Verifies factual claims against live sources and returns a verdict, confidence score, and citations for any agent to use before stating uncertain facts.
Enables agents to verify their own output mid-task by checking every claim against provided sources, returning supported, partial, unsupported, or contradicted verdicts with exact citations.
Implements Anthropic's multi-agent research methodology with tools for iterative web search, source quality scoring, citation tracking, and quality-tiered report generation.
Enables prior-art searches on granted US patent claims. Given an invention description, it returns a grounded memo with citations, verifying each finding against the source and quarantining unverifiable claims.
Runs a local Ollama multi-agent pipeline with collector, writer, and reviewer roles to transform messy notes into structured reports with a quality gate.