Skip to content

Automatic translation — the Portuguese version is the reference. View in Portuguese

Updated on 2026-10-03

Who can do what

Permissions in the agents area by capability: who sees, chats, creates, publishes, and authorizes, and why a high-risk action requires two people.

On this page (4)

The agents area is governed by capability, not by job title.

ActionWho can
See the list of agentsanyone in the workspace
Chat with a published agentmember or above
Create, configure, publish, scheduleadministrator or above
Connect outside systems and approve toolswhoever administers the workspace
Authorize an actionwhoever has permission for that action

The rule that matters most#

Authorizing what the agent proposed requires permission for the action itself — being able to chat with it is not enough.

If you can't reprocess a pipeline from the menu, you also can't authorize the agent to do it. The agent is not a shortcut to permissions you don't have.

This applies down the chain: when a coordinator asks a specialist, the permission is checked again, and it is still yours.

A high-risk action requires two people#

Whoever proposed it doesn't authorize their own proposal. It's the same idea as the person who pays not approving their own payment.

Scheduling acts with the permission of whoever scheduled it#

An automatic run has no authority of its own: it uses the permission of the person who created the schedule, checked on every trigger. If that person is deactivated, the schedule stops and says so.

Nothing crosses between customers#

Each workspace sees only its own agents, tables, documents, and runs. This doesn't depend on configuration — it's how the system behaves.

Related links