Skip to main content
Use the Coding Agent to implement a change, the Architect API to plan one, or Browser Agents to work with a website.

Choose your interface

The public API exposes planning and browser operations. For code implementation, start in the web workspace or CLI.

Build an integration

Get an API key

Choose your account, authenticate a request, and check access.

Handle results and errors

Recognize terminal states, recover from failures, and retry safely.
Giving these docs to a coding assistant? Start with the guide for agents and the OpenAPI schema. For account access and usage, see plans and credits.