Building a PDF Parser for Financial Data: Lessons from Arbiter V2

I’m Matthew, building Arbiter Briefs - an AI engine that helps founders make high-stakes decisions. This week we shipped financial PDF ingestion, and I want to walk through the architecture, the gotchas, and why we chose regex over ML for extraction. The Problem Our v1 was generating rulings based on web research + user input. But founders kept saying the same thing: “This would be way useful if you actually read my financial data.” So we added PDF upload.