AI Planning Without the Slop: How I Used Agents to Build a Roadmap
FeaturedHow I used AI agents strategically—including pitting them against each other—to build a bulletproof feature roadmap without falling into the 'AI slop' trap.
Read Entry →
From 56 to 100: How I Fixed My Own Slow Website
FeaturedHow I took my personal site from a sluggish 56 to a perfect 100 Lighthouse score by rethinking my architecture and image strategy.
Read Entry →
Say Play: Building an AI Director for Video
FeaturedHow I built an agentic video editor that writes React code instead of just generating pixels.
Read Entry →
Design First, Optimize Second: Reaching 60fps with Canvas
How we took a heavy, animation-rich UI and engineered it to run smoothly at 60fps without losing the soul of the design.
Read Entry →
The Physics of Glass: Why Your Dark Mode Blur is Broken
Why 'backdrop-blur' destroys thin lines in dark mode, and how to fix it by faking the physics of light.
Read Entry →
Keystatic: The CMS That Finally Clicked
How I wired up a headless CMS to my Astro site after debugging path mismatches and render functions.
Read Entry →
Workflow: Generating Nested Markdown Specs with LLMs
A simple prompt injection to prevent LLMs from breaking markdown rendering when generating documentation.
Read Entry →
Fixing LLM Hallucinations with MCP Servers
How I used the Model Context Protocol to inject fresh documentation into my Agentic IDE.
Read Entry →
GhostWriter: Engineering the Turing Test for Party Games
How I built a multiplayer social deduction game where AI agents try to blend in with humans.
Read Entry →