In “Micro and macro agents: The emerging architecture of the agentic enterprise,” I proposed a three-layer architecture for enterprise AI. Macro agents orchestrate end-to-end business processes. Meta agents provide governance through monitoring, compliance, security, and human oversight. As enterprises begin deploying thousands — and eventually tens of thousands — of autonomous agents, token costs have become a major concern. To track this economic concern, meta agents should do more than simply being the governance agents.