Loops All the Way Down, Part 6: Output, Not Craft
What the data proved, what it didn't, and what humans give up when agents do the building. The last part of a series on the contract between humans and agents.
series / newest first
A six-part series on designing the contract between humans and coding agents, backed by a month of production data from my software factory.
6 entries (newest to oldest)
What the data proved, what it didn't, and what humans give up when agents do the building. The last part of a series on the contract between humans and agents.
Quality gates don't go away when agents write the code. Humans just stop staring at them. A month of factory data on where quality actually comes from, and why the merge button doesn't matter.
My software factory spent 7.5 billion tokens in a month. Here's what that number hides, where the tokens really go, and why the human side costs more than you'd think.
My software factory isn't a pipeline. It's loops inside loops, and only one of them needs a person. A month of data on the loops that build, fix, simplify and watch themselves.
If humans and agents do different work, something has to sit between them. In my factory, that's a GitHub issue written as a contract: humans define done, machines check it.
Agentic development is two different jobs, judgement and mechanics, and we keep running them through one chat window. A series on designing the contract between humans and agents, with a month of data from my own software factory.