Agent execution

Controlled action with human oversight

Planned Updated 2026-09-26

Agent execution is planned. The direction is to let supported agents act within explicit authority and bring decisions back to people when needed. Autonomous execution, live watch and jump-in are not available in the documented app.

Start with what exists

Use Intent, context bundles and the assisted review pilot. The detailed edition explains the intended workflow and its open boundaries.

Something here wrong, missing or out of date? Tell us at support@orneos.com — corrections to these pages are welcome and we would rather hear it than have you work around it.