Profiling JavaScript is mostly easy. However, how do you profile gnarly performance issues? In this talk, you’ll learn a practical AI-assisted workflow for finding rendering bottlenecks fast. Using a real-world CSS performance bug, we’ll cover techniques like commit bisection, standalone reproductions, synthetic stress tests, and auto-generated lint rules to prevent regressions. We choose CSS because it is famously difficult to profile -- there are no stack traces, obvious breakpoints, or clear debugging workflows, which is why many rendering bugs go unfixed until users complain that the page feels slow. However, the same methodology can be used in dealing with other performance issues. You’ll also see how to use the Chrome DevTools MCP to give Claude direct access to a live browser session and accelerate investigation without replacing engineering judgment. The result is a repeatable process for going from “the page feels slow” to a pinpointed line of CSS in under an hour.
