Human intent. AI execution.

Ship intent,
not code.

Define Why, What, and Not. Stack, architecture, timeline, implementation: AI can choose the rest.

Quick Start Concept
"Everything other than intent is a choice."
Why, What, and Not are yours. The rest is AI's.

01 — The Problem

AI made generation cheap. Without intent, that speed becomes noise. With intent, it becomes clarity.

Without Intent

  • AI chooses a stack you never asked for
  • AI invents a timeline nobody needs
  • AI bloats specs, stories, and process
  • 8 files, 3,740 lines, 132KB of noise
  • You still don't know what should exist

With Intent

  • Why: why this must exist
  • What: what must be true
  • Not: where AI cannot go
  • 1 file, 47 lines, signal
  • AI executes instead of guessing

02 — The Framework

An Intent Document has four sections. No extras.

Why

Why does this exist?

State the problem, goal, and success bar. If this changes, the intent changed.

What

What are we building?

State features, flows, and edge cases. Stay concrete, but never prescribe stack, architecture, or timeline.

Not

What will we never do?

State the lines AI cannot cross. Scope limits, security rules, quality bars, forbidden moves.

Learnings

What did we discover?

Log what you tried, what you learned, and what changed. This is how intent gets sharper.

03 — The Lifecycle

Intent is not static. It sharpens through learning or dies on evidence.

seed
exploring
clarified
build
killed
← any state can end here. Good.
# INTENT.md # INTENT — Legacy Converter > status: exploring ## Why Problem: Legacy projects can't leverage vibe coding. Hypothesis: An automated converter can bridge the gap. Validation: Convert one small project, measure dev speed. ## What - [ ] Scan legacy codebase structure - [ ] Generate vibe-coding-ready CLAUDE.md - [ ] Suggest refactoring candidates ## Not Forbidden: Never modify source files without explicit confirmation Scope: Node.js/TS only for now ## Learnings [2026-04-01] Prototype v1 — type coverage was the key signal [2026-04-05] User interview — they want CLAUDE.md generation most

04 — The Pipeline

Humans define intent and judge outcomes. AI does the rest.

Write Intent
Write Why / What / Not
Human
Generate Spec
AI turns intent into tasks
AI
💻
Implement
AI agents write the code
AI
🔍
Verify
AI reviews, tests, and lint-checks
AI
🚀
Deploy
CI/CD pushes to production
AI
💡
Learn & Decide
Review results. Update intent or kill it
Human

05 — Principles

Four rules. Break them and AI starts guessing.

Never write How

Intent sets constraints, not implementation. Write "no external cache layer," not "use Redis."

Admit uncertainty

Mark unknowns with (?). Honest uncertainty beats fake precision.

Kill fast

If the idea is dead, say so and record why. A killed intent saves future time.

Intent precision = output quality

"Build a good app" is noise. "New users reach value in 30 seconds" is intent.

Start with intent.

Write Why/What/Not. Let AI choose the rest.

Quick Start GitHub
한국어 中文 日本語