# Welcome

Amigo is a healthcare AI platform built on a data foundation that absorbs messy, unreliable healthcare data from every source, cleans and unifies it, and makes it available to the systems that act on it - the agent engine, EHR connectors, operator workflows, and automated analytics.

The core idea: healthcare data is unreliable at the source, but the systems that consume it need it to be trustworthy. The [world model](https://docs.amigo.ai/data/world-model) scores every fact by confidence, verifies it through automated pipelines, and projects unified state that every system on the platform can trust. The agent engine, the connector runner, the safety monitors - they all work because the data underneath them is clean.

## Platform API

Multi-channel agents (voice, SMS, API) with EHR integration, operator escalation, and the event-sourced world model. Built for health systems running real patient volumes.

{% hint style="warning" %}
The Classic API (text chat) remains supported for current deployments. New deployments should use the Platform API.
{% endhint %}

## Architecture Overview

<figure><img src="https://3635224444-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvcLyiHRcwv7g83p6vxAd%2Fuploads%2Fgit-blob-168802eafb3cc6221a114fee61067e3fb0d5d916%2Farchitecture-overview-blue.svg?alt=media" alt="Platform architecture: World Model data foundation with systems"><figcaption></figcaption></figure>

## Start Here

{% content-ref url="platform-overview/what-amigo-does" %}
[what-amigo-does](https://docs.amigo.ai/platform-overview/what-amigo-does)
{% endcontent-ref %}

{% content-ref url="platform-overview/how-it-works" %}
[how-it-works](https://docs.amigo.ai/platform-overview/how-it-works)
{% endcontent-ref %}

{% content-ref url="platform-overview/design-principles" %}
[design-principles](https://docs.amigo.ai/platform-overview/design-principles)
{% endcontent-ref %}

{% content-ref url="platform-overview/deployment-model" %}
[deployment-model](https://docs.amigo.ai/platform-overview/deployment-model)
{% endcontent-ref %}

{% hint style="info" %}
**Developer Guide** - For API reference, SDKs, and implementation details, see the [Developer Guide](https://docs.amigo.ai/developer-guide).
{% endhint %}


---

# 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://docs.amigo.ai/readme.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.