Operations | Monitoring | ITSM | DevOps | Cloud

Getting Started with AI Agent Monitoring From Sentry

Sentry has released AI Agent monitoring, and in this video you can see the fast path to getting started with it using the Vercel AI SDK and Anthropic Claude. AI Agent Monitoring uses tracing to let you see details around how AI interactions are happening inside your application. You can see the back and forth conversation flow, token usage, model usage, durations, and much more. Agent Monitoring is out now, take it for a spin, let us know what you think in Discord!

Introducing AI Agent Monitoring in Sentry

Monitoring agents and LLM applications is... different. Managing everything from tool calls, to model configurations, token usage, and AI systems do their best to solve problems on their own - so errors aren't always clear. Sentry's agent monitoring focuses on making it easy to dive into your AI applications and understand whats breaking, where, so you can fix it faster.

Introducing Seer: Sentry's AI Debugging Agent

There's a lot more context to an error than the message blinking in red on your screen. Seer understands the context of your application and everything behind that error. Seer collects information from the Stack Trace, Logs, Traces and Spans, Profiles, and the code from your GitHub repo and uses it to understand what's causing your issues, and propose fixes.

Debugging Errors in Background Jobs

Debugging background jobs is one of those tasks that always sounds easier than it is—until you’re knee-deep in stack traces that offer no real clues. Background jobs love to run in isolated environments, cutting themselves off from all the helpful context you’d normally have. @nikolovlazar shows us how to debug these errors anyway—piecing together the missing context across systems so you can actually fix the problem instead of just guessing.