We instrumented 11 production agents with real token accounting. In 9 of them, the most expensive step wasn't the model.
This story is from 2026-10-28. It is preserved in the archive; the latest stories are on the live feed.
Last quarter we finally stopped trusting the LLM bill. We wired real per-step token attribution into 11 production agents — not the default "total tokens" the provider hands you, but a tracer that tags every call, every tool, every cache lookup with the trajectory it belonged to. The number that br…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-28 01:06 · DEV Community — AI
We instrumented 11 production agents with real token accounting. In 9 of them, the most expensive step wasn't the model.