The Operations Platform
A full-stack operations system I design, build, and run inside a small custom manufacturer: a product-and-cost engine, quoting, factory costing, and a customer portal.
I work in the open here: the methodology I'm building, the projects I'm in the middle of, and what I'm learning as I go, including how I work with the agent itself, not just the systems. It all points at one aim:making enterprise-grade operations reachable for small manufacturers.
A full-stack operations system I design, build, and run inside a small custom manufacturer: a product-and-cost engine, quoting, factory costing, and a customer portal.
Service businesses and platforms sit on a decomposable product too. The atoms change: scope units, hours by skill, cost-to-serve. The discipline, and the payoff, do not.
The eight phases were born in a factory, but their principles say nothing about manufacturing. Separating what is domain-specific from what is not, phase by phase.
For a long time the busiest I felt was the least I finished. On why one thing done all the way beats five at forty percent, and why a product nobody has tried to buy is not yet a product.
A skill written for your own agent teaches one assistant. Committed into a public repo, it teaches every agent that opens the folder. Two skills from the sandbox run just made that jump.
An agent gets better not from cleverer prompts but from corrections that stick: turn every fix into configuration (memories, rules, small skills) so the same mistake never comes back.
I build most of this alone, but not really alone. What working with an AI coding agent actually changes, where it carries real weight, and where you still have to be the one who understands.