Debugging agents in different environments

When an AI agent gives a bad answer, calls the wrong tool, or takes too long, you need to see what happened along the way.

In this two-part workshop series, Serge and Ryan will show you how to use Sentry Agent Tracing to understand and debug your agents. Start with the basics of traces and spans, then follow agents running in an ecommerce store, Slack, and GitHub Actions. In the second session, go inside Sentry to see how our engineers debug their own agents and find problems across large volumes of production traces.

October 7: Debugging Agents in different environments

An ecommerce chatbot, a Slack agent, and a PR review agent run in different environments. Each can fail across multiple steps, making the final response only part of the story.

Join Serge for an introduction to tracing and how it applies to AI agents. Through live walkthroughs, you’ll see how to follow an agent’s execution, inspect model and tool calls, and find where things went wrong. No prior tracing experience is needed.

You’ll learn how to:

• Read traces and spans, and understand the extra context agent tracing provides.
• Add agent tracing to an ecommerce chatbot, a custom Slack agent, and a PR review agent running in GitHub Actions.
• Inspect inputs, outputs, tool calls, and token usage to investigate errors and slow responses.

October 14: How Sentry debugs its own AI agents

How does Sentry debug the agents behind its own AI features?

Join Ryan and Serge for a look at how Sentry engineers use Agent Tracing in production. They’ll walk through how they collect traces, investigate agent behavior, and find failures worth investigating when there are too many traces to review one by one. You’ll see real examples and learn how to apply the same approach to your own agents.

This session will cover:

• How Sentry instruments and debugs its own agents.
• How engineers use traces to investigate unexpected behavior.
• How the team uses signals, such as user frustration, to find problems at scale.
• How to get started with agent tracing and review growing volumes of traces.