Monitoring and Telemetry
Learn how to monitor the behavior of agents and APIs in Llama Stack using its built-in telemetry system. Explore structured logs, metrics, and traces that help us debug, analyze, and optimize AI applications.
As we build more complex systems incorporating agents, tools, safety measures, and retrieval mechanisms, understanding the internal workings becomes increasingly challenging. An agent might retrieve an incorrect document, call a tool improperly, or fail to complete a turn. Visibility is crucial, not just into the final output, but into every intermediate step.
That’s where telemetry comes in.