n. / AI agents

Agent evaluation

Definition

Agent evaluation is the practice of scoring AI agent behavior against versioned datasets using deterministic or model-based evaluators, instead of relying on manual spot checks.

← LLM tracing Time to first token (TTFT) →

In more detail

Evaluations can run offline, over a fixed dataset before a release, or online, scoring live production traces continuously. Both modes attach a repeatable score to a specific version of the agent, prompt, or model being tested.

Related terms

Tool call
AI engineering lifecycle

See it in a live trace

Definitions are the start.

Open a real trace and watch these terms move.

Open the demo Read the docs