The challenge
In a world that is becoming increasingly automated, working with unstructured documents remains a challenge. Think of insurance files, medical documents, permits, and HR onboarding: documents play a crucial role almost everywhere. This also applies to the classic example of accounts payable and invoice processing. Invoices need to be matched with purchase orders and received items, but reference codes and product information are used differently by everyone. In some cases, information is simply missing or there is handwritten text within the document. The result? A lot of manual work is required, which is extremely labor-intensive. Processing time can take up to several days or even weeks, while technology is available to fully automate this process from start to finish.
The approach
With Intelligent Document Automation (IDA), KPMG helps organisations automate document-driven processes more effectively. It starts with the process itself and the desired outcome. Automation does not begin with technology, but with understanding how the process should ideally work.
This approach follows the ESSAR method: Eliminate, Simplify, Standardise, Automate and Robotise. Together with the organisation, each step is reviewed to determine what is necessary, where bottlenecks occur and where the biggest improvements can be made. Only then is the most suitable technology selected.
A key part of modern document automation is the use of Large Language Models (LLMs). These models are trained on large volumes of text, allowing them to interpret documents, classify content and extract relevant information, even when document structures vary. Unlike traditional template-based systems, LLMs recognise that terms like “order number”, “order ID” or “purchase reference” can mean the same thing in different contexts.
For a client with a product catalogue of more than 40,000 items, this approach was applied to processing incoming orders. The organisation wanted to speed up the process and reduce the number of manual checks. Based on the analysis, the AI tool Rossum was selected, a solution designed to extract and interpret large volumes of documents. KPMG supported the implementation and integrated the solution into existing processes and systems.
The result
After implementation, nearly 95% of all required data was automatically recognised and processed. Processing times dropped significantly, and the need for manual corrections was greatly reduced.
Employees spend less time on repetitive administrative work and can focus more on analysis, customer interaction and process improvement. At the same time, customer satisfaction improved as orders were handled faster and more consistently.
The next step is the development of so-called AI agents. While LLMs focus on interpreting information, agents can also take action independently, such as requesting missing data from a supplier. This creates increasingly automated processes, where technology and human expertise reinforce each other.
The team that made the difference
A multidisciplinary team from KPMG Netherlands supported the organisation in analysing and automating document-driven processes. By combining expertise in AI and data with Digital Process Excellence, they helped build a scalable solution that improves both efficiency and customer experience.
