> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/ai-in-umbraco/17.latest/concepts/concepts.md).

# Core Concepts

Understand the core concepts that make up Umbraco.AI's architecture.

Umbraco.AI is built around a hierarchical configuration model that separates concerns and enables flexibility. Understanding these concepts helps you make the most of the platform.

## The Configuration Hierarchy

```mermaid
graph TD
    A["Provider\n(plugin with capabilities)"] --> B["Connection\n(authentication/credentials)"]
    B --> C["Profile\n(use-case configuration)"]
    C --> D["AI Request\n(the actual call)"]
```

Each level adds configuration that flows down to the actual AI request.

## Key Concepts

<table data-view="cards"><thead><tr><th></th><th></th></tr></thead><tbody><tr><td><strong>Providers</strong></td><td>Installable plugins that connect to AI services like OpenAI or Azure</td></tr><tr><td><strong>Connections</strong></td><td>Store credentials and endpoint settings for a provider</td></tr><tr><td><strong>Profiles</strong></td><td>Combine a connection with model settings for specific use cases</td></tr><tr><td><strong>Capabilities</strong></td><td>The types of AI operations available: Chat, Embedding, and more</td></tr><tr><td><strong>Middleware</strong></td><td>Extensible pipeline for logging, caching, and custom behavior</td></tr><tr><td><strong>Guardrails</strong></td><td>Rules that evaluate AI inputs and responses for safety and compliance</td></tr></tbody></table>

## Built on Microsoft.Extensions.AI

Umbraco.AI is built on [Microsoft.Extensions.AI](https://learn.microsoft.com/en-us/dotnet/ai/ai-extensions), Microsoft's official abstraction for AI services. Building on M.E.AI provides:

* Standard types like `IChatClient`, `ChatMessage`, and `ChatResponse`
* Familiar patterns for .NET developers
* Compatibility with the broader M.E.AI ecosystem
* Compatible with future M.E.AI releases

The service layer in Umbraco.AI is lightweight - it adds Umbraco-specific features (profiles, connections, backoffice UI) while exposing standard M.E.AI types.

## In This Section

{% content-ref url="/pages/jpk1wrq5K8FdBEmlJ5PC" %}
[Providers](/ai-in-umbraco/17.latest/concepts/providers.md)
{% endcontent-ref %}

{% content-ref url="/pages/Z7ciNjjyUMyhXchcrVWd" %}
[Connections](/ai-in-umbraco/17.latest/concepts/connections.md)
{% endcontent-ref %}

{% content-ref url="/pages/9h7BRw4J6pIKJmfvrM9I" %}
[Profiles](/ai-in-umbraco/17.latest/concepts/profiles.md)
{% endcontent-ref %}

{% content-ref url="/pages/rTKTnyD7qe8wny7qADty" %}
[Capabilities](/ai-in-umbraco/17.latest/concepts/capabilities.md)
{% endcontent-ref %}

{% content-ref url="/pages/m55snNUOtJtXCekKgptV" %}
[Middleware](/ai-in-umbraco/17.latest/concepts/middleware.md)
{% endcontent-ref %}

{% content-ref url="/pages/neAKmFkE6LzfLLmpWLGK" %}
[Guardrails](/ai-in-umbraco/17.latest/concepts/guardrails.md)
{% endcontent-ref %}


---

# 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.umbraco.com/ai-in-umbraco/17.latest/concepts/concepts.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.