I'm komo, a technologist working in automation - currently doing PhD research in the field at the Hong Kong Polytechnic University. Here I write up what I actually learn building tools, engineering AI agents, and keeping systems running, along with the workflows and habits that stick. The best is yet to come. We've only scratched the surface.
Most of what I do lives at the unglamorous layer: parsing messy inputs, wiring retries, and trusting an agent's output enough to stop babysitting it. The loop was never the hard part. I write here about the things that actually shipped, the ones that quietly died, and the habits that survived contact with production.
What you'll find here
- Build logs - small command-line tools and the decisions behind them.
- Agents, honestly - what works and what is only a for-loop with polish.
- Plumbing - parsing, retries, queues, cron, and the boring 80% nobody demos.