Content classification is a distinct use case that is often considered secondary to content extraction. However, content classification, and more importantly, automatic document separation, is a critical aspect of intelligent capture. This process lays the groundwork for effective content extraction and supports advanced technologies such as generative AI. Despite its importance, cloud services have been slow to recognize and address the need for automated document separation. To fill this technological gap, enChoice has developed a supervised machine learning classification engine that empowers superusers to visually train documents, effectively addressing this need.