Confidence Score (Agent)

A confidence score is a numerical estimate of how certain an AI agent is about its output or the correctness of a decision.

Agents with calibrated confidence scores can trigger escalation to human reviewers or request additional context when confidence falls below a threshold, making confidence-aware routing a practical governance control.

Closely related concepts include Confidence Score, Groundedness, Answer Faithfulness, Evaluation Harness (Agent). Each is defined in the Prefactor glossary.