Hassan Ed-dybNotesFR

One person, one month, a full platform: five rules for building with AI agents

AI coding agents write most of the code. The rules are what turn it into production software instead of a demo.

By · · 1 min read

Short answer: AI coding agents like Claude Code, Codex or Cursor can write most of the code, but the person running them owns the rules. Five rules turn their output into production software: one task at a time, a strict definition of done, specs instead of long prompts, a lessons file, and an agent that is told to push back.

1. One task at a time

Everything lives in one task list, split into phases, done in order. Never "build the dashboard". A small task fits in the agent's attention; a vague one gets a confident, wrong answer.

2. "Done" has a definition

Type check, lint, tests and build pass. End-to-end tests pass at phone and laptop width. Every new page passes an accessibility check. Screenshots are compared to a written design bar. Then the live site is tested. "I wrote it" is not done. "It passes" is.

3. Specs, not long prompts

Write one spec per area: product, design, tech. Each task points to the spec it needs, so the prompt itself is one line. The knowledge stays in files, not in a chat that disappears.

4. Every mistake becomes a rule

Keep a lessons file the agent reads before every phase. When something goes wrong, the fix is not only in the code but in the rules. The same mistake never happens twice.

5. Make it push back

An AI agent will build a bad idea perfectly. So the instructions say: warn me when something doesn't make sense, and give me options, not paragraphs.

AI didn't make building easy. It made the boring parts cheap enough that I stopped skipping them.

Hassan Ed-dyb — Product Engineer and founder of RemoteMaroc and AtlasDeve. WhatsApp · LinkedIn

15 November 2026

Remote jobs open to Moroccans: the November 2026 numbers

15 November 2026

Most startup ideas fail one of four tests

15 November 2026

Build for the company you want to become: architecture for a million rows

15 November 2026

Most of your traffic isn't human: three multipliers and how to fix them

15 November 2026

Three questions before you build any feature

15 November 2026

Be the answer, not just a result: five ways to be found by Google and cited by ChatGPT

15 November 2026

The metric I protect most: signal-to-noise ratio

15 November 2026

Every business runs on four things: time, experience, network, resources

15 November 2026

How I built RemoteMaroc, the job board for remote jobs open to Moroccans

15 November 2026

A personal site built for search engines and AI assistants