Rossum, a leader in intelligent document processing, is thrilled to unveil Rossum Aurora: a next-generation AI engine poised to revolutionize document understanding and streamline automation from start to finish.
Rossum envisions a future where one person can effortlessly process one million transactions annually – getting one step closer with Rossum Aurora by overcoming the hurdle of achieving high accuracy quickly, no matter the document format.
What makes Rossum Aurora stand out is its focus on transactional documents, such as invoices, packing lists, or sales orders. Unlike generic AI models, this next-generation AI engine is tailored for speed and precision, ensuring no time is wasted on chatting with your document, or in dealing with hallucinated data.
At the core of Rossum Aurora is a proprietary Large Language Model (LLM) created specifically for transactional documents. This model is trained on one of the largest datasets in the industry, containing millions of documents with detailed annotations. Through its three levels of training, Rossum Aurora achieves human-level accuracy almost instantly, while being designed to provide enterprise-grade safety.
Also Read: France’s Mistral AI releases ChatGPT rival and partners with Microsoft
Early users of Rossum Aurora have experienced unseen levels of accuracy and productivity, such as:
- 10x reduction in the number of documents needed to reach desired accuracy;
- An average 37.6% error reduction, with zero hallucinated values;
- Accelerated discrepancy handling through generative AI custom emails straight into existing workflows.
“Rossum Aurora achieved a 92.6% accuracy rate after processing only 20 documents. To see the AI learning and instantly getting smarter gives us confidence we can truly deploy AI to automate processes and scale sustainably,” said Marco Favaretti, Financial Controller at Adyen, the global financial technology platform and one of Rossum Aurora’s early adopter customers.
“In 2017, we revolutionized the IDP market by introducing the first template-free platform. Today, we’re primed to replicate this success with the launch of our specialized Transactional Large Language Model,” commented Tomas Gogar, CEO at Rossum. “After two years of meticulous development, it’s ready to elevate learning speed, accuracy, and automation to unprecedented levels across the Rossum client base. We expect the industry to broadly adopt this approach in the coming year.”
SOURCE: PRNewswire
