Discovery & Intelligence

One logical worker: evidence-backed product, market, technology, and user intelligence · Discovery recommends. Hermes coordinates. Ari decides.
DCP READ-ONLY: CONNECTED DEVELOPMENT / UI PREVIEW DCP BATCH 5/6 SOAK IN PROGRESS TELEMETRY: UNKNOWN COMMAND EXECUTION LOCKED

DISCOVERY INBOX

On-demand Discovery · Continuous Intelligence (data model + UI only in V1)
Discovery recommends. Hermes coordinates. Ari decides.
New
4
from loaded data only
Reviewed
1
from loaded data only
Promoted
1
from loaded data only
Conflicting Evidence
1
from loaded data only

Filters

Simple attribute filters only — no semantic search, no vector DB.

Project

Allexample-crm-toolexample-inventoryexample-note-app

Type

AllFACTUSER COMPLAINTTRENDASSUMPTIONOPPORTUNITY

Confidence

AllLOWMEDIUMHIGH

Relevance

AllLOWMEDIUMHIGH

Mode

AllON DEMANDCONTINUOUS

Status

AllNEWREVIEWEDPROMOTEDDISMISSED

Evidence discipline

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 (4 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-003TRENDCONTINUOUSREVIEWEDMOCK

Chatter about lighter single-purpose tools

Several example community threads mention switching from heavy all-in-one tools to lighter single-purpose apps.

Project
example-crm-tool
Confidence
LOW
Relevance
MEDIUM
Opportunity
LOW
Source
Community aggregation (static example) https://community.example.com/trends
Source date
2026-09-28
Captured at
2026-10-05
Recommended next action
Do not escalate on its own; watch for corroborating evidence.
Aggregated chatter; not independently supported.
PROMOTE · LOCKED (PREVIEW ONLY) DISMISS · LOCKED (PREVIEW ONLY)
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.
PROMOTE · LOCKED (PREVIEW ONLY) DISMISS · LOCKED (PREVIEW ONLY)
DF-006FACTON DEMANDNEW CONFLICTING EVIDENCEMOCK

Example changelogs disagree on export fields

Two example changelogs disagree about whether API exports include custom fields.

Project
example-crm-tool
Confidence
LOW
Relevance
MEDIUM
Opportunity
N/A
Source
Changelog A (example) https://changelog.example.com/a
Source date
2026-09-02
Captured at
2026-10-05
Factual assertion from this source is UNVERIFIED until independently supported.
Recommended next action
Human review: reconcile the sources before any planning use.
Source B contradicts source A. The contradiction is displayed and is never auto-resolved.
PROMOTE · LOCKED (PREVIEW ONLY) DISMISS · LOCKED (PREVIEW ONLY)
DF-007TRENDCONTINUOUSDISMISSEDMOCK

Short-term spike of AI-summary posts (noise)

Example social posts show a short-term spike of interest in AI-generated summaries; no material use identified.

Project
example-note-app
Confidence
LOW
Relevance
LOW
Opportunity
LOW
Source
Social signal sample (static example) https://social.example.com/sample
Source date
2026-10-02
Captured at
2026-10-05
Recommended next action
None — dismissed as trending noise.
Dismissed: fails the continuous-intelligence escalation rule (not materially useful).
PROMOTE · LOCKED (PREVIEW ONLY) DISMISS · LOCKED (PREVIEW ONLY)

Promotion to Product Planning (conceptual handoff)

Discovery Finding→Hermes Review→Product Architect / Product Critic→

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.