> ## Content Index
> Fetch the complete content index at: https://blog.jestor.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# How to Extract Data From Invoices and Documents With OCR
- URL: https://blog.jestor.com/extract-data-from-invoices-ocr/
- Published: 2026-09-17T22:26:13.000Z
- Updated: 2026-09-17T22:26:13.000Z
- Author: Bruno Bannach

To **extract data from invoices with OCR**, you upload the document and the reader pulls the values into the record's fields. The document arrives as a file and becomes structured data without anyone typing it.

## The cost of manual document entry

Document entry is the clearest example of work that produces no value and consumes real hours.

- Invoice values retyped into a system that could have read them
- Contract terms transcribed by hand from a PDF
- Typos introduced at the point of entry, discovered much later
- Documents stored separately from the data they contain

## What the document reader handles

| Document type       | What gets extracted                                 |
| ------------------- | --------------------------------------------------- |
| **Invoices**        | Values and details, filling the record directly     |
| **Contracts**       | Value, dates, parties, registration numbers, object |
| **Images**          | Text and data contained in the image                |
| **Multi-page PDFs** | Each page processed and counted individually        |

## How to configure it in Jestor

1. Add a document reader field to the table in **Jestor**.
2. Choose which fields the reader should populate from the document.
3. Upload the file — an invoice, a contract, or an image.
4. Let the reader extract the data and create or fill the record automatically.
5. Review the extracted values before the record moves on in the process.

## Why choose Jestor for document automation?

**Jestor** meters document reading as pages processed rather than as generic **AI** credits, which makes consumption predictable: a three-page PDF counts as three, an image counts as one. That change exists because teams could not estimate cost per read otherwise.

The reader is available inside agents too, so a ticket agent can use an attached document to inform its reply.

## Frequently Asked Questions

### How is usage counted?

By pages processed — one page or one image counts as one.

### Can an AI agent read attachments?

Yes, document reading is built into agents. See [jestor.com](https://jestor.com/?ref=blog.jestor.com).

### Does it create the record automatically?

Yes, it can create the row and fill the selected fields.

## Video Tutorial: Step by Step

Check out other practical tutorials on the Jestor YouTube channel.

## Get to know Jestor

With **Jestor**, you can automate workflows, connect teams, and build internal systems your way — all without code and powered by **AI**. Discover Jestor at [jestor.com](https://jestor.com/?ref=blog.jestor.com) and see how to take your company's operations to a new level of efficiency and control.