I build things and then write about what I learned.

Most of my work lives in two places: AI automation and the infrastructure that keeps real operations running. I have spent over a decade in technical operations, IT, and manufacturing systems. One of the monitoring systems I built cut incident response from hours or days down to minutes. I run a homelab with a 40GbE backbone, VMware ESXi, and a full monitoring stack, and I have logged more than 500,000 AI interactions across every major platform over the last few years.

I publish the useful parts: open source monitoring tools on GitHub, practical breakdowns of AI workflows, and honest notes from running systems where downtime has real consequences. No hype, no theory I have not tested myself.

If something I built saved you time, or a post helped you solve a problem, you can buy me a coffee. It goes straight into the time it takes to keep the tools open source and the writing free. Thank You

Everything I make is here: github.com/StefanYasin