> For the complete documentation index, see [llms.txt](https://docs.veedna.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.veedna.com/unifai.md).

# UnifAI

UnifAI is the unified AI security orchestrator for agentic AI application development. It automatically secures AI applications as they are built and applies corporate security policies in real time. UnifAI provides continuous discovery of AI assets and enables developers to create secure AI applications by incorporating controls into agentic application development.

This gives security teams confidence that controls are consistently enforced while allowing developers to focus on speed and innovation.

<figure><img src="/files/rd3XNiqJpLYFdyqZ5SRI" alt=""><figcaption></figcaption></figure>

## Secure Your AI Apps and Workflows

UnifAI offers the following capabilities to discover, secure, and govern AI at scale:

* **Discover AI Asset Inventory (AI BOM)**: Find every AI model, AI agent, MCP server, Skills, and AI-related dependency — including shadow AI. You get a continuously updated AI Bill of Materials (BOM) so you always know exactly what AI is in your environment. To learn more, see [AI Asset Inventory (AI BOM)](/unifai/ai-asset-inventory-ai-bom.md) and [Viewing, Allowing, and Blocking Your AI Asset Inventory (AI BOM)](/unifai/ai-asset-inventory-ai-bom/viewing-allowing-and-blocking-your-ai-asset-inventory-ai-bom.md).
* **Apply Policies and Ensure Compliance**: Use built-in policies covering AI threats, privacy, access control, compliance, and vulnerabilities, or import your own. Policies map directly to frameworks like OWASP and the EU AI Act. To learn more, see [Regulatory Compliance](/unifai/regulatory-compliance.md), [Policies](/unifai/policies.md) and [Viewing and Enabling Policies](/unifai/policies/viewing-and-enabling-policies.md).
* **Enforce Controls and Remediate Risks**: Policy controls protect data exposure, PII leakage, prompt injection, and identity risks. Remediation agents fix issues automatically — blocking unsafe assets, replacing vulnerable dependencies, and giving developers clear guidance. To learn more, see [Commonly Searched Policies](/unifai/policies/viewing-and-enabling-policies.md#commonly-searched-policies).
* **Integrate Across Your Ecosystem**: Connect UnifAI to the tools your teams already use — IDEs and CLIs like Cursor, Codex, Antigravity, and Claude Code. To learn more, see [Configuring the Lineaje MCP Server](/unifai/setting-up/configuring-the-lineaje-mcp-server.md).
* **Interact With Conversational AI**: Ask questions in natural language. Get insights, enable policies, and generate instant dashboards and reports. To learn more, see [Lineaje AI Assistant](/unifai/lineaje-ai-ai-assistant.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://docs.veedna.com/unifai.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.