Testing systems that use generative AI requires a new approach. Because models produce probabilistic outcomes, a single user input can lead to thousands of different answers with varying degrees of accuracy. We just released a guide on WebMCP evals to test your system's exact touchpoints with an LLM. This allows you to systematically verify that a model understands your tool's purpose based on its schema and correctly acts upon the information it receives. Check out the full guide to see how to verify that agents pick the right parameters for user intent and successfully fulfill entire user journeys → https://goo.gle/4ftQUZI #GoogleIO
Chrome for Developers
Technology, Information and Internet
Helping you build, grow, and innovate on the web.
About us
The official Chrome for Developers LinkedIn account from Google. We want to help you build beautiful, accessible, fast, and secure websites that work cross-browser, and for all of your users.
- Website
-
https://developer.chrome.com/
External link for Chrome for Developers
- Industry
- Technology, Information and Internet
- Company size
- 5,001-10,000 employees
Updates
-
Chrome DevTools for agents changes how AI optimizes your web apps. Instead of letting a coding agent guess from static source code and burning tokens, this allows your AI to run actual performance traces and agentic web Lighthouse audits in a real browser. #GoogleIO
-
AI coding tools are incredibly powerful at writing code, but they are often disconnected from its execution. They can generate a complex web app, but they cannot observe its behavior or inspect its output in a live browser. Chrome DevTools for agents provides your coding agent with the visibility it needs to verify, debug, and optimize code in real time. A couple of months ago we showed it for the first time, and now we are excited to announce that Chrome DevTools for agents is now available as a stable 1.0 release → https://goo.gle/42K7Rrl #GoogleIO
-
-
Lighthouse is getting a new agentic browsing category. Instead of just auditing for human users, it tracks WebMCP schemas and layout shifts to see if AI agents can actually navigate your site. If machine-readability is on your roadmap, this is worth a look → https://goo.gle/3ReK3JD #GoogleIO
-
-
Backstage setup ➡️ Talking shop at the demo booth. A quick look at Una Kravets, Matthias Rohmer, Thomas Steiner, PhD and Mark Thompson's #GoogleIO journey.
-
Chrome for Developers reposted this
Modern Web Guidance + Chrome DevTools for agents = A powerful new workflow. 🛠️ Matthias Rohmer takes you inside the #GoogleIO Chrome Dev Prompt Lab to demo the next generation of web development. See coding agents in action and learn how to leverage AI evaluators for your projects. Watch the full session: https://goo.gle/4dxkzQv Read the top 15 Chrome announcements: https://goo.gle/4dDyJPP
-
Signing in shouldn’t feel like a hurdle for your users. As we discussed at #GoogleIO, authentication needs to be a secure, seamless entry point that builds trust from the very first click. This guide breaks down how you can optimize your identity flows, slash user friction, and implement robust security protections from day one → https://goo.gle/3Rd5TgI
-
Chrome for Developers reposted this
My talk on Modern Web Guidance is up! https://lnkd.in/g63SABHS This talk is a deep dive into how Modern Web Guidance works and why it's useful. 👉 Make sure you watch until the end, where I show some live demos that really highlight this tool's capabilities!
Unlock modern web capabilities in your AI coding workflows
https://www.youtube.com/
-
Chrome for Developers reposted this
At this year's Google I/O, Una Kravets and I delivered the “What's new in Web UI” talk, a talk that has become a bit of tradition by now 😊 https://lnkd.in/eaJEB6SB I might need to recount, but I think we cover 34 (!!) new #CSS and Web UI features in under 45 minutes. Every demo shown in the talk has a link, and there's also a ton of links to articles/explainers included throughout. Honored that I got join Una on the stage and that we get to present some of the nicer things our engineering teams have been working on. I'm very happy with how it went, and I think you might find it useful, so why not give it a watch? 😊
-
Personalized AI features don't have to be cost-prohibitive to scale. Trip.com is experimenting with built-in AI using Gemini Nano to process complex flight searches and summarize travel data locally. By moving inference to the client side, engineering teams will significantly reduce server overhead and token cost, all while delivering a highly responsive user experience. #GoogleIO