Matteo Collina @nodeland.dev · Apr 20 🔥 NEW BANTER: "AI Agents, Kubernetes, and the Sandbox That Made It Possible" Most teams building AI agents treat Kubernetes like it is optional. Until someone asks how to scale it. Or govern it. @lucamaraschi and I did a full launch week debrief. 📅 April 22nd 🔗 streamyard.com/watch/9n4cF3...
0 likes 1 replies
?
Replies
Here is the uncomfortable truth: agents are fundamentally stateful. Every assumption Kubernetes was built on, ephemeral pods, stateless workloads, horizontal scaling, works against you the moment your agent starts remembering things. The hard part was never the model. It was everything around it.