Michael Hablich @MHablich

Product Lead for @ChromeDevTools. Ideas my own. he/him Österreich Joined November 2013

Tweets

2K
Followers

1K
Following

275
Likes

1K

Michael Hablich @MHablich

a week ago

@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.

0 0 1 92 0

View Details

Michael Hablich @MHablich

a week ago

@C1B_nb @ChromiumDev eventually yes.

0 0 0 48 0

View Details

Michael Hablich @MHablich

3 weeks ago

@ChromeDevTools for agents is officially out of preview and now generally available! More infos: developer.chrome.com/docs/devtools/…

0 0 1 63 0

View Details

Mathias Bynens @mathias

4 weeks ago

That’s a first: GitHub’s Advisory Database (incorrectly) flags Puppeteer as malware. github.com/github/advisor… We are no longer able to publish new releases. Anyone at @github or @Microsoft who can escalate this, please?

3 10 49 12K 8

View Details

Michael Hablich @MHablich

2 months ago

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 .

0 0 0 47 0

View Details

Addy Osmani @addyosmani

2 months ago

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 👀

41 151 1K 130K 998

View Details

Michael Hablich @MHablich

2 months ago

@ThoBustos Thanks for the pics!

1 0 1 7 0

View Details

Michael Hablich @MHablich

2 months ago

@qtnx_ @shijith @piniwit @b_roziere github.com/ChromeDevTools…

0 0 0 26 0

View Details

Michael Hablich @MHablich

3 months ago

@mistralvibe I would love to get working setup instructions for Mistral Vibe added to github.com/ChromeDevTools… ... want to open a PR and cc me please?

3 1 3 3K 2

View Details

Michael Hablich @MHablich

2 months ago

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

1 0 1 32 0

View Details

Michael Hablich @MHablich

2 months ago

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

1 0 0 52 0

View Details

Michael Hablich @MHablich

2 months ago

@MistralAI gentle ping 😺

0 0 0 57 0

View Details

Michael Hablich @MHablich

2 months ago

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

Peter Steinberger 🦞 @steipete

2 months ago

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)

247 234 4K 815K 1K

0 0 0 100 0

View Details

Michael Hablich @MHablich

3 months ago

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: hablich.dev/articles/disco…

0 0 0 54 0

View Details

Michael Hablich @MHablich

3 months ago

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 hablich.dev/articles/trust…

0 0 0 32 0

View Details

Michael Hablich @MHablich

3 months ago

@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.

0 0 0 17 0

View Details

Michael Hablich @MHablich

3 months ago

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. 🧵

2 0 1 127 0

View Details

Michael Hablich @MHablich

3 months ago

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

0 0 0 27 0

View Details

Michael Hablich @MHablich

3 months ago

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.