cd /news/artificial-intelligence/gemini-in-chrome-adds-select-from-sc… · home topics artificial-intelligence article
[ARTICLE · art-38209] src=9to5google.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

Gemini in Chrome adds ‘Select from screen’ tool as Gemini 3.5 Flash gains computer use

Google's Gemini in Chrome now includes a 'Select from screen' tool that lets users add images to prompts, rolling out with Chrome 149. Separately, the Gemini 3.5 Flash model gains native computer use capabilities for developers to build custom agents that can interact with browser, mobile, and desktop environments.

read1 min views1 publishedJun 24, 2026
Gemini in Chrome adds ‘Select from screen’ tool as Gemini 3.5 Flash gains computer use
Image: 9To5Google (auto-discovered)

Gemini in Chrome now lets you focus a prompt with a new “Select from screen” tool, while developers can tap into Gemini 3.5 Flash computer use capabilities.

Gemini in Chrome now has a “Select from screen” tool that lets you quickly add an image to prompts. You can find it at the bottom of the ‘plus’ menu.

This highlights your current tab and has you “Select any text or image to ask Gemini.” Afterwards, that image is added to the prompt box.

Select from screen is rolling out as part of Chrome 149, with a browser restart introducing the feature if you’re not seeing it yet. In other related developments, Google announced today that the Gemini 3.5 Flash model now has a built-in computer use tool. Joining Search and Maps grounding, this native integration replaces the standalone Gemini 2.5 Computer Use model.

Developers can use the new functionality to “build custom agents that can see, reason and take action across browser, mobile and desktop environments.”

Improved long-horizon and enterprise automation task performance allows for “continuous software testing and knowledge work across professional applications.”

In the example below, 3.5 Flash leverages computer use to “analyze the Gemini app and return a categorized list of features.”

On the safety front, enterprise customers can:

  • Require explicit user confirmation for sensitive or irreversible actions.
  • Automatically stop tasks if an indirect prompt injection is identified.

Gemini 3.5 Flash is available today in the Gemini API.

Try it now: Test the capabilities in a[demo environment hosted by Browserbase.]Start building: Dive into our[reference implementation]and documentation via[Gemini API]and[Gemini Enterprise Agent Platform].

*FTC: We use income earning auto affiliate links.* [More.](https://9to5mac.com/about/#affiliate)

[our homepage](http://9to5google.com/)for all the latest news, and follow 9to5Google on

[exclusive stories](https://9to5google.com/feature/exclusive/),

[reviews](https://9to5google.com/guides/reviews/),

[how-tos](https://9to5google.com/guides/how-to/), and

[subscribe to our YouTube channel](https://www.youtube.com/9to5google)
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @google 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/gemini-in-chrome-add…] indexed:0 read:1min 2026-06-24 ·