FactSwarm v2.0
by MichaelGao1999
Multi-Agent full-picture evaluation engine ("FactSwarm / 事实蜂群" v2.0). Does not judge truth/falsehood; instead, draws cognitive maps: what is known, what is uncertain, what is unknown. Use when: (1) user asks to evaluate an event/entity/concept and wants a comprehensive fact-based landscape, (2) user mentions "FactSwarm", "事实蜂群", S1-S6 stages, or "全貌评估", (3) user needs cross-validated research for investment/content/risk/life decisions, (4) user explicitly wants the publisher-bridge output (/pub) for content creation, (5) user requests HTML report output from FactSwarm. Domains: business, tech, lifestyle, general. Supports hard-gated workflow (S1/S1.5/S2/S4/S5 require explicit user confirmation).