only when it is relevant, materially useful, evidence-backed, and not trending noise.
Findings (2 of 7 shown · MOCK/STATIC fixtures — not real current research)
All findings below are clearly-labelled MOCK/STATIC examples with generic placeholder content. None are live research results.
DF-004ASSUMPTIONON DEMANDNEWSTATIC
Multi-warehouse need is still an assumption
Planning assumes small sellers need multi-warehouse support; this has not been validated with any user.
Project
example-inventory
Confidence
LOW
Relevance
MEDIUM
Opportunity
N/A
Source
Internal planning note (example)
Source date
2026-10-01
Captured at
2026-10-05
Recommended next action
Validate or reject with real user evidence before any PRD scope includes it.
ASSUMPTION stays ASSUMPTION until independently supported.
UI semantics only. V1 has no write API: promotion/dismissal is LOCKED preview. A promoted finding is reviewed by Hermes before the Product Architect / Product Critic act on it — discovery never bypasses the Planning Cell and never creates build tasks from weak signals.