Michael Hablich

Product Lead for @ChromeDevTools. Ideas my own. he/him

[Michael Hablich @MHablich]

@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.

[Michael Hablich @MHablich]

@C1B_nb @ChromiumDev eventually yes.

[Michael Hablich @MHablich]

@ChromeDevTools for agents is officially out of preview and now generally available! More infos: https://t.co/aKQ7KisW1K

[Mathias Bynens @mathias]

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?

[Michael Hablich @MHablich]

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 .

[Addy Osmani @addyosmani]

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 👀

[Michael Hablich @MHablich]

@ThoBustos Thanks for the pics!

[Michael Hablich @MHablich]

@qtnx_ @shijith @piniwit @b_roziere https://t.co/6TggKFU0LS

[Michael Hablich @MHablich]

@mistralvibe I would love to get working setup instructions for Mistral Vibe added to https://t.co/nvzi6x9cbr ... want to open a PR and cc me please?

[Michael Hablich @MHablich]

@shijith @qtnx_ @piniwit @b_roziere Exactly :-)

[Michael Hablich @MHablich]

@shijith @piniwit @qtnx_ @b_roziere Sadly radio silence :-/

[Michael Hablich @MHablich]

@MistralAI gentle ping 😺

[Michael Hablich @MHablich]

Oh, that's going to be interesting (in a good way)

[Peter Steinberger 🦞 @steipete]

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)

[Michael Hablich @MHablich]

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

[Michael Hablich @MHablich]

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

[Michael Hablich @MHablich]

@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.

[Michael Hablich @MHablich]

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. 🧵

[Michael Hablich @MHablich]

7. If you had to set a performance budget for agent users, what would you put in it?

#WebPerf #AIagents

[Michael Hablich @MHablich]

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.