Tokens measure activity. They don't measure work. An agent doesn't answer. It works. Physics holds. Our metrics should too. A joule is a joule: on a steam engine, on a server rack, in a data center. Energy consumed is not the same as useful work delivered.

A Stanford study across 500+ agent tasks found agentic runs consume up to 3,500× more tokens than single-turn calls — often looping over bloated context logs without making progress. Three architectural patterns are essential to scale economically: context budgets before orchestration, queryable context instead of cumulative, and strict schema validation before inference.

GitHub Copilot's move to token-based billing surfaced a planning gap, not a pricing one. Until teams start tracking revenue, margin, or value created per million tokens, token economics stays in the finance review — not in the design decision where it belongs.

Observability is the first serious layer of AI in production, but once you can see what the system is doing, the harder question is whether it's still serving the business outcome it was put there to support. A system can stay within latency budgets, pass health checks, and still drift completely outside the intent it was supposed to operate within.