Operations | Monitoring | ITSM | DevOps | Cloud

Building AI applications? There's a lot more to monitor beyond errors. With tracing enabled, Sentry's built-in AI Dashboards give you deep visibility into how your agents are actually performing. This video walks through three key dashboard views: You'll also see how to drill from a dashboard widget straight into the trace explorer to pinpoint the root cause of errors, how to duplicate and customize dashboards to fit your needs, and how to set up monitors with alert thresholds - like getting notified if your LLM calls exceed 20 seconds.

Use Sentry's Seer Agent to ask anything you need to know about your application. Use Seer Agent to: Email seer@sentry.io for access.

We released a new type of dashboard widget - Text Widgets! You can use them to explain other widgets (good for onboarding), or even define your playbooks - instructions on how to investigate failures by reading the other widgets. They even support markdown!

Cursor Automations + Sentry Triggers: go from user feedback to a pull request automatically. See how to set up an end-to-end workflow that turns feedback into code changes, posts the PR to Slack, and keeps your team in the loop. In this video, we walk through a real-world example using Sentry Docs. A user submits feedback through a widget on the docs site, it lands in Sentry as an issue, and when assigned, a Cursor Automation kicks off. The automation reads the feedback, validates it, generates a PR against the repo, and posts the link in the relevant Slack thread. No manual work required.

Most observability stacks aren’t designed, they accumulate. A logging tool here, a tracing platform there, and before you know it you’re managing rising costs and a setup that ultimately slows down your team. And you’ve moved further away from actually solving problems for your users.

Building with Next.js and using Sentry? Our team put together a dedicated Next.js Overview Dashboard that gives you a full picture of your application's health, not just errors. Out of the box, the dashboard covers page loads, API latency, issue counts, performance scores, rage and dead clicks, and slow SSR. Since Next.js runs on both client and server, you get a breakdown of client transactions, server transactions, and your SSR file tree all in one place.

Logging in Next.js is more difficult than you might think. Most logging libraries are only designed to run in Next.js. Some have "hacks" to work in the browser, but almost none will work in the Edge runtime where your middleware lives.

Next.js runs in up to three runtimes in a typical deployment, but most logging libraries only support one. Watch the full video.

​We put the internet’s loudest developers in one room at Chase Center. On purpose. Tune in for highlights from the event from: ​Wes Bos and Scott Tolinski: hosts of your favorite developer podcast, Syntax. Taught half of you how to actually use React. ​Teej and ThePrimeagen: sell coffee through the terminal, have over a million YouTube subscribers and even more opinions on memes.