First Agent Command
Audience
This page is for users running AiOS through CLI/Agent identity for the first time.Goal and Scope
This page helps you execute a first command and understand:- CLI/Agent is not a separate control plane
- commands still flow through the same server-side authorization chain
Core Concepts
- CLI/Agent commands ultimately invoke the server-side API
- high-risk production mutations still enter the approval chain by default
- error semantics, resource model, and task model are shared with the Web channel
Standard Workflow
- prepare CLI/Agent identity context
- execute a low-risk command (for example, a dev deployment)
- observe the returned task/error/status response
CLI Examples
Web UI Path
The resulting task state and audit result should later be visible through task and approval views in the Web UI.Pitfalls / Risk Notes
- an agent command is not a way to bypass authorization or approval
- production commands should still be subject to the same step-up and approval guardrails