Your Agents Are in Solitary Confinement: Why MCP & A2A Aren't Enough — Vlad Luzin, Band
If you run Claude and Codex side by side, one planning and one reviewing, you're doing the job of a network router, passing messages between two stateful agents by hand.
Loop engineering hands that job to a script. Neither one lets agents actually work together. Vlad Luzin (Co-founder & CTO, Band) explains why connecting agents is a distributed systems problem. Bigger context windows don't fix the single-agent bottleneck. Messaging platforms like Slack, Discord and WhatsApp are built for humans and block bot-to-bot traffic. Protocols like MCP and A2A are too low-level: stateless calls, one-way client/server, no discovery, and queues and timeouts you still have to build yourself. He then walks through what's needed: real-time ordered transport, persistence and rehydration, runtime binding across frameworks, agent-first abstractions (participants, rooms, routing) and enterprise governance. Two live demos show Codex, LangGraph, Claude Code and a personal assistant finding each other and collaborating in real time, with full human-in-the-loop visibility.
The text is the source's own description of its publication. The content belongs to AI Engineer.
