Gemini Spark takes over desktop Chrome
Google's agent can now drive the desktop version of Chrome, using accounts you are already signed in to and passwords saved in the browser. It books property viewings, prepares flight searches, and fills in forms, handing the task back to the user to finalize a payment, accept terms, or create an account. This is the same pattern that has settled in with Claude and the rest: the agent does everything up to the step that cannot be undone, and a person confirms that step.
Source
Gemini Spark now integrates with ChromeGoogle: The Keyword, AI · Original published August 19, 2026
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 in forms, handing the task back to the user to finalize a payment, accept terms, or create an account. This is the pattern that has settled in with Claude and the rest: 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.
Sources
Corrections
Corrected on August 23, 2026: the piece said it came from secondhand reports and was not verified against a Google source, while Google's own post on Gemini Spark in Chrome was already its first source. Google's help page for auto browse has been added alongside it, and it settles what the piece left open: desktop Chrome only, the device language set to English, and a Google AI Pro or Ultra subscription. The description of where the agent stops was corrected with it — Google names finalizing a payment, accepting terms and creating an account, not payment alone. A rolling weekly page from an aggregator was removed as a source, because its content changes under the same address.
Related
A proxy that stripped one header was doubling Claude Code's API bill
Version 2.1.239 fixes streaming on Bedrock behind proxies that remove the response Content-Type header. Claude Code silently fell back to re-running every turn without streaming, and each turn was billed twice. The same release makes cost estimates show the 1.1× premium that data-residency workspaces pay.
Anthropicverified
ChatGPT now reads and sends your Apple Messages, on the Mac only
A plug-in in the ChatGPT desktop app reads and searches your iMessage, SMS and RCS threads and sends messages through Messages on your behalf. By default nothing goes out until you approve both the text and the recipients. There is a switch that removes that step, and OpenAI's own documentation argues against using it.
OpenAIverified
GitHub Copilot moved into Slack and Microsoft Teams on the same day
Both shipped on August 21 in public preview. Mention @GitHub in a channel and the agent triages issues, investigates failures, writes changes in a cloud sandbox and opens a pull request, with the conversation attached. The interesting part is not the capability list, which is familiar, but the room it moved into: the place where work gets discussed rather than written.
GitHubverified