> For the complete documentation index, see [llms.txt](https://docs.bluestorm.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bluestorm.io/overview/product-architecture/ai-powered-features.md).

# AI Powered Features

AppControl uses AI in a number of features to help simplify tasks and surface insights that would otherwise require manual analysis. This page explains how AI is used across the product, and the safeguards that are built around it.

**Bring Your Own AI**

AppControl does not require you to use a specific AI provider. You can connect your own AI service, such as Mendix GenAI or OpenAI, and AppControl will use it for its AI-powered features.

**Token Usage**

Because token usage depends on the size and complexity of the data being processed, AppControl cannot provide an exact estimate of tokens consumed. We do, however, optimize prompts and payloads to keep usage as low as possible. As an indication, data classification typically uses between 150 and 300 tokens per attribute classified.

**Identifying AI-Generated Data**

Whenever AppControl creates data using AI, this is always indicated in the product (flagged as 'SYSTEM'). This makes it possible to distinguish between data that was generated by AI and data that was entered by a human.

**Human Oversight**

AI-generated data is a suggestion, not a final decision. Any data generated by AI can always be reviewed and overridden by a human.

**Safe Defaults**

AI-generated data always falls back to sensible, deterministic, and safe defaults. This provides a safety net in case the AI is unavailable, fails, or produces data that doesn't make sense.

**Optional by Design**

Using AI-powered features in AppControl is never mandatory. Their use can simplify certain tasks or surface insights you might otherwise miss, but every feature that uses AI can also be used without it.


---

# 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://docs.bluestorm.io/overview/product-architecture/ai-powered-features.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.