Enterprise AI, agentic systems, and the gap between what AI promises and what it delivers.
Principal FDE. Building enterprise and personal AI systems.
Enterprise AI projects don't fail because organizations lack information. They fail because that information exists in a form no system can reliably act on. Curio is built to fix that.
Every agent platform shipping today treats a model call as a request — short-lived, stateless, RPC. Real agents have memory, in-flight tool calls, and partial plans. The request model makes you rebuild context on every call. Sessions are the unit.
Multi-agent systems don't fail because the agents are stupid. They fail because the coordination cost wasn't budgeted for.
Six persistent Claude Code sessions, scoped to different domains, coordinating through MissionControl. Here's what it looks like in practice.
The dominant model for agent orchestration is the linear pipeline. It breaks down the moment two agents need to touch the same artifact. Here's what the alternative looks like.