> 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/configure-the-cortex-agentic-assistant.md).

# Configure the Cortex Agentic Assistant

Configure AI agents, actions, knowledge, and access controls in Cortex AgentiX.

The Cortex Agentic Assistant helps SOC teams investigate and respond through AI agents. Agents turn requests into plans and execute approved actions within each user's permissions.

### How the components work together

An **agent** is a specialized virtual persona for a domain or workflow. It selects from its assigned **actions** to build and run a plan.

Actions wrap capabilities such as playbooks, scripts, AI prompts, and commands. Add only the actions each agent needs.

**Knowledge** gives agents business-specific context and Cortex product expertise. Knowledge sources and MCP integrations can extend an agent's context and capabilities.

**Role-based access control** defines who can use chat, manage actions, and manage agents. Agents never exceed the permissions of the user running them.

### Configure your agent workforce

1. Review [Agentic Assistant components and concepts](/cortex-agentix/configure-cortex-agentix/configure-the-cortex-agentic-assistant/agentic-assistant-components-and-concepts.md) before designing an agent.
2. Use the [Agentic Assistant Hub](/cortex-agentix/configure-cortex-agentix/configure-the-cortex-agentic-assistant/agents-hub.md) to register actions, build agents, and assign actions.
3. Add knowledge sources or MCP integrations when the agent needs more context or capabilities.
4. Configure [role-based access control](/cortex-agentix/configure-cortex-agentix/configure-the-cortex-agentic-assistant/agentic-assistant-role-based-access-control.md) before giving users access.


---

# 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/configure-the-cortex-agentic-assistant.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.