Why is my agent doing that? OTel 101: Live agent instrumentation
Too often, agent debugging comes down to print statements. We add OpenTelemetry to a plain agent, walk through the resulting trace, and see it come together in Pydantic Logfire.
OTel 101: Live agent instrumentation.
Overview
- 30 min
- On demand replay
- Online event
- Free
Speaker
About this recording
Too often, agent debugging still comes down to print statements and logs. The agent is the one piece of the stack nobody can see into, and the one piece that fails in ways nothing else does. It doesn't have to stay that way. OpenTelemetry already traces the rest of your stack, and it works for agents too.
In this session we add OpenTelemetry to a plain agent and walk through the resulting trace: which spans matter, which are noise, and how a specific span ties back to why the agent did what it did. Then we use Pydantic Logfire to see what your agent is doing once it's running in production. No prior OpenTelemetry experience needed.
A 30-minute session, with questions at the end.
What you'll learn
- What OpenTelemetry is, and why it's the observability standard for AI
- How to instrument an agent, and what's worth capturing
- How to trace a bad run back to its cause
- How this scales out to real-world deployments
Watch the recording
Tell us where to send Pydantic updates and unlock instant access to this replay.
You're all set
Your request was received. You can close this page.
We couldn't open the recording
Please go back and try again in a moment.
Explore Logfire
Explore our open source packages
