Building AI That Thinks Like a Human - Brian Raymond Unstructured on Agentic Software & Human-AI Collaboration | EP 128

Building AI That Thinks Like a Human - Brian Raymond Unstructured on Agentic Software & Human-AI Collaboration | EP 128

From AI Agents Podcast by AI Agents Podcast

March 17, 2026 · 43 min · Season 1 · Episode 128

About this episode

In this episode, Demetri Panici interviews Bryan Raymond about the importance of data preparation in AI and the challenges faced in enterprise AI implementations.

Subscribe to AI Agents Podcast Channel: https://link.jotform.com/subscribe-to-podcast In this episode of the AI Agents Podcast, host Demetri Panici sits down with Bryan Raymond, founder and CEO of Unstructured, to break down one of the least flashy but most important layers in AI: data preparation. They dig into why so many AI prototypes still fail in practice, why RAG systems struggle with messy enterprise data, and how structured inputs like JSON, Markdown, and HTML can dramatically improve model performance. Bryan explains how Unstructured helps enterprises turn raw files, scanned documents, audio, video, and other messy sources into AI-ready data for RAG pipelines and agent systems. The conversation covers why context quality matters so much, why tables and document layout are still hard for models, how vision-language models changed the game, and what it takes to move from AI prototype to production. They also get into where AI is heading in 2026: declining failure rates, more practical “bread and butter” use cases, better multi-agent systems, and why companies like Cursor and Lovable have succeeded by packaging great UX around powerful infrastructure. If you want a clearer…

People in this episode

Host: Demetri Panici

Guest: Bryan Raymond

Topics covered

  • AI data preparation
  • human-AI collaboration
  • enterprise AI
  • RAG systems
  • model performance
  • AI prototypes
  • future of AI

Keywords

  • data preparation
  • AI prototypes
  • RAG systems
  • enterprise AI
  • model performance
  • vision-language models
  • multi-agent systems

Mentioned in this episode

Organizations: Unstructured, Cursor, Lovable

More episodes of AI Agents Podcast

Explore listener stats, chart rankings, contacts and more on the AI Agents Podcast podcast page.