I built BuildIt because I noticed a pattern in my own workflow — what people now call "vibe coding": AI agents (Claude Code, Codex, etc.) write code fast, I run it, it works, I merge — and a week later I can't explain why it works, or where the next bug is hiding.
BuildIt is a set of hands-on courses (Arduino, STM32 HAL/LL, ESP32, Next.js, Python, React, React Native, Flutter — 9 courses, 45 real shipped projects) where an AI agent proposes code changes like a normal diff, but you can't move to the next step until you explain — in an actual conversation with an AI tutor — why the change was made and what could go wrong. You also have to write the prompt yourself before the AI generates anything.
A few technical notes:
The tutor AI runs locally in your browser — your code never leaves your machine.
No pseudocode/toy examples — every project is real, compilable code from lesson one.
Credits-based pricing; unlocked courses stay yours even after cancelling.
Would love feedback, especially from anyone who's felt the same "I merged this AI diff and don't actually understand it" feeling.

3 hours ago
2





![[테크 차이나] DeepSeek V4 Flash 1위… 중국 모델 강세 지속(OpenRouter 주간 AI 모델 사용량 순위)](https://img.etnews.com/news/article/2026/08/06/news-p.v1.20260806.379c2eee15bb4be5b29d934a203a6106_Z1.jpg)


English (US) ·