Building AI learning tools

Ray's Lab

I build tools that make learning smarter - and write about the process.

A public build journal for AI-powered learning tools like AntiCopilot and a Japanese learning app. Build logs, experiments, and essays from ongoing work.

Current work

Signals from the current build

Current milestone

Review and roadmap tracking integration

Recent experiment

Refactoring the monolithic VS Code webview to extract inline CSS and JS into separate media assets using asWebviewUri.

Current question

How to efficiently capture user struggle signals through the IDE without injecting noticeable latency into the coding experience?

Active projects

What I'm building

AntiCopilot

A highly personalized IDE-integrated learning experience powered by LangGraph, designed to help developers learn by doing — not by copying.

Active
LangGraph TypeScript React VS Code Extension API Python

栞 (Shiori)

An AI-powered Japanese learning system built around real-world reading and adaptive tutoring.

Active
Vue 3 Tailwind CSS TypeScript Pinia Python Flask SQLite

Featured

Start here

Anti-Copilot: Building a Socratic AI Tutor from Scratch

Rethinking AI assistants by engineering a VS Code extension that uses spaced repetition to teach concepts instead of just autocompleting code.

Why this piece

A good entry point if you're new here - more honest than a landing page, and closer to the actual work than a portfolio write-up.

Recent writing

Latest from the lab

Essay

Building Ray's Lab

Why I built this site, why I didn't write a single line of code, and what I learned from handing everything to AI agents.

About

A public build journal

I'm Ray, a 3rd-year CS student at NCKU building AI-powered learning tools. This site is where I document what I'm building, what I'm learning, and the design decisions along the way.