I have written a lot of posts about individual pieces of how I work, like the terminal, the multi-repo workspaces, the coordination bus, and the harness that drives the model. What I never had was one place that put them together, so when someone asked how I actually work, from start to finish, all I could point at was a scattered pile of links.
So I built one page that walks the whole thing in order, from a laptop with nothing on it to a binary shipped to production. It is called The subaud setup, and it covers the machine setup, the terminal, the folder and repo layout, the harness that drives the model, the models behind it, the tools that let separate agent sessions coordinate, the review workflow, and the continuous integration that ships it all.
The page is deliberately an overview. Each section is a short summary of one layer, enough to see how the pieces fit rather than a full manual for any one of them. Most of the tools it mentions are ones I built and run in the open, so the page doubles as an index of them.
What I want it to become is a living map. Each section is going to grow into its own dedicated post that goes deep on that one piece, and the page will link out to each as I write it. Some of those posts already exist and some do not yet, so the overview stays the same shape while the depth accumulates underneath it over time.
The page is at subaud.io/the-subaud-setup, and it will keep filling in.