The Orchestrator

Not everything should be delegated. Before any build, the triage question is whether the work justifies the spend, and it has three tests.

Frequency times hours. On time savings alone, a task done once a month that takes twenty minutes is a poor delegation candidate; even a modest build can cost more than a year of doing it by hand. A task done ten thousand times a week that takes ten minutes can justify frontier prices. Estimate the volume and current cost, then compare them with the cost of building and operating the delegated version.

The first-run trap. Preparation, skills, memory setup, and failed drafts belong on the first run’s bill. Counted honestly, the first change may cost about what it would have cost the ordinary way. What the investment buys is the capability to move fast on everything after. It is the point Chapter 4 made about time, and it is equally true of money: a workload assessment that only prices the steady state is lying by omission.

Experiment versus production. A $2 run is a $2 experiment. The same run ten thousand times a week is a budget line the finance department will eventually find. The discipline is to price the production version, not the demo: the real volume, the real failure rate, the real retry behavior, and the real model — not the one the demo happened to run on. A surprising share of “agent bills” that land in executives’ inboxes are experiments that were never re-priced when they became production.