Skip to main content
One agent turn is rarely one job. This takes a support workflow billed as a single line item and splits it into four tasks. Time: about an hour of code changes, then a week of traffic to read.
1

List the model calls on one path

Pick your highest-volume path and write down every call it makes. Most teams find more than they expected, because retries, guardrails and formatting passes are easy to forget.For a support reply: classify the intent, fetch the account, draft the reply, check the tone.
2

Name each one

One name per job. A name that survives a prompt rewrite.Resist the urge to encode the tenant or the model. Tenants go in user.
3

Label them

Keep model as it was if you want zero behaviour change; the labels work either way. Only auto lets a task get cheaper later.
4

Wait, then read the split

Give it enough traffic to be representative, usually a week. We report spend per task.The result is almost always lopsided. A guardrail call that nobody thought about turns out to be a third of the bill, because it runs on every turn while the expensive-looking reasoning call runs on one turn in twenty.

What good looks like

Ideal. Take it to Write an eval contract and route it down.
Usually a sign the split is too fine. Merge tasks that share an input shape and a definition of correct.
Still too broad. Something inside it branches into genuinely different jobs. Split again.

Next: write an eval contract

Nothing can be routed until correct is defined.