Posts tagged #ai
Inside the Harness: Four Months of Being Wrong About pi
The thing I'd missed was that everything I'd been building around my harness could live inside it.
Read → claude-codeFleet: A Control Tower for Claude Code
A tmux dashboard for running many Claude Code agents at once — it shows which one needs you, sorted by urgency, so you stop polling and start responding.
Read → aiAIE Europe
A talk, a workshop, and a podcast at AIE Europe. Here's what I did.
Read → aiCase Statement: Building a Harness
I codified my job as a DX engineer into a system that dispatches agents, enforces conventions mechanically, and learns from its own failures. Here's how case works and why I think every developer should build something like it.
Read → aiWriting My First Evals
I had no background in evals. I built two very different evaluation systems for two AI-powered developer tools, and they taught me the same lesson: trust isn't a feeling, it's a measurement.
Read → aiIdeation: Because Planning Needs More Than a Mode
Claude Code's plan mode is a great starting point for thinking before coding. But for complex work, I needed more than a mode. I needed a system. Here's what I built.
Read → aiVery Important Agents
My recent Changelog and Friends podcast appearance and the Claude Code plugins that help me get real work done with AI.
Read → aiWhy Everyone Should Try Claude Skills
Claude Skills are the approachable AI tool I didn't know I needed.
Read → aiEvolving with the Tools
After 16 years of writing code, I fought the idea of AI agents replacing developers until I discovered they could amplify rather than replace me. This is my journey from skepticism to embracing Claude Code as a pair programmer who speaks fluent bash and transforms how I ship software.
Read → mcpCoding With My Eyes Wide Shut
At WorkOS's AI onsite and MCP Night, I experimented with vibe coding. What started as a two-hour experiment with 5,000 lines of unseen TypeScript became a glimpse into programming's future.
Read →