How to Make an AI Coding Agent Actually Yours
I built Monet to fix the agent that forgets yesterday's conventions. How an agent that writes its own memory, reads what mattered, and grows with use actually works.
Read articleIDEAs · PRODUCTS · OPPORTUNITIES
I share how I build better with AI, ship for real, and grow products for the long run.
Insights
I built Monet to fix the agent that forgets yesterday's conventions. How an agent that writes its own memory, reads what mattered, and grows with use actually works.
Read articleTwo developers, same tool, wildly different setups. How deep coding agent customization goes — from bare defaults to full pipelines — and what actually pays off.
Read articleWhat today's LLM benchmarks actually measure, what they miss, and why we need behavioral benchmarks instead of more knowledge tests.
Read articleTwo requests with near-identical input tokens, a 46x cost gap. How prompt caching really works, and why agents should be designed around structured state.
Read articleAI Radar
From the daily flood of AI news — only what matters to builders.
View all AI RadarEU AI Act rules become enforceable today: The EU's rules on general-purpose AI models took effect on August 2, cementing the European Commission as the world's most prominent AI r…
Read latest radarGuides & Tools
Written the way I actually work — read it, then put it to use.
View all Guides & ToolsA CLAUDE.md does not get better as it grows. Why piling up rules degrades your agent, what belongs in the file, and where the rest should live: …
Read the guideHow to customize the PaperMod Hugo theme without forking it: homepage override, CSS-variable palette, the dark-mode trap, and CJK typography, with …
Read the guide