Sentry Engineers Show How They Debug Their Own AI Agents with Agent Tracing
Summary
Sentry engineers Ryan and Serge show how the company traces its own AI agents in production, using Agent Tracing to collect traces, investigate unexpected behavior, and surface failures too numerous to review individually. They describe using signals such as user frustration to find problems at scale. The session is part two of a workshop series on debugging agents.
Key Points
- Sentry says Serge covered traces and spans in part one, following agents in an ecommerce store, Slack, and GitHub Actions.
- Sentry sponsors the Syntax Podcast, which the company points listeners to on their preferred listening platform.
- Sentry is a registered trademark of Functional Software, Inc., per the footer of the workshop page.