Latent Space

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

Published 2026-11-06 · Duration 50:38

Summary

Adit Abraham, CEO of Reducto, discusses the challenges of reliable AI document parsing, arguing that general-purpose LLMs often fail on complex structures like tables and handwriting. He details Reducto's approach, which involves specialized pipelines and model routing to achieve high fidelity. Key technical advancements include the proprietary R1 model, designed for end-to-end processing and improved cost efficiency, and a focus on continuous evaluation to catch production failure modes, especially in low-margin-of-error industries like healthcare. The discussion also covers the architectural shift toward treating document processing as a search and context synthesis problem, rather than just a generation task.

Download summary

Key takeaways

  1. The Limitations of General-Purpose LLMs for Documents 17:37

    Frontier models can fail by silently dropping rows or missing context in long documents, a failure mode not visible in production. Specialized platforms are necessary to audit and ensure data integrity, especially when 99% accuracy is insufficient for critical use cases. (10:57)

  2. Reducto's Architecture and R1 Model 6:59

    Reducto utilizes a model routing strategy, combining smaller traditional CV models for baselines with larger models for complex tasks. The proprietary R1 model aims to provide end-to-end processing, improving accuracy and simplifying pricing by eliminating complex multipliers. (4:19, 9:29)

  3. Focus on Continuous Evaluation and Failure Modes 21:45

    Reliability requires continuous evaluations (Evals) to spot imperfect, out-of-distribution failure patterns, not just incorrect data points. For high-stakes industries, traceability (knowing the source of extracted data) and accurate confidence scoring are critical. (13:05)

  4. The Nature of Document Processing as a Search Problem 20:35

    The core problem is often viewed as a search problem: retrieving relevant context from multiple sources (e.g., a file system) and synthesizing it, rather than solely relying on Retrieval Augmented Generation (RAG) or simple document parsing. (12:35)

More digests on AI Document Parsing

Technical details

  • Document Processing Evolution 215s

    The field has evolved from OCR to IDP (Intelligent Document Processing) and now incorporates LLMs and agents. The goal is to replicate human-level fidelity when reading documents, which is a complex vision problem. (3:35)

  • Reducto's Capabilities 329s

    Reducto aims to be the best platform for any interaction with unstructured files, covering data extraction, classification, and editing. It handles the entire workflow from reading to writing into documents. (5:29)

  • Model Strategy and Ownership 700s

    The company's mandate is to be the best provider regardless of whether the model is in-house or external. The stack has shifted toward in-house models to maintain control and performance consistency. (7:00)

  • Scaling and Performance Metrics 929s

    Reducto processes over a billion pages monthly. Performance improvements are measured not just by accuracy, but by cost efficiency and the ability to drive the Pareto frontier (better intelligence per dollar). (9:29, 14:30)

Mentioned resources

  • Reducto (Company/Product)
  • Deep Extract (Product/Benchmark)

Channel & topics

Watch on YouTube · Back to latest

This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.