Skip to content

Brian Raymond

Unstructured.io

  • 1 episode on Chain of Thought
  • 4 topics covered
  • 1 full transcript
  • Nov 2024 first on the show
Brian Raymond

Brian Raymond is the founder and CEO of Unstructured.io, which prepares messy enterprise data for AI systems. He joined the "Got Agents?" panel on Chain of Thought to define what an AI agent actually is and to work through the data-management and deployment problems teams hit when they move agents toward production.

What this guest adds

Brian Raymond points to role-based access controls as a data availability obstacle for enterprise agents. Read transcript at 10:34

Cover art for Got Agents? Agentic Workflows & Architecture | Weaviate, Unstructured & CrewAI

Latest episode with Brian Raymond · EP 2

Got Agents? Agentic Workflows & Architecture | Weaviate, Unstructured & CrewAI

Brian Raymond, Bob van Luijt & João Moura ·

Show notes & transcript → All listening options →

Episodes

What the conversations cover

These notes summarize the episodes featuring Brian Raymond, including other speakers in panel conversations. Follow a source link to read the discussion in context.

EP 2 Got Agents? Agentic Workflows & Architecture | Weaviate, Unstructured & CrewAI

  • João Moura (CrewAI) draws the line at agency: a fixed if-this-then-that flow isn’t an agent. An agent “controls the flow of the application,” using an LLM “as a brain” to reason about what tools to use, when to use them, and how to format the answer — “something that has agency.” Episode takeaways
  • Bob van Luijt (Weaviate) argues data is still the bottleneck, not models. A CIO told him: “it’s all great what you guys are building over there… but I still have like 15 ERP systems and I can’t, you know, I can’t make heads or tails of it.” Low data quality and not getting to insights remains “the number one problem.” Episode takeaways
  • João Moura (CrewAI) warns agent architectures start simple but explode in production: once inside an enterprise you bolt on a caching layer, a memory layer (long-term memory of what the agent has done and learned), guardrails, validation, security, and distribution — and the complexity “can get…to skyrocket a little bit.” Episode takeaways

In their words

On the success side, we're hoping to move this into prod somewhere time around, like after Thanksgiving around like reinvent December 1, but this isn't like prop. I, it depends on how strict you are with the definition of agents, but with the definition I gave you earlier, we're looking at like dynamic pipelines where models are sampling data. Like say you have a fresh, you're doing a fresh pull from S3.

Brian Raymond Got Agents? Agentic Workflows & Architecture | Weaviate, Unstructured & CrewAI · 18:56

Transcript excerpts; ellipses mark omitted words. Some automatically selected quotes have filler words removed.