Gemini Computer Use Quick start 1. Source the env file and set your API key: 2. Create a virtual environment and install dependencies: 3. Run the agent script with a prompt: Browser selection - Default: Playwright's bundled Chromium (no env vars required). - Choose a channel (Chrome/Edge) with . - Use a custom Chromium-based executable (e.g., Brave) with . If both are set, takes precedence. Core workflow (agent loop) 1. Capture a screenshot and send the user goal + screenshot to the model. 2. Parse actions in the response. 3. Execute each action in Playwright. 4. If a is , prompt the user bef…