Google

AI-powered IDE built as a fork of Visual Studio Code, designed with an 'agent-first' paradigm where autonomous AI agents plan, execute, and validate code. Features two primary views: Editor View (traditional IDE with agent sidebar) and Manager View (control center for orchestrating multiple parallel agents across workspaces). Agents generate verifiable 'Artifacts' including task lists, implementation plans, screenshots, and browser recordings. Supports multiple AI models including Gemini 3 Pro, Gemini 3 Deep Think, Gemini 3 Flash, Claude Sonnet 4.5, and open-source GPT variants. Agents have...

Google Chrome has evolved from a simple browser into a native agentic layer powered by Gemini 3.0. By integrating Gemini directly into the sidebar and core browsing engine, Chrome can now 'see' and reason across all open tabs. The 'Auto-Browse' feature allows Gemini to autonomously execute multi-step tasks, such as researching complex topics, comparing products across multiple sites, and handling travel bookings, without the user ever leaving the active window. It leverages the full Google ecosystem (Gmail, Calendar, Drive) to act as a unified reasoning layer for the entire web.

Web-based integrated development environment for prototyping and building applications with Google's generative AI models. Provides access to the Gemini family of models including Gemini Pro, Gemini Flash, and multimodal capabilities. Features prompt engineering workspace for testing and refining prompts, code generation and export in Python and Node.js, API key management for seamless integration, and support for multimodal inputs (text, images, video). Enables rapid prototyping of AI applications with Google's latest models. Suitable for developers building applications with Gemini models,...