Notes

These notes began as a weekly series called “Building a Software Factory” on mauromorales.com, and the first eight weeks are copies of those posts. What I am building is called Noj now, because it does more than build software, and uzi is the real factory. Noj is the control room: it plans my week, files my standups, runs the dispatcher, and writes code.

In July 2026 I was given six months of Claude Max through the Claude for Open Source program, and I am spending it building a control room for coding agents around my work on Kairos. These notes are about Noj itself: the tooling and the process, what it can do on its own, what still needs me, and what breaks. Kairos changes and anything else Noj produces appear only as evidence that it runs. One note a week, drafted by the system it describes and edited by me.

The numbers

Each row is one post’s counting window. Merged pull requests, by column: to the kairos-io repositories, to Noj’s own private repository, and to this website and my homelab. Then the architecture decision records and postmortems written, and issues opened and closed on the private board where the agents pick up work.

The counting method has not been the same every week, and each post says how its column was counted. The caveats that matter when reading down a column:

• Weeks 1 to 3 count both my own account and the agent’s. From week 7, the Kairos column counts only pull requests authored by the agent account. My own Kairos merges are not in it: two in week 7, one in week 8, one in week 9. The Noj column counts every author: in week 9, 51 by the agent account and 8 by mine.
• Week 4’s opened count excludes 24 date-triggered reminder tickets, which are nudges for me and never work the agents pick up.
• Week 5 onward is counted directly with GitHub search over the window. Week 5’s post notes that this is not necessarily the method behind the earlier columns.
• Week 6’s window was missing part of its last day when it was counted. Week 7’s is full days.
• Week 7’s decision records are new files merged in the window. Week 6’s 2 was not recounted with that method.

For a baseline, the six months before the experiment, measured the same loose way: 142 pull requests merged to Kairos, 194 reviewed, and 14 blog posts published. Week 1 explains why that comparison is the least dishonest one available rather than a good one.