> For the complete documentation index, see [llms.txt](https://docs.ins-pi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ins-pi.com/models/work-in-the-app/ai/privacy.md).

# Data Privacy & Transparency

YouDesign Models' AI features are built so you always know what data is being sent to the AI provider. You can inspect the exact payload for any AI response, and your diagram data stays inside your own organization's provider account.

## What Data Is Sent to the AI

When you send a message, the AI receives:

* **Your message text** — the prompt you typed.
* **Relevant diagram data** — node names, positions, connections, and properties needed to answer your request.
* **Attached images**, if any.
* **Chat history** for the current session, to keep context.

What *isn't* sent:

* Data from boards you aren't actively working on.
* Other users' sessions.
* ServiceNow records that aren't referenced by the shapes you're working with.

## Inspecting Exactly What Was Sent

For every AI response, you can see the raw payload that was shared with the AI provider:

1. Locate the **eye icon** next to any AI response in the chat.
2. Click it to open the **"Data Sent to AI"** dialog.
3. The dialog shows the nodes, links, and other context that were included in the request.

> **🖼 Screenshot needed:** \[The "Data Sent to AI" dialog showing a JSON-like summary of the payload] *Show: a modal over the editor with a tree/list of nodes and links included in the AI request, with a close button.*

Use this whenever you want to verify exactly what was shared before showing a board to sensitive stakeholders.

## How Data Flows

* Requests go directly from YouDesign Models (running inside your ServiceNow instance) to the AI provider configured by your administrator.
* The AI provider uses **your organization's own API key**, not a shared key.
* No intermediate server stores your diagram data.
* The AI provider may log requests according to its own policy. Consult your provider's data retention terms.

## Admin Controls

Your administrator decides:

* Whether AI features are enabled at all.
* Which AI provider (for example, OpenAI, Anthropic, Azure OpenAI) is used.
* Which models are available.
* Which users have the role required to use AI.

See [AI Configuration](/models/admin/ai-configuration.md) for the admin-side setup.

## Tips for Sensitive Boards

* **Rename confidential labels** before asking the AI to reason about a board, if the names themselves are sensitive.
* **Use `@mentions`** to narrow the scope — the AI only sends data it needs to act on.
* **Open the "Data Sent to AI" dialog** for spot-checks on what left your organization.
* **Talk to your administrator** about provider choice if you have strict data-residency requirements.

## Related

* [AI Chat](/models/work-in-the-app/ai/chat.md) – Sending messages
* [AI Configuration](/models/admin/ai-configuration.md) – Admin-side setup


---

# 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.ins-pi.com/models/work-in-the-app/ai/privacy.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.