# Observability

See what your agents do in production: what they log, how long each step takes, what each model call cost, and whether the process is healthy.

- [Monitor agents](monitor.md): structured logs, OpenTelemetry traces and metrics, a Prometheus endpoint, health checks and structured agent traces.
- [LLM calls](llm-calls.md): capture every model call as an `LLMCallLog` event with prompt, response, usage, cost and timing, or trace it as a GenAI span.
- [Sampling](sampling.md): decide per event whether to capture, drop or down-sample, and cap volume per tenant.

To score what agents answer rather than how they run, see [Evaluation](../evaluation/index.md).