Castuner

Agentic Conversations (formally mlops.community)

Demetrios

Relaxed conversations and technical deep dives around AI Agents. This Show is brought to you by the Agentic AI Foundation where the leading agentic open-source projects like MCP, Agents.md, and Goose live. See more at aaif.io

Podcast website

Listen in your app

Episodes

565 episodes

  1. Why Stripe Cut 500,000 Internal Docs Down to 5,000? 32:36
  2. My AI Agent Bought Me A Car 35:15
  3. Cut One AI Cost and Two More Grow Back 41:43
  4. How Stanford Teaches AI Coding Now 43:42
  5. From Slop Code to Software Factories 47:00
  6. Tim O’Reilly 34:11
  7. AI Agents Need a Babysitter 45:52
  8. Token Maxxing Is Over and Here Is What Comes Next 35:19
  9. The World Wild Web & Bots With Buying Power 49:58
  10. Agents Acting Safely on Our Behalf 23:05
  11. Bridging the Gap Between AI Builders and Domain Experts 22:36
  12. Inside a Game Where AI Agents Never Sleep 1:01:03
  13. How a Logistics Giant Keeps AI Data Locked Down 20:34
  14. The Caveman Prompting Challenge 44:07
  15. AWS Has 16,000 APIs. Can MCP Handle It? 41:38
  16. Skills over MCP on the streets of Tokyo 32:30
  17. Walking Tokyo Talking Agent Protocols 28:49
  18. Why Cost Per Million Tokens Is A Useless KPI? 38:49
  19. The Five-Layer Cake Approach to Scaling AI Without Wasting Money 38:55
  20. The Winchester Mystery House Problem in AI Development 59:41
  21. How Predictive Analytics Stops Budget Overruns Before They Happen? 29:23
  22. How To Delegate To An Agent Like You Would An Employee? 55:15
  23. Why Your AI Bill Will Double Before It Gets Better 32:24
  24. MCP Goes Stateless 52:27
  25. AI Hype vs. Real Value 42:37
  26. The Creator of FastMCP Explains the Future of MCP 55:11
  27. What Happens When Every Developer Has 20 AI Agents? 34:37
  28. AI Agents Should Be Treated Like Hackers 31:35
  29. Developers May Stop Depending on Libraries 46:52
  30. 10 Cities. 4 Countries. One Unexpected MCP Lesson. 22:18
  31. The Next Programming Language Is English 38:13
  32. Omnigent: Composition, Control, and Collaboration for AI Agents 58:16
  33. The Current State of Agentic Retrieval - Qdrant Roundtable 58:54
  34. AI Agents in Healthcare? 39:28
  35. Coding Agents Are Secretly General Agents 1:12:02
  36. The Dark Side of MCP Servers 1:09:59
  37. Sandboxing, Agent Harnesses, and Agent Teamwork 1:19:53
  38. Zipline Roundtable episode: Building Real-Time ML Systems with Zipline + Chronon 51:27
  39. MCP Servers Are Becoming the UI for AI Agents 47:21
  40. Agents & the $40M Bet on Multiplayer AI 1:20:46
  41. From Single-Player to Multi-Player: Operating AI Agents at Scale 55:54
  42. The Control-vs-Magic Spectrum Building Agents 43:18
  43. Logs Are All You Need: Rethinking Observability with AI Agents 46:39
  44. AI Is Fast. AI Projects Are Slow. Let's Fix That. 56:47
  45. Architecting Modern AI Systems: Platforms, Agents, and Integration 56:59
  46. [Special Announcement] MLOps Community Linux Foundation 2:19
  47. Inside Just Eat's AI Lab: Voice Agents & Agentic Commerce 1:18:38
  48. Autonomous Agents at Work: From OpenClaw Hype to Enterprise Reality 42:19
  49. Agents are Just While Loops 41:11
  50. The Latency Goldilocks Zone Explained 48:13