Epistemic reasoning engine for AI Agents — assess claim credibility with calibrated confidence. Includes a ready-to-use .skill package for agent frameworks. 87%+ accuracy with evidence, 85%+ abstain without.
Skill Claude CodeCodex
LLM-driven epistemic reasoning engine. Evaluates claims against evidence, outputs calibrated confidence and structured belief state (VERIFIED/CONTESTED/UNCERTAIN). v2 adds 4-way constraint system, parameterized configuration, and formula-based confidence intervals. Use when the agent needs to assess whether…
Skill Claude CodeCodex
LLM-driven epistemic reasoning engine. Evaluates claims against evidence, outputs calibrated confidence and structured belief state (VERIFIED/CONTESTED/UNCERTAIN). Use when the agent needs to assess whether information is trustworthy, detect contradictions in evidence, or quantify uncertainty.