I’ve pushed a full-stack educational platform for parents, My DigitAlly, to production using what we call "Systematic AI Collaboration" (a matured version of vibe-coding).
It isn't a static site; it’s a production app with:
Full Auth: Google OAuth and email/password.
Engagement Engine: A node-cron system that automatically sends weekly tips to 200+ subscribers every Saturday.
Dynamic Curriculum: A 5-block lesson flow driven by a JSON-based instructional design framework.
Automated Resources: Auth-aware server-side PDF generation for parent checklists.
The "Methodology" that made it work:
We moved from initial idea to production in four weekends while I maintained a full-time role. The key was moving past "chaotic vibes" and treating different LLMs like specialized team members:
A) Strategic Layer (Gemini Pro): Used for architectural decisions (React/Vite, Node/Express, PostgreSQL/Prisma) and product prioritization.
B) Execution Layer (Claude Code): Used for heavy lifting—implementing the cron jobs, refactoring API patterns, and writing the test suite.
C) TDD as the Guardrail: We never "just coded." Every AI-generated feature followed a strict Test-Driven Development cycle using Vitest. If the tests didn't pass, the code didn't go to production.
The result is a stable system serving 200+ active users with a codebase that doesn't feel "schizophrenic" because we maintained strict cognitive boundaries and context documents for the AI to follow.
This is written like some over-professional marketing ad or something. Like trying to defend its qualify even though it was vibe-coded. Not against vibe coded apps, this reads weird.
Touché. The corporate voice is a hazard of my day-job of 15 yrs.
It is 100% vibe-coded/AI-assisted. I'm just trying to layer actual engineering discipline (TDD, proper DB migrations) on top of that workflow so it doesn't break when actual parents use it. Thanks for the feedback.
The "Methodology" that made it work: We moved from initial idea to production in four weekends while I maintained a full-time role. The key was moving past "chaotic vibes" and treating different LLMs like specialized team members: A) Strategic Layer (Gemini Pro): Used for architectural decisions (React/Vite, Node/Express, PostgreSQL/Prisma) and product prioritization.
B) Execution Layer (Claude Code): Used for heavy lifting—implementing the cron jobs, refactoring API patterns, and writing the test suite.
C) TDD as the Guardrail: We never "just coded." Every AI-generated feature followed a strict Test-Driven Development cycle using Vitest. If the tests didn't pass, the code didn't go to production.
The result is a stable system serving 200+ active users with a codebase that doesn't feel "schizophrenic" because we maintained strict cognitive boundaries and context documents for the AI to follow.
reply