Since AI coding tools went mainstream, the web has been gaining weight fast. Research shows the average site's JavaScript has grown three times faster than before. The reason is simple: AI writes code that looks right, not code that runs fast. And here's the irony, most AI crawlers can't even read the heavy sites that AI built, because they don't run JavaScript.

The good news: the same AI agents that caused this can help fix it. In 2025, Chrome DevTools MCP gave AI agents the ability to actually measure what they build. Combined with Agent Skills, we can turn an AI agent into something closer to a careful performance engineer.
In this talk we look at three things:

- The data: what really happened to the web after November 2022
- The cause: why AI writes slow code, and why it couldn't see what it shipped
- The fix: a working protocol you can use, with Chrome DevTools MCP and a performance skill you can install today

You leave with a ready-to-use performance skill, real before/after numbers, and a clear way to make AI build faster sites instead of heavier ones.

Target audience: Frontend developers, performance engineers, tech leads working with AI coding tools.

Level: Intermediate. You should know what LCP and bundle size mean. You don't need to know what MCP or Agent Skills are, we'll cover that.

Preferred duration: 30 minutes. Can be extended to 40 with more case studies, or condensed to 20.

Technical requirements: Projector, audio, stable wifi for live demo. A recorded backup of the demo is included.

Languages: English. Dutch on request.

Sources: Based on research by Ethan Gardner (HTTPArchive analysis), Addy Osmani (Web Performance Engineering in the Age of AI, O'Reilly 2026), and Vercel's AI crawler study.