Home

All 27, on one page

The system in eight steps, then one rule from each lesson. Made to be printed, or kept open while you work.

Print this pageThe same as plain textGive it to your agent

The system

  1. 1

    Ask before building. The agent reads what exists, asks the blocking questions together, and records my decisions.

  2. 2

    Create one source of truth. The PRD defines the product, its users, its limits, and the decisions only I can make.

  3. 3

    Prove one complete user journey. A thin path through the interface, the logic and the database, before anything is made wider.

  4. 4

    Split the project into slices. Each slice owns one end-to-end outcome. The repository carries verified state between fresh chats.

  5. 5

    Coordinate specialist work. One lead agent assigns bounded tasks to builders and reviewers. Shared state records scope, diff, evidence, status and budget.

  6. 6

    Run safely while I am away. A written contract sets permissions, permanent fences, exit tests, and the point where a person is needed.

  7. 7

    Move through production gates. Review, automated checks, database readiness, deployment and a live check. Deployment alone proves nothing.

  8. 8

    Turn failures into controls. Each serious failure is written up, then pushed as far toward a test, a permission, a hook or a database control as it will go.

One rule from each lesson

1Choose the problem

2Assign the work

3Set the boundaries

4Judge the result

5Make it stick

6What stays mine

What stays human

These three are mine. A low-risk internal prototype may need fewer. A product that handles money, personal data or public claims may need more.

After all this, you should be able to explain

  1. Why a project starts with questions and written decisions, not with code.
  2. Why one vertical slice reduces risk more than finishing separate layers.
  3. How Git carries context between fresh agent chats.
  4. When to use a sequence, a loop or a graph.
  5. How an AFK run keeps irreversible actions under human control.
  6. Why working code, deployment and live verification are separate milestones.
  7. Why independent review must test intended behaviour, not only check for errors.
  8. How a failure becomes a durable rule or a mechanical control.
  9. Which tool names are replaceable and which principles stay.
  10. Why I stay the bottleneck on purpose.

Try “secrets”, “merge”, “handover” or “database”.