Semadox’s PDF DataXtract Engine is state-of-the-art technology. Wherever data from PDFs needs to be processed within a business process, Semadox has the right solution with FormXtractor and SmartXtractor.
Pdf documents processed in
State-of-the-art document processing
At the heart of Semadox’s technology lies the PDF DataXtract Engine. Our dual product strategy is built upon it. FormXtract or SmartXtract: the perfect solution for PDF data extraction in your business processes.
Depending on the use case, either the AI-driven SmartXtract or the form-based FormXtract may be more suitable – or perhaps a combination of both products.
Demotest SmartXtract
Semadox SmartXtract processes business documents using artificial intelligence. Ideal when PDF documents are not exclusively created electronically and when data extraction at header level is sufficient.
detailCapture: Processes header data with high precision
Any PDF technology: for every PDF document
Cheapest solution
Infinitely scalable
ROI in just a few months
For all PDF documents
Try Semadox SmartXtract Click on one of the business documents provided.
Demotest FormXtract
Semadox FormXtract processes business documents based on templates. Ideal for high volumes of documents with rather low document variance, for 100% precision and for data processing at position level.
DetailCapture+: Processes data at item level
E-PDF Pro: for PDF documents created electronically
100% accurate
Launch & Relax – no follow-up check required
Can be integrated into any existing data workflow
ROI in just a few months
Fully scalable
Try Semadox FormXtract. Click on one of the business documents provided.
We connect your system to Semadox. This includes setting routing rules in your email software that determine which of your emails should be automated.
Your ERP is connected to Semadox. We ensure that your specific system, such as EDIFACT or openTRANS, is adapted to Semadox so that it can automatically receive PDFs.
If a PDF is not recognized when entered, our fine-meshed monitoring sounds an alarm. With our team, we correct layout errors transparently and promptly within 48 hours.
Now the system is running and all your documents are automatically processed into structured data, which is then sent to your system.
Do you need a closer look?
Through our technical documentation, you can take a look at how our system works, with topology and HTTP endpoint communication, including example instructions.










With know-how and drive at your side
Artificial intelligence and the processing of PDF documents are our core competencies. We work directly with our experienced team of specialists in Austria to provide you with the best possible support.
Our system can be integrated via SFTP, HTTP or email and forwards the data to any ERP system (SAP,...).
Orders, invoices, order confirmations, delivery notes, payment advices and more are processed centrally and fully automatically.
We are constantly working on system improvements. System or recording errors are resolved within 48 hours.
Semadox is smoothly integrated into your workflow and connects seamlessly to your desired ERP system, without any IT resources.
Make an appointment for a consultation
In a joint discussion, we will give you specific insights and options for completely automating your data inputs