> 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/detect-investigate-and-respond-to-threats/investigation-and-response/analyze-and-resolve-cases/start-case-analysis/agentic-assistant-case-investigation-agent.md).

# Agentic Assistant - Case Investigation agent

Use the Case Investigation agent to analyze cases in Cortex AgentiX.

The **Agentic Assistant** is a context-aware, generative intelligence tool embedded directly within the case card. It is designed to act as a side-by-side partner for security analysts, eliminating the need to pivot away from the investigation to consolidate complex data.

When you open the Agentic Assistant you can select the agent that is best suited for each task. The dedicated Case Investigation agent can help you with your case investigation. It specializes in advanced summarization, and recognizes the context of the case, ensuring every insight provided is highly relevant and grounded in the specific issues, assets, and telemetry of the current investigation.

For more information about using other agents in the Agentic Assistant, see [Get started with Agentic Assistant chat](/cortex-agentix/detect-investigate-and-respond-to-threats/agentic-assistant-chat/get-started-with-agentic-assistant-chat.md).

**Core functionalities of the Case Investigation agent**

To streamline case analysis, the assistant provides the following areas of support:

* Dynamic summarization of log data and issues into clear, actionable narratives, including:
  * **Executive overviews:** High-level summaries that focus on impact and risk.
  * **Extended technical overviews:** Deep-dive summaries that outline the technical progression of the threat.
* Focused contextual inquiries to extract specific details without manual filtering. You can ask targeted questions regarding:
  * **Issue deep-dives:** Understanding the specific triggers and severity of an issue.
  * **Asset relationships:** Identifying which users or devices are at the center of the activity.
  * **Asset and artifact investigation:** Understanding the impact and risk of the assets and artifacts in the investigation.
* Intelligent pivoting and clarification to help you navigate through complex investigations:
  * **Entity-specific prompts:** By clicking **Ask AI** next to a specific entity (such as an IP address or file hash), the assistant launches with a pre-configured prompt tailored to that specific object.
  * **Investigation guidance:** It suggests potential next steps and actions, and links to detailed views


---

# 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/detect-investigate-and-respond-to-threats/investigation-and-response/analyze-and-resolve-cases/start-case-analysis/agentic-assistant-case-investigation-agent.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.