AI Agents Drift: Identifying and Correcting Subtle Failures

Ivan’s first attempts at performance debugging were chaotic. He would see a slow interaction, try a random optimization, see that it didn't help, and keep trying other optimizations until he found the right one (or gave up).
Back then, Ivan didn’t know how to use performance devtools well. He would do a recording in Chrome DevTools or React Profiler, poke around it, try clicking random things, and then close it in frustration a few minutes later. Now, Ivan knows exactly where and what to look for. And in this workshop, Ivan will teach you that too.
Here’s how this is going to work. We’ll take a slow app → debug it (using tools like Chrome DevTools, React Profiler, and why-did-you-render) → pinpoint the bottleneck → and then repeat, several times more. We won’t talk about the solutions (in 90% of the cases, it’s just the ol’ regular useMemo() or memo()). But we’ll talk about everything that comes before – and learn how to analyze any React performance problem, step by step.
(Note: This workshop is best suited for engineers who are already familiar with how useMemo() and memo() work – but want to get better at using the performance tools around React. Also, we’ll be covering interaction performance, not load speed, so you won’t hear a word about Lighthouse 🤐)

Frontend issues that affect your users are often triggered by backend problems. In this workshop, you’ll learn how to identify issues causing slow web pages and poor Core Web Vitals using tracing.
Then, try it for yourself by setting up Sentry in a ready-made Next.js project to discover performance issues including slow database queries in an interactive pair-programming session.
You’ll leave the workshop being able to:- Find backend issues that might be slowing down your frontend apps- Setup tracing with Sentry in a Next.js project- Debug and fix poor performance issues using tracing
This will be a live 2-hour event where you’ll have the opportunity to code along with us and ask us questions.

Ivan’s first attempts at performance debugging were chaotic. He would see a slow interaction, try a random optimization, see that it didn't help, and keep trying other optimizations until he found the right one (or gave up).
Back then, Ivan didn’t know how to use performance devtools well. He would do a recording in Chrome DevTools or React Profiler, poke around it, try clicking random things, and then close it in frustration a few minutes later. Now, Ivan knows exactly where and what to look for. And in this workshop, Ivan will teach you that too.
Here’s how this is going to work. We’ll take a slow app → debug it (using tools like Chrome DevTools, React Profiler, and why-did-you-render) → pinpoint the bottleneck → and then repeat, several times more. We won’t talk about the solutions (in 90% of the cases, it’s just the ol’ regular useMemo() or memo()). But we’ll talk about everything that comes before – and learn how to analyze any React performance problem, step by step.
(Note: This workshop is best suited for engineers who are already familiar with how useMemo() and memo() work – but want to get better at using the performance tools around React. Also, we’ll be covering interaction performance, not load speed, so you won’t hear a word about Lighthouse 🤐)

Learn the ways of the clinic suite of tools, which help you detect performance issues in your Node.js applications. This workshop walks you through a number of examples, and the knowledge required to do benchmarking and debug I/O and Event Loop issues.

You just shipped a new feature. Tests passed. CI’s green. Everything’s deployed. Life’s good… until the alerts start rolling in. Users reporting “weird stuff happening”, UI glitches, vague “it seems slow” reports, and that dreaded “can’t login” message. Well, this is shaping up to be a bad day. But… maybe not.Watch this hands-on session to learn how to build it, break it, debug it, and go from “no idea what’s wrong” to fixing issues—all in one go. Since we’re serious developers (obviously), we’ll use Next.js and:Setup Sentry from the ground up - including Errors, Session Replay, and TracingLearn ways to use Replays to understand the real user experience, and how to use Tracing to debug application issuesLeverage Sentry AI and the context of your application to understand what’s actually broken, and use Autofix to generate a fix - from root cause all the way to PR.Use this workshop guide to follow along: Quickstart Guide.

You know that annoying bug? The one that doesn’t show up locally? And no matter how many times you try to recreate the environment you can’t reproduce it? You’ve gone through the breadcrumbs, read through the stack trace, and are now playing detective to piece together support tickets to make sure it’s real.
Join Sentry developer Ryan Albrecht in this talk to learn how developers can use Session Replay - a tool that provides video-like reproductions of user interactions - to identify, reproduce, and resolve errors and performance issues faster (without rolling your head on your keyboard).