Configure permissions to access Cortex Agentic Assistant features.
Instance and Account admins have full control over the permissions and access that users have to the Cortex Agentic Assistant. Cortex XSIAM uses role-based access control (RBAC) to manage access to the chat, as well as access to view, create, edit, delete, disable, and enable Agents and Actions in the Agents Hub.
By default, Instance and Account admins have full view/edit permissions enabled. When editing or creating other roles, in the → section, you can select the following:
Permission | Description |
|---|---|
View/Edit | When selected (and nothing else is checked in this section), the user role can only see actions and public agents in the Agents Hub, but cannot interact with agents. You can also select the following permissions:
|
View | N/A |
None | The user role does not see any agents and can’t use the chat. The Agents Hub is not visible to the user. Cortex Agentic Assistant is only available for navigation and insights. |
Note
Agents are limited by the individual permissions of the user. For example, if users do not have sufficient permissions to isolate an endpoint, they cannot use an agent to isolate an endpoint.
The execution of system or custom actions that are based on integration commands can be restricted to specific roles using integration permissions.