For the complete documentation index, see llms.txt. This page is also available as Markdown.

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.

Last updated