Four outcomes for your application
A Harness is the engine that runs the Agent loop: it interprets the task, interacts with a model and chooses execution steps. Hexagon supplies the surrounding task and resource lifecycle. Its Console is useful for configuring and investigating that lifecycle; your application normally integrates through the Python SDK, TypeScript SDK or HTTP API.
Follow a project task
Suppose your application lets users upload a Web project and ask an Agent to add filtering:- Configure, validate, and enable a cloud Sandbox connection and model connection.
- Choose a compatible Harness, create a Session, and upload project files.
- Submit the change request and retain its Run ID.
- Hexagon executes in the cloud Sandbox. Your application observes durable events and presents progress.
- The Agent edits files, runs tests, and places deliverables in the Run’s artifact directory.
- Retrieve results and artifacts, optionally exposing an authorized private Web preview.
- Submit follow-up work as another Run in the same Session.
- Close the Session and confirm cloud cleanup; exported artifacts and completed records remain queryable.
Responsibilities
This diagram shows responsibility boundaries; actual request paths depend on connection type. Provider credentials remain in the control plane. Protected model/Tool credentials use scoped access. Values you explicitly put into Session env or variables are readable by Sandbox code.