Long-form pieces written while building, not after the fact. New essay every two or three weeks.
built a multi-agent operating system from scratch. Six specialized agents. Cron jobs. A Discord bot named after Opus. Memory layers. Routing logic. The whole stack. I called it Nexus. And I shut it down. Not because it was broken. Because
Read →Everyone's obsessed with picking the "best" AI model. The one model to rule them all. Spoiler: it doesn't exist. And the more you try to find it, the more you handicap yourself. The winning
Read →You build with something long enough, you stop seeing it as a product and start seeing it as a collaborator. OpenClaw did that for me. Two months in, it surprised me. Frustrated me. Changed how I think about AI orchestration.
Read →I get asked all the time: "How do I learn AI?" The answer everybody gives is wrong. "Use ChatGPT. Prompt it. Get outputs. Repeat." That's not learning AI. That's using AI. They&
Read →Twenty years ago, every device had proprietary connectors. Your camera had one. Your phone had another. Your printer had yet another. Then USB came along and said: we're done with this. The Model Context Protocol is doing the
Read →I've spent the last two months running OpenClaw against real enterprise problems. Not proof-of-concept stuff. Actual workflows where people depend on the output. So here's the unfiltered truth: it's close, but not quite there
Read →Notes from building agentic systems. One essay every two or three weeks. No filler.