Learnijoy
NewsAI Engineering & DevToolsAI News & Tools

Gemini 3.5 Flash Now Supports Native Computer Interaction

@GoogleDeepMind· June 25, 2026 View original

▶ The 2-minute explainer

Summary

Gemini 3.5 Flash now offers native computer use, enabling developers to build custom AI agents that can interact across browser, mobile, and desktop interfaces. This new capability allows agents to perceive and act within various digital environments.

Google has announced a significant upgrade to its Gemini 3.5 Flash model, which now includes native computer interaction capabilities. This enhancement allows the AI model to directly perceive and execute actions across a wide range of digital platforms, including web browsers, mobile applications, and desktop environments. The new built-in tool empowers developers to create sophisticated custom agents. These agents can effectively "see" what's on a screen and "take action" within those interfaces, opening up possibilities for highly integrated and automated workflows.

Why it matters

This development is crucial for professionals looking to automate complex digital tasks and build more versatile AI agents that can operate seamlessly across different computing environments. It significantly expands the potential applications of AI in workflow automation and intelligent assistance.

How to implement this in your domain

  1. 1Explore the Gemini 3.5 Flash API documentation for native computer interaction features.
  2. 2Design and prototype custom agents that automate repetitive tasks across web, mobile, or desktop applications.
  3. 3Integrate these agents into existing business processes to enhance efficiency and reduce manual effort.
  4. 4Develop new AI-powered tools that leverage cross-platform interaction for novel user experiences.

Who benefits

Software DevelopmentIT AutomationCustomer ServiceBusiness Process Outsourcing

Key takeaways

  • Gemini 3.5 Flash now allows AI agents to interact natively with computers.
  • Developers can build custom agents that operate across browser, mobile, and desktop.
  • This feature enables advanced automation and integrated AI workflows.
  • The capability expands the scope for AI-driven task execution.

Original post by @GoogleDeepMind

"Gemini 3.5 Flash now supports native computer use. This built-in tool lets developers build custom agents that can see and take action across browser, mobile, and desktop interfaces. Find out more →"

View on X

Primary sources

Originally posted by @GoogleDeepMind on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses

More in AI Engineering & DevTools

AI Engineering & DevToolsAI News & Tools

MCP and A2A Protocols Standardize Agentic Internet Development

The Model Context Protocol (MCP) and Agent-to-Agent (A2A) Protocol are standardizing how AI agents discover tools, call services, and coordinate across systems. Understanding these protocols is crucial for developers building agent-compatible infrastructure.

Theo VasilisJun 28, 2026
VISReg Enhances JEPA Training with Novel Regularization
Video
AI ResearchAI Engineering & DevTools

VISReg Enhances JEPA Training with Novel Regularization

A new research paper introduces VISReg, a Variance-Invariance-Sketching Regularization technique designed to improve the training of Joint Embedding Predictive Architectures (JEPA). This method aims to create more robust and generalizable self-supervised learning models.

@_akhaliqJun 28, 2026
AI News & ToolsAI Engineering & DevTools

Ford's AI-Driven Layoffs Backfire Significantly

Ford reportedly replaced human workers with AI, a decision that subsequently led to severe negative repercussions for the company.

speckxJun 28, 2026