Skip to content

Collections

Best Chain of Thought Episodes on Multi-Agent Systems

Many agents, one system: orchestration patterns, protocols, and the overhead they add.

These four conversations approach coordination from different parts of the stack. Mikiko Chandrasekhar discusses engineering discipline, João Moura maps orchestration, and Siva Surendira compares managerial, DAG and hybrid patterns. Giovanna Carofiglio introduces AGNTCY and the protocols for discovering agents and exchanging messages between them.

  • 4 episodes
  • 4 guests
  • 3 hours of listening
  • 1 jump-to moment
  1. 1 EP 33 40 min Transcript Mastering Multi-Agent Systems | MongoDB’s Mikiko Chandrasekhar Mikiko Chandrasekhar, MongoDB Mikiko Chandrasekhar argues that agents are software products and should be developed with the rigor and best practices of software engineering and MLOps.
  2. 2 EP 29 50 min Transcript The Emerging AI Agent Stack | CrewAI’s João Moura João Moura, CrewAI CrewAI’s João Moura maps the emerging agent stack and explains why nondeterministic agents change how developers test their systems.
  3. 3 EP 21 39 min Transcript Why Enterprises Need a Different Approach to AI Agents | Lyzr’s Siva Surendira Siva Surendira, Lyzr Lyzr’s Siva Surendira walks through the orchestration shapes (managerial, DAG and hybrid) and where each one runs into an enterprise’s integration and data-readiness limits. Jump to the moment · 12:53 · Combining manager and DAG →
  4. 4 EP 31 41 min Transcript Architecting Reliable Agentic AI | Cisco’s Giovanna Carofiglio on the AGNTCY Collective Giovanna Carofiglio, Cisco Cisco’s Giovanna Carofiglio on AGNTCY and the Internet of Agents: agent discovery, the transport layer under agent-to-agent traffic, and why MCP and A2A are solving different problems.

More collections

All collections →

New here? Start with five → Browse by topic →