# Start Here — The 5-Phase System

> The five-phase system for building real software with AI: Context, Rules, Documentation, Verification, Feedback Loops. Read this once. Then start. No prior code required.

## The five-phase system for building real software with AI.

Read this once. Then start. No prior code required.

## The framework

### Phase 1: Context

Give AI the full picture. Project, audience, constraints, conventions, history. Without context, AI guesses.

**Failure class:** AI hallucinates because it doesn't know what you're building.

**Problem statement:** You re-explained the project five times in one session and AI still missed it.

**How it works:**

- Capture the full project brief, audience, and constraints
- Document the conventions that govern the code
- Surface the history — decisions, dead ends, what NOT to do
- Make context discoverable for the AI on every call

### Phase 2: Rules

Set the standards it must follow. Code style, schema, naming, security. Without rules, AI drifts.

**Failure class:** Code that drifts every time a model updates.

**Problem statement:** You shipped on Tuesday. By Friday, the same prompt gave different code. By Sunday, nothing worked.

**How it works:**

- Lock the rules in version-controlled spec files
- Tell the AI to read them every time, before generating
- Run the rules as automated checks in CI
- Reject any output that violates them — no exceptions

### Phase 3: Documentation

Keep the project organized. Specs, decisions, change logs. Without docs, AI re-invents.

**Failure class:** Knowledge that lives in someone's head doesn't survive the project.

**Problem statement:** You came back to a project three weeks later and couldn't remember why anything was structured the way it was.

**How it works:**

- Document specs before you build — not after
- Capture every architectural decision as it's made
- Keep change logs at the module level
- Treat documentation as code — versioned, reviewed, tested

### Phase 4: Verification

Test, review, improve. Don't trust the first answer. Without verification, demos masquerade as products.

**Failure class:** "It works on my prompt" is the new "it works on my machine."

**Problem statement:** You demoed it to a friend, it broke, you couldn't reproduce the bug to fix it.

**How it works:**

- Tests before merge — written by AI, reviewed by you
- Manual verification on every user-facing change
- Real data, real users, real edge cases
- Reject the demo if it doesn't pass the bar

### Phase 5: Feedback Loops

Catch drift early. Every commit teaches you something. Without loops, the same bugs ship twice.

**Failure class:** Drift you don't catch becomes the bug your users find.

**Problem statement:** A customer reported the bug you fixed two months ago — except now it's back.

**How it works:**

- Every commit is a chance to learn
- Observability on production from day one
- Capture every error, every miss, every surprise
- Feed the loop back into Context, Rules, Documentation

## What comes next

Pick the path that fits where you are:

- **The Starter Harness** — download the folder scaffold and start a session: https://aicodethatworks.com/starter-harness
- **Free course on Skool** — take the structured walk-through: https://www.skool.com/aicodethatworks/about
- **Community** — join operators shipping the same week: https://aicodethatworks.com/community

## Next step

Get the Starter Harness: https://aicodethatworks.com/starter-harness

---

Canonical: https://aicodethatworks.com/start-here

This is the markdown view of the page. The full rendered version lives at the Canonical URL above.