Writing skills for coding agents is easy; proving they actually work in a real browser took a lot of the engineering effort here.
Sharing our eval lessons at VibeKode Berlin (Nov 18): https://t.co/Mye9UxTBnt
& AI Summit Europe (Nov 25): https://t.co/GbMeNWNNBk
Left to their own devices, AI coding agents will happily write 100 lines of custom JavaScript for something modern HTML and CSS can do natively in a few lines.
Today, in partnership with @FirefoxWebDevs, @MozDevNet, and @MSEdgeDev, we're releasing Modern Web Guidance 1.0 with 200+ expert guides and Baseline support → https://t.co/lQXQBxUcx1
🚀 API Conference #Berlin session highlights:
AI agent governance, integration, APIs as product surfaces & agent interfaces — with Frederick Elewaut, @dret, Alpesh Pawar and @MHablich.
📍 Berlin
📆 November 16–20, 2026
👉 https://t.co/5UcgZpPeAI
#APIConference
@testy_cool@ChromiumDev a few things: 1.) the audit should be applicable for any significant browsing agent out there 2.) SEO is another topic anyways - but related. 3.) audit is experimental and will change, file feedback on our repo please.
That’s a first: GitHub’s Advisory Database (incorrectly) flags Puppeteer as malware. https://t.co/temhdomjPt We are no longer able to publish new releases.
Anyone at @github or @Microsoft who can escalate this, please?
We are entering the era of dual interface products:
- Rich UI for humans
- Token efficient API for agents
Your API is costing agents money.
I'm speaking at Agentic DevDays in Stockholm on April 28 to share how we are addressing this for @ChromeDevTools .
Want to give your agent quality checks?
Chrome's DevTools MCP now includes:
⚡️ Performance checks via Lighthouse
📈 Memory leak detection Skill
🦻 Accessibility debugging Skill
🎨 LCP optimization Skill
and an experimental new CLI 👀
The next version of OpenClaw is also an MCP, you can use it instead of Anthropic's message channel MCP to connect to a much wider range of message providers.
(I know, this is awkward)
Your #AI agent isn't picking the wrong tool because it's dumb. It's picking the wrong tool because your description didn't help it pick the right one.
Link: https://t.co/SPpVhBbGek
Wrote about something that's been on my mind: every browser #AI agent tool runs on CDP, which has zero auth. The security story is entirely in the layers around it. Checkout https://t.co/BKDG4I5RTN
@kurtextrem True and there will be a gravitational pull towards more optimized interfaces like WebMCP. I wonder if screenreaders/accessibility tools will also use WebMCP to do actions on a page, instead of trying to navigate the a11y tree.
1. We spent a decade building web performance metrics around human perception.
Turns out they matter just as much when your user is an AI agent.
The reasons are completely different. 🧵
6. The mental models still hold: set a budget, measure, optimize the critical path.
But the budgets change, the measurements change, and what counts as "critical" changes when the user doesn't have eyes.