Data entry is dead

Artificial Intelligence for documents is here.

How it works

Do you spend a lot of time dealing with data input from invoices? Rossum's deep learning technology radically simplifies this process.

Convert your digital and scanned invoices to structured data (UBL, XML or CSV) with no prior setup. Experience a quantum leap beyond traditional OCR, and eliminate deployment costs.

Get started

Rossum's Invoice Robot technology preview
for US invoices (in English) is now available.

Test with our sampleExplore API docs

About Rossum Technology

Rossum develops advanced neural networks that can read documents very much like humans do. Unlike existing text mining approaches, Rossum reflects the way humans read in its unique deep learning approach. Neural networks extract structured knowledge from an unlimited number of documents, of any format, thousands of times faster than a human could.

About us

Petr Baudis
Petr was one of the original authors of Git, built one of the top AIs for the board game of Go and his text understanding algorithms rival Facebook's neural networks.
Tomas Gogar
Tomas loves transforming scientific results into easy-to-use products. In his research he proposed an unique way of employing visual information in the field of text mining.
Tomas Tunys
Tomas is keen on mathematics and statistics which drives his passion for deeper understanding of the underlying principles making machine learning models work.
Ondrej Raska
Ondrej is co-founder and partner at Miton, CEE investment group with +100M euro in portfolio companies. He loves the creative process of building tech company from scratch.