confidence-scoring
Deterministic structured extraction from noisy LLM/OCR output. Zero LLM round-trips, microsecond latency, confidence score on every result. msgspec · Pydantic · dataclasses.
Selective prediction based on uncertainty scores
Framework-agnostic confidence-gated escalation middleware for LLM agents: multi-signal scoring (logprob, verbalized, tool risk), threshold policies, and escalation handlers for LangChain, CrewAI, AutoGen, and Google ADK.
MFGC confidence scoring and safety gates for AI agents. Zero dependencies.
