> For the complete documentation index, see [llms.txt](https://cortex-docs.paloaltonetworks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cortex-docs.paloaltonetworks.com/cortex-xdr-5.x/onboard-cortex-xdr/post-deployment-steps/configure-the-cortex-agentic-assistant/agents-hub/manage-actions.md).

# Manage actions

Actions wrap diverse capabilities (such as playbooks, scripts, AI prompts, and commands) to make them accessible and executable by an agent. You can use out-of-the-box system actions or register new actions.

{% hint style="info" %}

### Note

To manage actions in the Agents Hub, you must have the correct permissions. For more information, see [Agentic Assistant role-based access control](/cortex-xdr-5.x/onboard-cortex-xdr/post-deployment-steps/configure-the-cortex-agentic-assistant/agentic-assistant-role-based-access-control.md).
{% endhint %}

There are two types of actions in the Agents Hub:

* **System actions**: Cortex XDR contains more than 50 out-of-the-box system actions that can be disabled or enabled, but cannot be edited or deleted.

  To find and install additional content packs that include actions, go to **Marketplace** and select **Content pack includes** and **Actions**.

  <div data-gb-custom-block data-tag="hint" data-style="info" class="hint hint-info"><h3>Tip</h3><p>System actions may rely on content packs that need to be installed and configured.</p></div>
* **Custom actions**: Users can register existing or new scripts, commands, and AI prompts as actions. Custom actions can be edited, deleted, enabled, or disabled.

Any action marked as sensitive to require user approval requires explicit user approval before execution. This is particularly crucial for operations that might alter system reality or affect an organization’s budget, such as isolating an endpoint or revoking user access. System actions are marked sensitive if they affect system reality. When creating custom actions, you decide which actions should be marked as sensitive for your organization.

The execution of system or custom actions that are based on integration commands can be restricted using [integration permissions](/cortex-xdr-5.x/configure-cortex-xdr/cortex-xdr-data-sources/administration-and-troubleshooting/integrations/configure-integration-permissions.md).

### Manage existing actions

From the **Actions** tab of the **Agents Hub**, click ![three-dots.png](/files/gHHbrKy5jm4WlNwZ9gqX) for an action to edit, delete, or disable an existing custom action. System actions can be enabled or disabled and you can change them from sensitive to non-sensitive or from non-sensitive to sensitive.

### Search, filter, and sort actions

You can use the dropdown filter to search all actions, custom actions, system actions, enabled actions, disabled actions, sensitive actions, or non-sensitive actions. You can also filter by source types: command, script, or playbook.

You can sort actions by creation time or update time.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://cortex-docs.paloaltonetworks.com/cortex-xdr-5.x/onboard-cortex-xdr/post-deployment-steps/configure-the-cortex-agentic-assistant/agents-hub/manage-actions.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.