Google 给 Gemini 3.5 Flash 加了 Computer Use 工具，能让智能体跨浏览器、手机和桌面干活，还能自定义安全策略，实用！
Google AI Devs 宣布 Gemini 3.5 Flash 的 Computer Use 工具正式可用。该工具支持在浏览器、移动和桌面环境中构建可看可操作的智能体，处理长时任务。新增特性包括：内置移动和桌面操作系统支持、所有函数调用的意图参数、可定制客户端函数支持人机交互接管、提示注入检测及可配置安全策略。可用于自动化 QA 测试和业务流程等场景。
The Computer Use tool is now available for Gemini 3.5 Flash 🛠️ Build agents that see and take acti...
The Computer Use tool is now available for Gemini 3.5 Flash 🛠️ Build agents that see and take action across browser, mobile, and desktop environments to seamlessly handle long-horizon tasks. Here’s what’s new: - Built-in support for mobile and desktop operating systems - Intent arguments for all function calls - Customizable client-side functions to easily support human-in-the-loop (HITL) takeover - Prompt injection detection and configurable action-level safety policies to fit your app’s needs Learn how you can use 3.5 Flash to automate QA testing, business processes, and more in the blog: blog.google/innovation-and… u 💬 1 🔄 4 ❤️ 23 👀 2822 📊 6 ⚡