> 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-agentix/configure-cortex-agentix/automations/playbooks.md).

# Playbooks

Build and manage playbooks in Cortex AgentiX to automate security response workflows.

Playbooks are a series of tasks that run in a predefined flow. They save time and improve investigation and response outcomes. They automate security processes, including investigations and ticket management. For example, a task can parse an issue or a PDF attachment. Playbooks also standardize incident response workflows.

{% hint style="warning" %}

### Prerequisite

To work with playbooks, an administrator must configure their user role with specific RBAC permissions.

* Permissions must be enabled in the following order:

1. **Scripts**: Under **Investigation & Response** → **Automations**, set this component to **Enabled** first. It is required for all automation. Without it, you cannot configure **Playbooks** or **Cases and Issues**. Role permissions control script creation and edits to **Public** scripts.
2. **Playbooks**: Under **Investigation & Response** → **Automations**, set this component to **Enabled**. Role permissions control playbook creation and edits to **Public** playbooks. Object-level permissions control access to individual custom playbooks and scripts. See [Access to playbooks](/cortex-agentix/configure-cortex-agentix/automations/playbooks/access-to-playbooks.md).
3. **Cases and Issues**: After enabling **Scripts** and **Playbooks**, set this permission under **Cases & Issues** to **View** or **View/Edit**. This permission is required to view playbook results within a case.

* **Credentials**: While not required to open the Playbook Editor, a minimum of **View** permissions for **Credentials** is required to select or reference stored secrets within playbook tasks. If your role has the **Credentials** permission set to **None**, you will be unable to select credentials from dropdown menus. Furthermore, any task that attempts to retrieve a credential to authenticate an integration command will fail during execution because the system cannot fetch the secret under your role's restricted context.
* **Restricting playbook access**: To completely restrict playbook access, first set the **Cases and Issues** RBAC permission to **None** and then set the **Playbooks** permission to **Disabled**.
  {% endhint %}

### Agentic Playbook Builder for playbook development (preview)

Use the AI-powered Agentic Playbook Builder to simplify playbook creation and management through an intuitive, interactive experience. It enables you to generate, modify, and query playbooks with the Cortex Agentic Assistant natural language chat prompt. For example, within the chat, you can ask the agent to "Add a step to block the domain in Okta" or ask it to explain how a specific conditional branch operates.

{% hint style="info" %}

### Note

The Agentic Playbook Builder preview feature is not enabled by default. To request access, contact [Cortex Product Management](mailto:dl-CortexAgentixDesignPartners@paloaltonetworks.com).
{% endhint %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://cortex-docs.paloaltonetworks.com/cortex-agentix/configure-cortex-agentix/automations/playbooks.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.