This page summarizes the changes and improvements to Skwiz.
23 Sep 2026
Skwiz now has an MCP server. MCP (Model Context Protocol) lets AI assistants like Claude or ChatGPT connect to Skwiz. You can set up and manage document types by describing what you need, instead of configuring every field by hand.
23 Sep 2026
Dashboards now have their own tab. The usage and performance dashboards have moved out of the settings to a new Dashboard tab in the top menu.
27 Jul 2026
You can now send documents to Skwiz by email. Each newly created mailbox gets its own address (e.g. abc123@inbox.skwiz.ai), and Skwiz automatically processes every PDF attachment as a separate document. Other file types are ignored.
12 Jun 2026
We've added a more detailed performance dashboard, so you can see how well Skwiz processes your documents and where there is room for improvement.
10 Apr 2026
We've added two features to make working through your inbox queue faster and less repetitive.
19 Mar 2026
We’ve introduced a few updates to make collaboration in Skwiz easier and give teams a clearer overview of what needs to be worked on.
04 Mar 2026
It’s been a while since our last product update, and a lot has changed in Skwiz.
07 May 2025
We've optimized our generative AI models to extract data from even the most complex table structures.
24 Mar 2025
You can now fine-tune generative AI models specifically for your document types, delivering strongly improved extraction accuracy with minimal training data.
21 Jan 2025
We’ve rebuilt our PDF splitter to handle any document type intelligently with an accuracy above 95%. This update is now live for all users. Drop your next multi-document PDF into Skwiz and see the new splitter in action.
17 Nov 2024
We've reworked our technical architecture to handle massive PDFs.
11 Sep 2024
Skwiz now supports single sign-on for both Microsoft and Google accounts.
18 Jan 2024
You can now further automate your document workflows with our PDF splitting feature.
19 Oct 2023
You can now detect all barcodes and signatures on your documents. Configure this new functionality with the click of a button in your Document type settings and Skwiz will locate the position of each object and extract the data associated with the barcodes.
26 Sep 2023
Our network of trusted partners plays a significant role in introducing and delivering Skwiz to our clients effectively. To streamline the management of various clients within Skwiz from a single account, we’ve added a collaborative partner interface. This allows you to facilitate client introductions and conduct demos showcasing value from day 1. In addition, you can invite colleagues and maintain a full overview and control, all from a single hub. We are confident that this feature will simplify your project management and further improve your experience in Skwiz.
10 Aug 2023
We’re introducing our optimized invoice and receipt models, which are specific pre-trained models that use machine learning instead of large language models (LLMs). Trained on tens of thousands of example documents, these models have already demonstrated their effectiveness in improving data extraction for a number of our clients.
01 Aug 2023
You can now use classification, also known as categorisation, on multiple levels of your documents.
05 Jul 2023
Skwiz enables you to extract data from any type of document with the use of large language models (LLMs) like ChatGPT. These LLMs have the capacity to understand and generate natural language, enabling very precise extractions and allowing simpler and more enjoyable ways to work with documents, in virtually any language. This further results in shorter and less costly setups in comparison to traditional rule-based or machine learning approaches as it mitigates the need for extensive training data and time-consuming manual labelling.
We use cookies to provide you with the best user experience. For more information, please read our Cookie Policy.