This agent uses Google’s Gemini 2.5 Pro model, featuring advanced multimodal reasoning, a 1 million-token context window, and state-of-the-art coding capabilities. With Deep Think mode and native support for text, image, audio, and video inputs, it excels at complex problem-solving, agentic workflows, and creative tasks across diverse domains.
Sign up to work with this agent
Get full access to run, customize, and share this agent — plus hundreds more.