Cooking with Reducto’s CEO: Why PDFs Still Break AI — Adit Abraham

Document-heavy agents miss rows and misread tables even with frontier models. The discussion covers routing hard pages to specialized models and catching extraction failures in production.

• eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.

• videoDeep Dive: Anthropic S-1 Myths and Mythos — Jamin Ball, Altimeter
• video⚡️ The 2026 Software Factory Standard — Zach Lloyd, Warp.dev
• videoBuilding Legal Agents When You Can't See the Data — Jacob Lauritzen, CTO of Legora
• videoUsing Agents for Long-Horizon Financial Work — Aman Singh, Arca

• videoFrom Ingestion to Agents: How AI Teams Build on Document Intelligence — Adit Abraham, ReductoAI Engineer
• videoWhy We Deleted Our MCP Server and Rebuilt It — Abhi Arya, ReductoAI Engineer
• podcastThe 100-person AI lab that became Anthropic and Google's secret weapon | Edwin Chen (Surge AI)Lenny Rachitsky

Checking sign-in…

Loading comments…