Featured
Building an AI Research Lab
A system that runs autonomous experiments, scores results, and surfaces insights. Nine workstreams running overnight, 154 tests.
Research labs, monitoring systems, automated pipelines. Here's what I'm working on and what I'm learning along the way.
A system that runs autonomous experiments, scores results, and surfaces insights. Nine workstreams running overnight, 154 tests.
The gap between buying AI tools and getting value from them. What I've seen work and what keeps stalling.
The architecture behind my agent fleet — how they communicate, recover from failures, and handle work autonomously.
What actually happens when autonomous systems work through the night. The failures are more interesting than the successes.
The difference between an AI prototype and something that runs reliably every day. Most of the work is in the second part.
I build AI agent systems — fleets of autonomous programs that research, monitor, write, and operate around the clock. I design the architecture, define what each agent does, and let them handle the execution.
Right now I'm running 9 workstreams across an AI research lab, an agent monitoring platform, a content pipeline, and an automated job search system. Most of it runs while I sleep.
This site is where I share what I'm building and what I'm learning. The wins, the failures, and everything in between.
Questions, ideas, or just want to compare notes on what you're building.