> For the complete documentation index, see [llms.txt](https://docs.courtaid.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.courtaid.ai/chat-and-documents/pdf-enrichment.md).

# PDF enrichment (scanned documents)

CourtAid now accepts scanned PDFs. When you upload a document that doesn't have a searchable text layer, CourtAid automatically detects it and runs an enrichment process to extract the text.

## What happens when you upload a scanned PDF

1. You upload a PDF to a [Matter](https://docs.courtaid.ai/matter-workspaces/matters.md) or via the chat attach menu
2. CourtAid detects that the PDF is scanned (image-based, no text layer)
3. An **enrichment process** runs automatically to extract text from the document
4. Once complete, the document becomes fully searchable and usable across CourtAid

You'll see a processing indicator while enrichment is in progress. Chat and tabular features become available once enrichment finishes.

## What you can do after enrichment

An enriched scanned document works the same as any other uploaded PDF:

| Feature                                                                    | Available after enrichment                                 |
| -------------------------------------------------------------------------- | ---------------------------------------------------------- |
| **Matter chat**                                                            | Ask questions across your scanned documents and court data |
| **Chat PDF**                                                               | Talk directly to the document with highlighted citations   |
| [Tabular View](https://docs.courtaid.ai/matter-workspaces/tabular-view.md) | Run extraction queries across scanned documents in a table |
| **Chronologies**                                                           | Build timelines from dates and events in scanned documents |
| **Search within a matter**                                                 | Find content across all of a matter's files                |

## Tips

* Upload scanned documents directly to a matter — no need to OCR them first
* Wait for enrichment to complete before starting Chat PDF or tabular reviews on scanned files
* Enrichment works alongside CourtAid's existing support for native (text-based) PDFs — both are handled automatically

## Related

* [Matters](https://docs.courtaid.ai/matter-workspaces/matters.md) — upload documents to a matter workspace
* [Chat PDF](https://docs.courtaid.ai/chat-and-documents/chat-pdf.md) — talk to individual documents
* [Tabular View](https://docs.courtaid.ai/matter-workspaces/tabular-view.md) — extract structured data across many documents


---

# 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.courtaid.ai/chat-and-documents/pdf-enrichment.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.
