Book a call

Notes from the booth3 min read

Start with a workflow, not an agent.

Default to a fixed workflow, and use an agent only for the judgment call inside it.

Andre Shonubi

An isometric tabletop with a searchlight over an empty inbox and a rail that splits at a blue switch.

What happened

In its Q3 2026 AI Workflow Index, Zapier compared two ways to run AI work. One is a scheduled agent that uses a model to check for work and decide what to do. The other is a step workflow that starts when something happens, and calls a model only when reasoning is needed. Zapier modeled 2,944 AI workflows from 360 companies. On its central estimate, the scheduled agent cost 2.1x as much overall. For jobs with fewer than 30 completed runs a month, which were 61% of the sample, it cost 8.3x as much. For jobs that ran 30 or more times, the multiple was 1.2x. These are modeled estimates at October 2026 list prices, not bills. Zapier also notes that a scheduled agent can still spend tokens finding out there is nothing to do, and that for most workflows in the study, letting software run the path cost less.

Primary source: Zapier, Q3 2026 AI Workflow Index

My take

I would default to a fixed workflow, and use an agent only for the judgment call inside it. For a 10 to 50 person team, a lot of useful jobs live in that low volume group: a weekly check, a form that arrives a few times a month, a renewal that almost never fires. A scheduled agent still spends tokens looking for work when the queue is empty. Software can wait for the event and then run the steps.

The plain test I would use is this. Write the steps for one real job, as you would hand them to a new teammate. If you can write every step for one real run, it is a workflow. The step where you would write "it depends" or "use judgment" is where the agent goes. Keep that step narrow. Do not hand the model the whole path just because one decision is hard. Build the path first. Call the model when a person would have to decide, not to watch an empty queue.

Next step: Book a call at codedre.com/call.

More notes

  1. 3 min readMeta's smallest model is built for everyday agent work.A capable model can plan. A smaller one can handle the volume.
  2. 3 min readClaude can now read your bank accounts. It cannot move a dollar.Personal money is the demo. The pattern is bigger.
  3. 5 min readTen questions that find the work worth automatingThe checklist I run on every first call. Run it on your own week.
  4. 4 min readThe work that grows every time you hireSome tasks scale with the business. Others scale with headcount. Only one kind is worth keeping.
  5. 4 min readNothing leaves the building without a yesHow I run eight agents across three businesses without letting any of them send an email on its own.
  6. 3 min readKill the automation nobody usesZero form submissions is an answer. Narrow, scheduled and boring beats broad and clever.