Observability for agents

Observability for agents enables measurement of a system's internal state, including reasoning traces, tool calls, and latent model outputs, by analyzing its external telemetry and structured logs. When building agents, you may need these features to help debug and diagnose their in-process behavior. Basic input and output monitoring is typically insufficient for agents with any significant level of complexity.

Agent Development Kit (ADK) provides configurable logging functionality for monitoring and debugging agents. However, you may need to consider more advanced observability ADK Integrations for monitoring and analysis.

ADK Integrations for observability

For a list of pre-built observability libraries for ADK, see Tools and Integrations.