Gemini Spark takes over desktop Chrome

Google's Gemini Spark agent can now drive the desktop version of Chrome, using accounts you are already signed in to and passwords saved in the browser.

What it looks like in practice

It books property viewings, prepares flight searches, and fills forms, then hands the task back for you to finalize a payment, accept terms, or create an account. Claude and the rest have settled on the same shape: the agent does everything up to the step that cannot be undone, and a person confirms that step.

What it means for the sites you build

A growing share of visits comes from agents that read a page as structure rather than as a picture. That favors semantic HTML, clear labels on fields, and predictable forms — which is exactly what helps accessibility too.

The reverse also holds. Sites that lean on visual tricks, hand-rolled dropdowns without ARIA roles, and forms without real labels become harder for agents, and that will show up in completed purchases.

What is not confirmed yet

Google does not publish the list of countries where auto browse is available. It does publish the conditions: auto browse runs in desktop Chrome only, needs the device language set to English and a Google AI Pro or Ultra subscription, and works in neither Incognito mode nor a school account.