Lesson 0001 · about 6 minutes

Why software factories fail

Not because agents cannot produce working code. Because the factory rewards what it can measure quickly—and maintainability is not one of those things.

The mechanism

1. GenerateCode arrives cheaply
2. VerifyTests pass quickly
3. AccumulateDesign debt stays hidden
4. PayFuture changes become costly
Factory throughput is a local metric.
Maintainability is a delayed system property.

A benchmark such as SWE-bench asks whether a patch resolves an issue without breaking known tests. That is useful evidence. It does not answer whether the patch preserves clear boundaries, keeps one concept in one place, or makes the next unknown requirement cheap. Those costs may surface months later as “shotgun surgery”: one conceptual change requiring edits in many places.

Harness engineering genuinely helps. Better tools, context, sandboxes, tests, and review loops raise the floor. But a harness cannot optimize a property for which it has no timely, reliable signal. More loops around an incomplete verifier optimize the incompleteness harder.

Retrieve before revealing

Scenario: An agent ships ten passing PRs per day. Three months later, every feature requires edits across six modules. Which capability was never verified?

The practical response

Keep humans at the high-leverage decision points: product intent, architecture, program shape, and review of small vertical slices. The goal is not to supervise every keystroke. It is to catch expensive design errors while the diff is still small.

Your diagnostic: identify the reward, its blind spot, the delay before harm appears, and the cheapest human steering point.

Apply it now

Pick one agent workflow you use. Without reopening this lesson, answer:

  1. What fast signal declares success?
  2. What important quality can that signal miss?
  3. Where would you insert the cheapest human judgment?

Reply with your three answers. I’ll give immediate feedback and record the learning only after you demonstrate it.