Introducing computer use in Gemini 3.5 Flash

2026-06-24 · Source: Google DeepMind News · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems · Depth: Intermediate, medium

Summary

Google DeepMind has integrated "computer use" as a built-in tool within its Gemini 3.5 Flash model, announced on June 24, 2026. This capability, previously a standalone Gemini 2.5 computer use model, now allows developers to build custom agents that can see, reason, and act across browser, mobile, and desktop environments. The integration aims to deliver improved performance for agentic "computer use" tasks, specifically targeting long-horizon and enterprise automation, such as continuous software testing and knowledge work in professional applications. To address prompt injection risks, Gemini 3.5 Flash employs targeted adversarial training and offers two optional enterprise safeguard systems: explicit user confirmation for sensitive actions and automatic task stoppage upon indirect prompt injection detection. Developers can access this feature through the Gemini API and Gemini Enterprise Agent Platform.

Key takeaway

For AI Engineers developing automation solutions, Gemini 3.5 Flash's integrated computer use capability changes how you approach agent design. You can now build more robust, cross-platform agents for tasks like software testing or knowledge work, directly using the model's native tool capabilities. Implement the optional enterprise safeguards and defense-in-depth practices to mitigate prompt injection risks and ensure secure, reliable agent deployments. Explore the Gemini API and Enterprise Agent Platform to begin building your advanced automation agents.

Key insights

Gemini 3.5 Flash now natively supports "computer use" for building advanced, cross-platform automation agents with enhanced safety features.

Principles

• Agentic computer use improves automation.
• Defense-in-depth enhances AI safety.
• Native integration boosts model performance.

In practice

• Build agents for cross-platform automation.
• Automate continuous software testing.
• Implement enterprise safeguard systems.

Topics

• Gemini 3.5 Flash
• Computer Use
• AI Agents
• Enterprise Automation
• Prompt Injection
• AI Safety

Code references

• google-gemini/computer-use-preview

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Engineer, MLOps 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 cross-platform automation agents with enhanced safety features.
• Gemini 3.5 Flash: Frontier Intelligence with Speed — Gemini 3.5 Flash delivers rapid, low-latency AI for agentic workflows, coding, and multimodal reasoning.
• Demis Hassabis Thinks AI Job Cuts Are Dumb — Gemini 3.5 Flash excels at complex agentic coding, challenging views on AI-driven job displacement.
• 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 CEO: Agents, Open Source, Race to AGI, Cybersecurity, Chips, China — Agents will fundamentally reshape internet interaction, demanding trust, control, and efficient, responsible AI development.
• TAI #206: Gemini 3.5 Flash Is Stronger, But Flash Is No Longer Cheap — Google's latest Gemini models offer strong capabilities but come with significantly increased costs and deployment challenges.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Google DeepMind News.