惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

人人都是产品经理
人人都是产品经理
Apple Machine Learning Research
Apple Machine Learning Research
云风的 BLOG
云风的 BLOG
罗磊的独立博客
博客园 - 三生石上(FineUI控件)
量子位
GbyAI
GbyAI
腾讯CDC
T
Tailwind CSS Blog
博客园 - Franky
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
D
Docker
G
Google Developers Blog
aimingoo的专栏
aimingoo的专栏
The GitHub Blog
The GitHub Blog
Microsoft Security Blog
Microsoft Security Blog
Stack Overflow Blog
Stack Overflow Blog
Hugging Face - Blog
Hugging Face - Blog
小众软件
小众软件
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
N
Netflix TechBlog - Medium
Jina AI
Jina AI
IT之家
IT之家
Y
Y Combinator Blog

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
How I Revamped a Local Cram School Website Using AI (Clau...
Nonoka Tanak · 2026-04-29 · via DEV Community
Cover image for How I Revamped a Local Cram School Website Using AI (Claude, Gemini, and Codex)

Nonoka Tanaka

Introduction

I recently took on the challenge of modernizing the website for my parents' cram school in rural Japan.

As an IT professional specializing in cloud infrastructure, I wanted to see how far I could go by leveraging AI as my primary development partner.

Here is the story of how Claude, Gemini, and Codex helped me transform an outdated site into a modern web presence.

The AI Dream Team

I used three different AI models, each for a specific role:

  • Gemini: My "Strategy Consultant." I used it to brainstorm the revamp plan and organize ideas for site structure.

  • Claude: My "Lead Developer." It was incredibly fast and accurate with code generation.

  • Codex: My "UI/UX Designer." While Claude was fast, Codex generated a design that perfectly appealed to our target audience—young mothers.

The Development Process

Phase 1: The One-Pager
Claude initially built a high-quality single-page site in seconds. It was impressive, but I needed more.

Phase 2: Designing for the Audience
Codex stepped in to refine the aesthetics. It created a design that felt much more approachable and modern for young parents.

Phase 3: The Biggest Challenge (The "Multi-Page" Wall)
The hardest part was splitting the site into seven distinct HTML pages. I spent 7 hours trying to get Codex to handle the linking and structure—I even took a nap while it processed—but it just couldn't cross the finish line.

The Breakthrough
I switched back to a combination of Claude and Gemini. Claude’s coding efficiency is unmatched; it handled the multi-page logic without breaking a sweat.

Key Takeaway: For pure coding speed and logic, Claude is currently king. It saves developers an incredible amount of time.

Feedback from my Parents (and Next Steps)

After showing the result to my parents, I received some "tough but fair" feedback, which I’m now addressing:

  • "Changing the old site is scary."

    • Solution: They were worried about the transition. I'm considering a blue-green deployment or hosting both versions. Since they are worried about server costs, I’m looking into AWS (EC2/S3) or Google Cloud to optimize hosting for a lightweight static site.
  • "It looks a bit too much like AI-generated art."

    • Solution: I am manually refining the fonts and CSS in VS Code to give it a more "human" and professional touch.
  • "We won't be able to edit it ourselves!"

    • Solution: I'm setting up a simplified workflow (perhaps a headless CMS or a specific Git-based setup) so they can update information without needing to touch the raw code.

Conclusion

Building this was a reminder that AI is a powerful tool, but the "human in the loop" is essential for final adjustments and navigating complex site architectures.

Have you used AI to build projects for your family? I’d love to hear your experiences in the comments!