Laravel AI agents now trace themselves.
Update to sentry-laravel 4.27 and every agent invocation, LLM call, and tool call shows up in Agent Tracing — no Sentry code required 🙂↔️
Check out the full blog post 👇
Our AI search assistant returned no results, even though the data was there. The prompt was wrong.
Here’s how we used agent tracing to follow the tool calls, find the bug, and verify the fix—without spelunking through JSON 🤝
Kyle Tryon built video size estimator. The AI-written version turned out to be up to 83% off, and manual testing wasn't catching it.
Read the full blog about how he used Sentry Application Metrics to fix it 👇
Everyone wants to spend less time fixing bugs, including us.
So we built an automated debugging workflow using our Seer agent in Slack, Claude routines, and Seer autofix.
Check out the full blog by @dhrumilPM to see how we did it 👇
We got a little behind on updating our changeLOG, so we’re dumping it all into this bLOG post instead.
Here’s everything that shipped for Sentry Logs this summer 🪵
Your AI agent finished successfully, but was it actually right?
We built a daily Claude Routine that inspects both failed and successful conversations using Sentry Agent Tracing.
Read the full blog by @rovert_snikle 👇
If you export OTel to Sentry and still can’t jump from error ➡️ span, you’re missing the bridge.
OtlpIntegration does that wiring for you 👀 check it out in the new blog