Introducing computer use in Gemini 3.5 Flash

@GoogleAIStudio
英語3 週前 · 2026年6月24日
186K
2.1K
232
87
989

TL;DR

Google has integrated native computer use into Gemini 3.5 Flash, allowing developers to build cost-effective AI agents that can interact with software across desktop and mobile environments with enterprise-grade safety.

Computer use is now a built-in tool supported in Gemini 3.5 Flash, delivering our best performance yet for agentic computer use tasks. Previously only available as a standalone Gemini 2.5 computer use model, computer use is now integrated natively in the main Gemini Flash model. Gemini already excels at function calling and using built-in tools like Search and Maps grounding. With built-in computer use capability, developers can now use 3.5 Flash to reliably build custom agents that can see, reason and take action across browser, mobile and desktop environments. This unlocks improved performance for long-horizon and enterprise automation tasks like continuous software testing and knowledge work across professional applications.

Google AI Studio - inline image
Google AI Studio - inline image

3.5 Flash uses computer use to analyze Gemini app and return a categorized list of features

Google AI Studio - inline image

Flash with computer use audits its own documentation for accessibility issues

Making computer use safe in 3.5 Flash

To mitigate some of the prompt injection risks for agents operating in live environments, we use targeted adversarial training for computer use in Gemini 3.5 Flash. We’re also releasing two optional enterprise safeguard systems that enable enterprises to:

  • Require explicit user confirmation for sensitive or irreversible actions.
  • Automatically stop tasks if an indirect prompt injection is identified.

Taking a “defense-in-depth” approach, we encourage developers to combine these features with secure sandboxing, human-in-the-loop verification, and strict access controls. Additional information on safety measures can be found in our best practices documentation.

We are already seeing customers drive value with computer use. Here’s what some of them have to say:

  • Browserbase: “On OnlineMind2Web and private benchmarks, Gemini 3.5 Flash with Computer Use delivers comparable accuracy to frontier models with better cost and latency, making complex, long-horizon browsing tasks affordable to run at scale.” Miguel González Fernández - Browserbase
  • Browser Use: “Gemini 3.5 Flash is a clear step up from the previous Flash generation on agentic browser-use harnesses. It catches up to frontier-level performance while keeping the speed and cost profile that makes Google our #1 choice at scale.” Magnus Müller, CEO - Browser Use
  • UiPath: “Gemini 3.5 Flash adapted particularly well to the UiPath computer use harness that powers agents like Delegate and ScreenPlay. Gemini 3.5 Flash delivers high throughput, strong reliability, and the best price-performance ratio among the models we evaluated for computer use, all while being easy to steer.” Alvin Stanescu, Senior Director- UiPath

To start building with computer use today:

一鍵儲存

使用 YouMind AI 深度閱讀爆款文章

保存原文、追問細節、總結觀點,並在一個 AI 工作空間裡把爆款文章沉澱成可複用筆記。

了解 YouMind
寫給創作者

把你的 Markdown 變成乾淨的 𝕏 文章

圖片上傳、表格、程式碼區塊,往 𝕏 上手動重排太痛苦。YouMind 把整篇 Markdown 一鍵轉成乾淨、可直接發佈的 𝕏 文章草稿。

試試 Markdown 轉 𝕏

更多可拆解樣本

近期爆款文章

探索更多爆款文章