> For the complete documentation index, see [llms.txt](https://omniminds-ai.gitbook.io/whitepaper/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://omniminds-ai.gitbook.io/whitepaper/4.-who-are-we/demonstration-based-agent-training.md).
# Demonstration-Based Agent Training
At its core, Omniminds allows users to teach AI agents by simply doing — performing digital tasks on-screen as they normally would. Most AI platforms train their models using the same datasets scraped from the internet or developed by centralized teams. Omniminds uses real-human demonstrations to train AI agents in executing tasks. The platform captures:
* Mouse movement, clicks, and keyboard input
* Screen context and UI elements
* Application navigation and timing
* Task-level goals and intent
These demonstrations are then used to train agents capable of replicating the task autonomously, adapting to slight UI changes, and even transferring behavior across similar applications.
This model makes training intuitive, enabling anyone, regardless of technical skill, to contribute to agent intelligence.
---
# 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://omniminds-ai.gitbook.io/whitepaper/4.-who-are-we/demonstration-based-agent-training.md?ask=&goal=
```
`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.