AI BriefingGoogleFeature Updates16:21
AI summarized from verified sources
Build agents that directly control screens with Gemini 3.5 Flash
Easier automation of tasks involving complex screen interactions.
SOURCE CHECK
1 sources
Sources
Key Points
- 1Native screen recognition and control
- 2Supports browser, mobile, desktop
- 3Immediately available for developers
Google DeepMind added native computer use to Gemini 3.5 Flash. Developers can now build custom agents that see and act across browser, mobile, and desktop interfaces.
Key points
The new feature lets AI directly view and perform clicks or inputs on screens. Developers can quickly create practical agents with this capability.
Impact
Automation of tasks requiring web or app interaction advances, reducing developer workload.