Google bakes computer control directly into Gemini 3.5 Flash, letting the model see and operate your screen

2026-06-25 · Source: The Decoder · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems · Depth: Intermediate, quick

Summary

Google has integrated "Computer Use" directly into Gemini 3.5 Flash, enabling the model to autonomously operate computers, web browsers, and mobile devices. This significant advancement allows developers to build sophisticated agents via the Gemini API for various applications requiring direct system interaction. On the OSWorld benchmark, Gemini 3.5 Flash achieved a score of 78.4, placing its performance on par with GPT-5.5. This capability facilitates the creation of AI-driven solutions for tasks such as automated software testing, complex office automation, and other scenarios where AI models need to directly control digital environments.

Key takeaway

For AI Engineers developing automation solutions, Gemini 3.5 Flash's direct computer control capability means you can now build agents that operate systems autonomously. Consider integrating the Gemini API to streamline software testing workflows or automate complex office tasks, potentially reducing manual effort and accelerating development cycles. This feature offers a new paradigm for creating intelligent agents that interact directly with digital environments.

Key insights

Gemini 3.5 Flash now directly controls computers, enabling autonomous agent development.

In practice

• Software testing automation
• Office task automation

Topics

• Gemini 3.5 Flash
• Computer Use
• AI Agents
• OSWorld Benchmark
• Gemini API
• Software Testing
• Office Automation

Best for: Machine Learning Engineer, CTO, AI Architect, AI Engineer, Software Engineer, Automation Engineer

Related on AIssential

• Introducing computer use in Gemini 3.5 Flash — Gemini 3.5 Flash now natively supports "computer use" for building advanced, cross-platform automation agents with enhanced safety features.
• With Gemini 3.5 Flash, Google bets its next AI wave on agents, not chatbots — Google's Gemini 3.5 Flash shifts AI from conversational to autonomous agentic capabilities, excelling in speed and complex task execution.
• Google launches Gemini 3.5 Flash as its default AI model — Google's Gemini 3.5 Flash offers high-speed, cost-effective AI for agentic tasks, becoming the default model.
• Introducing computer use in Gemini 3.5 Flash — Gemini 3.5 Flash now natively supports "computer use" for building cross-platform automation agents with enhanced safety features.
• Gemini 3.5 Flash has landed. — Gemini 3.5 Flash offers frontier intelligence with four times faster output speed and improved benchmark performance.
• Demis Hassabis Thinks AI Job Cuts Are Dumb — Gemini 3.5 Flash excels at complex agentic coding, challenging views on AI-driven job displacement.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The Decoder.