Vibe Coding: Building Software with AI
What I have learned shipping real apps with tools like Claude, ChatGPT, Cursor and Codex: choosing tools, a working method, design consistency and the road to the store.
13 posts
Recapday Couple Mode: Why a Two-Person Group Needed Its Own Mode
How Couple Mode found its way into Recapday: what changes at two people, why a mode beat a separate app, and what I deliberately left out.
How I Built Recapday: A Decision Log From Idea to Store
The architectural decisions behind Recapday, a daily clip app for groups of friends: why identity lives in Firebase but data lives on my own server, why I deleted the social features, and which choices turned out to be irreversible.
What Is Claude Design? Seven Levels of AI Design
Most people stop at the first level of Claude Design and get generic results. Here are seven levels, the costly mistake at each one, and how to move up.
What Is a Harness? The Difference Between the Model and the Coding Tool (with DeepSeek)
Why does the same model behave completely differently in two tools? The answer is the harness. Using DeepSeek as the example, here is what a harness actually does — the agent loop, tool calling, and context management.
What Is an Agent Skill? How to Write Skills That Work
Most agent skills add little value. Learn the patterns that work, the rules for writing reliable skills, and the security checks to run before installation.
What Is AI Slop? Building a Website That Doesn’t Look AI-Generated
Why do AI-generated websites all look alike? Learn the signs of AI slop and practical ways to escape it through typography, imagery and copy.
Website Design Audit: Comparing Against a Reference
Can’t explain why your website falls short? Compare it with a strong reference and turn vague impressions into a concrete design audit.
AI Motion Graphics: Data, Icons and Automation
Why do AI-generated animations all look the same? Turn real data into motion, use quality assets, and generate graphics automatically from video.
Consistency in AI Design: The Critic Loop
AI-generated designs become inconsistent when the model grades its own work. Learn how an independent critic loop fixes this and what it costs.
What Is Vibe Coding? A Realistic Beginner's Guide
What is vibe coding, how does it work, which tools should you use? A practical starting point for anyone who wants to build apps with Claude, ChatGPT, Cursor, or Codex — written for real developers, not for hype.
Vibe Coding Tools Compared: When to Use Claude, ChatGPT, Cursor, and Codex
Which vibe coding tool should you pick? A hands-on comparison of Claude, ChatGPT, Cursor, Codex, and GitHub Copilot from real projects: strengths, weaknesses, and when to use each one.
The Vibe Coding Method: 7 Practical Tips and the Art of Writing Prompts
Seven tips that actually work in vibe coding: writing prompts, building a decision document, giving small tasks, protecting with tests, auditing, and refactoring. The formula to go from 'it works' to 'it keeps working'.
Shipping an App Store App with Full Vibe Coding: The LevelUpStudy Story
Can you actually ship an App Store app by coding with AI? Here is the method that worked while building LevelUpStudy, the three real walls I hit, and the lessons I took away.