Outside Read

parallel panel → synthesis → audit·7 agents

Four vendor-diverse attack-vector reviewers examine your question in parallel — no cross-talk. A synthesizer distills their outputs into a battlefield map (core_agreement / concessions / irreducible_conflict / risk_ranking). BlindCritic and FactChecker audit the map before it reaches you. Three presets: find-blind-spots, critique-draft, pre-mortem.

Claude
Assumption Hunter

Attack vector: surfaces load-bearing assumptions the user has not named.

Gemini
Base Rate

Attack vector: grounds claims in reference class and historical frequency.

OpenAI
Failure Mode

Attack vector: enumerates failure modes the proposal has not addressed.

Grok
Second Order

Attack vector: surfaces downstream and second-order consequences.

Claude
Battlefield Synthesizer

Synthesizer — produces the locked battlefield-map output contract (web-off).

Blind Critic

Logical/structural auditor — no tools; blindness is the audit mechanism.

Fact Checker

Factual auditor — web search to verify verifiable claims in the map.