The distributed systems framing is right but it undersells the problem. In a traditional distributed system, each node runs code a human wrote and can reason about. When something fails, you trace the call chain and find the bug.

With multi-agent development, each agent generates code that no single human fully understands. The failure mode isn't a consensus problem or a network partition. It's a comprehension partition. Five agents each wrote part of the system. None of them hold a mental model of the whole. Neither does the human who orchestrated them. When it breaks, there is no call chain to trace because there was never a unified understanding of what the system was supposed to do at that level of specificity.