Skip to content

João Moura

CrewAI

  • 2 episodes on Chain of Thought
  • 7 topics covered
  • 2 full transcripts
  • Nov 2024 first on the show
João Moura

João Moura is the founder and CEO of CrewAI, a framework for multi-agent systems. He came on Chain of Thought first to define agents as software with agency, then returned to map the emerging AI agent stack and the questions enterprises face when they run hundreds or thousands of agents in production.

Cover art for The Emerging AI Agent Stack | CrewAI’s João Moura

Latest episode with João Moura · EP 29

The Emerging AI Agent Stack | CrewAI’s João Moura

João Moura, CrewAI ·

Show notes & transcript → All listening options →

Episodes

What the conversations cover

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

EP 29 The Emerging AI Agent Stack | CrewAI’s João Moura

  • João Moura traces the agent stack from the data layer up — Databricks, Snowflake, BigQuery, then LLM orchestration, authentication, and connectors, topped by agentic apps with a natural UI. His point is that no single product covers it: enterprises going “agentic native,” running hundreds or thousands of agents in production, need a whole suite. Episode takeaways
  • Moura argues the early enterprise questions — memory, graphs versus events, which open-source project — are a commodity, with roughly twenty ways to do memory and none of it mattering much. The questions that decide outcomes surface only once a company commits to scale: how to provision agents, authenticate them, evaluate them, and measure them. Episode takeaways
  • Infrastructure choices are reopening rather than settling, per Moura. Companies are calling workloads back from the cloud, some to self-host and some demanding on-prem physical servers, and he points to a scenario where running at huge scale on physical hardware can save around 60% — though he won’t predict which way it lands. Episode takeaways

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

I think that's a little bit on overall the vision that we're seeing in the market. And the potential is right there. I think this is a unique time window for companies that are operating in the industry, given how hot the market is. And what that means for crew is land grab. It's like literally closing as many customers as we can and help them to get to success.

João Moura The Emerging AI Agent Stack | CrewAI’s João Moura · 44:11

Where now companies can move as fast as the market and then double down on what works. So I would say that would probably be the most important thing from my point of view for the future of agents can like live to its full potential.

João Moura Got Agents? Agentic Workflows & Architecture | Weaviate, Unstructured & CrewAI · 25:15

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

Essay featuring João Moura