Automated Documents Processing


Every company faces the challenge of processing the documents it receives in the most efficient way.

Document processing is time consuming and prone to errors, and the volume of documents to process can be very high for customer-facing companies.
Which means that automating this task has a significant potential in terms of operational optimisation.

This is the reason why Sagacify decided to use its AI knowledge to automate document processing tasks.

The resulting product is called Skwiz. 


Skwiz is capable of automating most tasks related to document processing in companies, on a wide (and growing) number of document types: 

  • Document splitting
  • Document type classification
  • Automatical identification of specific fields in documents
  • Extraction of line items in tables 
  • Cross check values between line items
  • Automated or manual validation depending of the confidence of the extraction

These capabilities, used alone, or in conjunction other Sagacify solutions, like Mailbot, Sagacify’s email processing solution, means that Skwiz can be used as a central tool for automating most of the incoming documents processing of a company, without the need to rely on templates or documents models that are painful to maintain. 


To achieve these high-performance results, Skwiz relies on advanced AI models specially designed to automatically extract and structure all the data contained in invoices, receipts, and other semi-structured documents, without the need for templates. Our unique model uses a combination of NLP and computer vision to understand the document semantically, but also spatially, like a human would. 

Today, Skwiz is the central piece of the administrative optimization initiative in several large companies, in various sectors such as insurance, banks, financial software, but also logistics or the public sector.

Related cases