# 6. Demonstration-Based Training System (The Dojo)

Omniminds believes in a simple concept: the best way to teach an AI how to use a computer is by showing it how. This idea comes to life by training agents in the Dojo. Rather than relying on code, APIs, or predefined workflows, Dojo training captures human interactions with digital environments in real time and translates them into structured datasets for training autonomous agents.<br>

So, how does demonstration-based training work? Why does it matter, and how does it power the emergence of general-purpose CUAs (Computer-Use Agents)?


---

# Agent Instructions: 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:

```
GET https://omniminds-ai.gitbook.io/whitepaper/6.-demonstration-based-training-system-the-dojo.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.