- High quality multi-tenant document OCR that works on diverse image quality settings
- Build document "split" models to break pdf packets into discrete documents
- Build document classification models to categorize documents into custom groups
- Build extraction models to capture elements of data from unstructured documents
- Create a custom data schema or ontology unique to your business
- Import and export data without programming
- Collaborate accross teams by sharing projects and permissioning priviliges
- Review extracted data and model outputs en masse with a unique view
- Use human-in-the-loop views to tune models to your business and guarantee quality
- Integrate with internal applications using an API
Documentation
Read more detailed descriptions of the platform and learn how to use the api to build your own integrations.
