Reading agent traces
A trace shows every model call and tool call behind one agent answer, with timings, status and token counts. Use it like a QA engineer to find a slow tool, a failed tool call hidden behind a polite answer, and a model call that costs far too much.
Checking your access…
This is a Pro lesson
Sign in to continue. Pro members get every animated lesson, its code and its quiz, across ADK, Agent Platform, Agent QA and CX Agent Studio.
You're signed in, but this lesson is part of Pro
Get every Pro lesson, its code and its quiz for ₹999, once. Lifetime access, including lessons added later.
Unlocking your lesson…
If this doesn't change in a moment, reload the page.
In this module: Observability with OpenTelemetry
- OpenTelemetry for agents Traces, spans and attributes, from first principles. Pro
- Set up tracing on Agent Runtime Sending agent traces to Cloud Trace. Pro
- Logging and monitoring Logs, metrics and dashboards for deployed agents. Pro
- Reading agent traces Finding the slow, failing or expensive step. Pro
- Monitoring gateway traffic Gateway metrics and Model Armor spans. Pro