AI-powered data extraction for finance professionals from unstructured documents
ProSights extracts structured financial data from PDFs at scale—hundreds to thousands of datapoints per document—and deposits them directly into Excel. The stack (ChatGPT, RAG, Python, Office.js, VBA) reveals a purpose-built extraction engine optimized for document parsing and spreadsheet integration rather than a horizontal platform. Active projects span core extraction tech, AI workflow automation, and institutional onboarding, while pain points cluster around reconciliation delays and expanding beyond PE/IB—suggesting the product is mature in its core vertical but the team is working to broaden TAM into broader financial services.
Notable leadership hires: Head of Growth
ProSights builds a data extraction engine purpose-built for finance professionals who spend hours copying data from PDFs into spreadsheets. The product pulls structured data directly from unstructured documents and lands it in Excel in the exact schema users need. Their customer base includes the majority of top global private equity firms, along with bulge bracket banks and independent advisors. The company is 11–50 people, engineering-heavy in seniority (7 senior/lead roles out of 9 total), based in New York, and currently focused on both deepening adoption within large financial institutions and opening new workflows beyond PE and investment banking.
ChatGPT, Next.js, React, Python, TypeScript, Office.js, VBA, C#, .NET, RAG, Rust, and Go. The stack emphasizes document extraction (RAG), spreadsheet integration (Office.js, VBA, Excel), and multi-language backend resilience (Rust, Go, Python).
Core extraction tech and AI finance workflow automations, institutional onboarding for large financial services firms, and expansion beyond PE/IB into adjacent financial services workflows. Product roadmap is informed by forward-deployed customer situations.
Other companies in the same industry, closest in size