I Stopped Chatting and Started Filing Issues
Chat is a good scratchpad and a terrible filing cabinet. I moved the actual conversation into Gitea issues, and my projects stopped stalling.
The LLM Tax, Revisited: Cost, Latency, and Where to Run the Model
Quality, cost, and latency. You can usually have two. Here is the framework I use to pick which two on purpose, with a voice assistant, an RSS scorer, and a Frigate box as the worked examples.
My AI-Native PM Operating System: Idea to Shipped, Solo
The gap between an idea and a working product used to be an engineering team. Here's the whole loop I run now: spec first, backlog in Gitea, Claude Code doing the building, and me making the calls that actually matter. Including the two features I shipped and then threw out.
What I Learned Shipping a Multi-Agent System
I planned Ceres with seven specialist agents and cut half of them in the first week. The surviving ones still broke, just not the way I expected. They gave me good answers and then quietly assumed somebody acted on them. What that taught me about restraint, state, and where the real work in a multi-agent system actually lives.
Meet Alfred, the Server That Runs the House
For a while my setup was split across two machines. Home Assistant lived on my Synology NAS, alongside the Mosquitto MQTT broker and ring-mqtt, while Frigate ran on a separate custom rackmount PC. It worked, but two things kept nagging…
What Building a Pile of Small AI Projects Taught Me About the PM Job
The tools let me build things I never could have built alone. What surprised me is which parts of the product job got more important, not less.