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.
Texten är källans egen beskrivning av publiceringen. Innehållet tillhör AI Engineer.
Mer att läsa
Server-Side Code Execution Tools for AI Agents, Compared
OpenRouter för 10 tim sedan
v0.40.0
Ollama för 11 tim sedan
Google froze its open source bug bounty program due to a ‘significant rise’ in AI submissions
TechCrunch AI för 14 tim sedan
Can ‘super intelligence’ and a non-binding safety pact solve AI’s image problem?
TechCrunch AI för 14 tim sedan