Solutions · Data extraction · Custom project Capture the details you need from your documents.
Invoices, delivery notes, orders by email: using your examples, we assess which fields can be read automatically and where a manual check is still needed.
The details are in the document. They still reach your system by hand.
Open the document, find the detail, type it in, double-check. Document after document, day after day.
The challenge: Typing from PDFs and scans
Invoice number, amount, order number: every detail is looked up and keyed into an entry screen. That time is then missing for the cases that really need attention.
With deepsight: Extract instead of re-keying
The application reads the agreed fields from incoming documents and stores them as records.
The challenge: Every sender, a different layout
The same detail is called order number in one place and order no. or PO number in another, and it sits somewhere different every time. Reading by fixed position means a separate template for every sender.
With deepsight: Describe fields by meaning
We describe which detail is meant – not where it sits. Using your examples, we check whether that holds across your senders’ layouts.
See the methodologyThe challenge: Errors surface later
A transposed digit in an amount or a wrong order number often only shows up during reconciliation, at payment or when someone follows up.
With deepsight: Check before handing over
Values that are hard to read or break an agreed rule are flagged by the application for your team to review.
See how it runs in operationThe challenge: Sensitive documents, strict requirements
Contracts or HR records don’t belong in just any online tool. Your IT often requires processing to stay in your own environment.
With deepsight: Operation on your terms
Where the application runs is defined in the project – with local language models in your infrastructure if you prefer. We set up, maintain and operate the models; the sample shows whether a local model is good enough for your documents.
Go to custom development
One document, three fields, one review view
Invoice no. RE-2026-0412
Invoice date: 08/14/2026 · Customer no.: 20931
Printer paper A4, 40 boxes ........ €612.00
Toner, 6 units ........ €437.20
plus 19% VAT ........ €199.35
Total €1,248.55
Select a field to see where it appears in the document.
Illustrative document.
What we clarify at the start
Document type
Which documents arrive regularly, in which format and in what quality?
Required fields
Which details do you need, and which rules apply when checking them?
Target system
Where does the data go: a spreadsheet, a business application or an ERP system? The connection is defined in the project.
From sample documents to operation
- Review samples
A selection of typical documents, including difficult cases.
- Define fields
Which details are extracted and when a field goes to manual review.
- Measure a sample
We measure how often fields are read correctly using your documents.
- Connect
Export or connection to your target system, depending on the project.
What your documents should answer
- Which invoice number, which amount, which due date – and which order number does the invoice state?
- Which pickup address, which quantities and which delivery date are in an order sent by email?
- Which items and quantities does the delivery note list?
- Who are the contracting parties, how long does the contract run, and what notice period applies?
- Has every mandatory field in an application been filled in?
- Which measurements and designations appear in test or lab reports?
What we work with
Documents that arrive regularly and whose details you need again and again.
The path of a document
- Intake
Documents arrive through the agreed channel, for example a mailbox, a folder or your business application.
- Extract
The application reads the defined fields and puts dates, amounts and numbers into the format your target system expects.
- Review
Your team sees flagged fields next to the document and confirms or corrects them.
See the review view - Hand over
Reviewed records go to your target system – as a file or via its interface.
- Adjust
New senders or revised forms? We then check the affected fields again using examples and adjust the rules, as agreed.
Project phases
The application reads. Your team decides.
Doubtful cases are resolved by the people who know your processes.
What you receive in the project
What matters in extraction
Assess each field on its own
Misread bank details matter more than a wrong delivery date. That’s why we discuss for each field whether, after measurement, it is captured automatically or always goes to review.
Rules from your expertise
Mandatory fields, expected formats such as the structure of your order numbers, or cross-checks such as line items against the total – we define these together. This also flags values that are readable but implausible.
Traceable for audits
On request, we also trace automatically captured values back to their place in the document and build logging and review steps for your internal audit into the project.
Good to know: Need a custom-trained model? As part of a custom project, we assess whether this approach suits your use case.
Questions about data extraction
No. We develop data extraction as a custom project for your documents and systems; there is no standard module to upload documents to. deepsight cloud is built for surveys and the analysis of open-ended responses. You can load free text from the records into deepsight cloud as an Excel or CSV file and analyze it by topic there.
That depends on your documents: on image quality, structure and the fields themselves. A blanket rate says little about that. What counts is what the measurement on a sample of your own documents shows.
A few sample documents for each document type, the details you transfer by hand today and – if available – work instructions or review rules. If the samples contain personal data, we agree beforehand how you send or redact them.
We work that out with your IT team: whether a file is enough, for example in Excel or CSV format, or whether the data is passed on via your system’s interfaces. The integration is developed in the project.
Yes, if we process personal data on your behalf – under Art. 28 GDPR. What we state about running on Microsoft Azure in the EU applies to deepsight cloud and slide factory; for custom projects, the infrastructure depends on the project. More under Hosting.
Related to data extraction
Have your documents assessed
Send us examples, and we will show you which fields can be extracted.