Route cheap work away from expensive models

Summary

Long-running agents become expensive when supervision logic retries on expensive models. Separating task routing by complexity cuts spend to one-third while improving reliability through explicit state and hard retry limits.

Why it matters

Long-running agents become expensive when supervision logic retries on expensive models. Separating task routing by complexity cuts spend to one-third while improving reliability through explicit state and hard retry limits.

Sources

1. 1.moving heartbeat checks, cron pings, and other low-value supervision off Claude Opus cut spend to about one-third
2. 2.The expensive part usually isn't the main reasoning step. It's the invisible scaffolding around it.
3. 3.heartbeat checks, cron-trigger validation, retry bookkeeping, simple routing, status classification, watchdog logic, 'did this step finish?' checks
4. 4.Agents rarely become expensive because one prompt was huge. They become expensive because a workflow can't confidently tell whether it succeeded.
5. 5.A lot of teams pay premium model costs to compensate for weak state handling. That's backwards. Better state is cheaper than better prompting.