> 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/data-security-documentation/agentic-ai-and-cortex-agentic-assistant/data-security-agent.md). # Data security agent The Data security agent is a system agent in the [Cortex Agentic Assistant](/data-security-documentation/agentic-ai-and-cortex-agentic-assistant/agentic-ai.md). It gives you a natural language interface to your data security program. From a single chat, you can ask questions about your data, take action on what you find, and create custom data patterns. The Data security agent supports three main types of task: * Answer questions about your data. * Take actions. * Write custom data patterns. ## Answer questions about your data Ask questions in natural language about any data the platform has discovered and classified, and the agent returns answers grounded in your inventory, posture findings, and detections. For example: * Which data stores contain unencrypted PII? * Show me the publicly exposed assets that hold financial data. * Which AI agents accessed sensitive data in the last 30 days? * Summarize the highest-risk data issues from the past week. ## Take actions The agent can open tickets in ticketing systems such as Jira and share information through communication channels such as Slack, Microsoft Teams, and email. For example, you can ask the agent to open a Jira ticket for an over-exposed data store, or post a summary of new high-severity issues to a Slack channel. {% hint style="info" %} Available actions depend on which integrations are active in your tenant and which actions are assigned to the agent. The agent runs within your tenant permissions, and sensitive actions require explicit approval. See [Agentic Assistant security](/data-security-documentation/agentic-ai-and-cortex-agentic-assistant/agentic-assistant-security.md). {% endhint %} ## Write custom data patterns The agent can help you create custom data patterns to identify sensitive data that is specific to your organization. Describe the data you want to detect, and the agent helps generate the pattern definition. Once saved, a custom data pattern runs on all data in the same way as any out-of-the-box pattern. For the full procedure on building and validating patterns, see [How to create and validate a custom data pattern](/data-security-documentation/data-security/data-classification/how-to-create-and-validate-a-custom-data-pattern.md). --- # 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/data-security-documentation/agentic-ai-and-cortex-agentic-assistant/data-security-agent.md?ask=&goal= ``` `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.