Parsing the Epstein Files for JMail — Palak Agarwal & Omar Alhait, Reducto

Why watch

A technical case study showing how Reducto's document processing pipeline handled the Epstein files—handwritten flight logs, heavily redacted PDFs, and inconsistent document formats—to create structured, searchable data for JMail. The talk covers schema design, extraction workflows, and practical evaluation strategies for document processing systems. For engineers building document pipelines or working with complex, semi-structured documents.