Posts tagged LLM Orchestration — AI × software engineering, made practical.
A sub-agent's "yes, I'm prepared" can quietly evaporate the second its context gets truncated — and most orchestrators have no way to notice until two agents have already clobbered the same resource.
Borrowing Raft's leader election into a multi-agent LLM pipeline makes the design doc look rigorous — right up until you notice it can't stop the one thing that actually goes wrong: two confident agents disagreeing.