Papers on agentic and multi-agent systems (MAS) skyrocketed from 820 in 2024 to over 2,500 in 2025. This surge suggests that MAS are now a primary focus for the world’s top research labs and universities. Yet there is a disconnect: While research is booming, these systems still frequently fail when they hit production. Most teams instinctively try to fix these failures with better prompts. I use the term prompting fallacy to describe the belief that model and prompt tweaks alone can fix systemic coordination failures. You can’t prompt your way out of a system-level failure. If your agents are consistently underperforming, the issue likely isn’t the wording of the instruction; it’s the architecture of the collaboration.
