> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/document-ai/get-started/key-concepts.md).

# Key concepts

Document AI turns files into structured, reviewable outputs.

{% hint style="info" %}
**Core workflow:** Upload → Classify when needed → Extract → Validate → Deliver.
{% endhint %}

### Start with the right document type

A document type defines the fields Document AI extracts from a file.

Select it when you submit an extraction. It also determines the fraud checks that run.

Use the same document type across your workflow.

{% hint style="info" %}
Classification categories and extraction document types are different. Classify unknown files first, then select the closest document type.
{% endhint %}

### Jobs run in the background

Extraction, classification, and generation each create a background job.

Track each job until it is processed or failed. Each file has its own job.

### Use confidence to route review

Every extracted field includes a confidence score. Use it to prioritize human review.

High-confidence values can move forward automatically. Lower-confidence values should be reviewed.

### Manage credits and access

Document AI uses prepaid credits for processed pages. Check your balance in **Settings → Usage**.

Account roles control access to workspace settings. Collection roles control access within each collection.

### Deliver results with webhooks

Webhooks notify your systems when a background job completes.

Document AI sends the complete result to your configured URL. Verify each request before processing it.

{% hint style="warning" %}
Configure a webhook URL in **Settings → Account** before processing.
{% endhint %}


---

# 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://docs.uptiq.ai/document-ai/get-started/key-concepts.md?ask=<question>&goal=<endgoal>
```

`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.