@_philschmid: Yesterday we launched computer use in Gemini 3.5 Flash with browser, mobile, and desktop environments. I put together a…

X AI KOLs Timeline 06/25/26, 04:07 PM Products

computer-use gemini-3.5-flash android mobile quickstart automation adb

Summary

Phil Schmid announces the launch of computer use in Gemini 3.5 Flash, enabling control of browser, mobile, and desktop environments, with a quickstart guide for controlling Android phones via adb.

Yesterday we launched computer use in Gemini 3.5 Flash with browser, mobile, and desktop environments. I put together a quickstart for how to control an Android Phone. 1. Single script to install emulator from terminal. 2. Basic agent loop with interactions API using `adb` to control the phone. 3. Connects to remote devices too (`adb connect <ip>:5555`). 4. Same pattern works for iOS with, e.g. simctl.

Original Article

View Cached Full Text

Cached at: 06/26/26, 02:04 AM

Yesterday we launched computer use in Gemini 3.5 Flash with browser, mobile, and desktop environments. I put together a quickstart for how to control an Android Phone.

Single script to install emulator from terminal.
Basic agent loop with interactions API using adb to control the phone.
Connects to remote devices too (adb connect <ip>:5555).
Same pattern works for iOS with, e.g. simctl.

Similar Articles

@_philschmid: https://x.com/_philschmid/status/2070176665045434477

X AI KOLs Following

A guide and Python script for controlling an Android emulator using Gemini 3.5 Flash's Computer Use capability, which allows the model to view screenshots and return actions (taps, clicks, text input) to be executed via ADB.

Introducing computer use in Gemini 3.5 Flash

Google DeepMind Blog

Gemini 3.5 Flash now natively supports computer use as a built-in tool, enabling developers to build agents that can interact across browser, mobile, and desktop environments for long-horizon automation tasks like software testing and knowledge work.

Computer use in Gemini 3.5 Flash

Hacker News Top

Google announces that computer use is now a built-in tool in Gemini 3.5 Flash, enabling developers to build agents that can see, reason, and take action across browsers, mobile, and desktop environments.

@_philschmid: I'm excited to introduce Managed Agents in the Gemini API. One API call gives you a full agent with code execution, web…

X AI KOLs Following

Phil Schmid announces Managed Agents in the Gemini API, enabling one-call agents with code execution, web browsing, and file management in isolated sandboxes, powered by Gemini 3.5 Flash.

@chetaslua: Gemini 3.5 Flash built a full Ubuntu/GNOME web OS in ONE shot. single HTML file, embedded CSS + JS. from one prompt: >w…

X AI KOLs Timeline

Gemini 3.5 Flash generated a fully functional Ubuntu/GNOME-style web OS in a single HTML file from a single prompt, including dock, terminal, file manager, window management, and settings.