Agent factories
Running many agents and services without care and feeding.The basement server, ClickHouse, the fleet controller.
Building an agent factory in my basement.
277 agent sessions last week, one boxMany agents, self-healing infra, metrics over code.
Claude Code sessions on one box (life), 5 Nov to 12 Nov, from its own telemetry. The fleet has more boxes than this one.
Kiter when the wind is right.The factory runs itself in the meantime, with a little oversight.
The last 24 hours on that box, 11 to 12 Nov, 08:00 to 08:00 Oslo time. 10 of its 53 scheduled jobs, one tick per hour of runs.
Grey ran fine. Red failed. Yellow failed and came back (4 in this window, 2 still red at the hour). 14,411 job runs in all. Source: the box's job telemetry, read 12 Nov.
What I write about
The posts live on LinkedIn, not here. Read them there. I post about once a week.
Engineering taste
What good engineering means when change is cheap.Best practice, tech debt, over-engineering, when not to optimise.
Building in the open
Concrete things I built, what broke, and what the data said.
Product over tech
The consultant habit of chasing tech instead of shipping product.I had it for years.
Nothing posted here yet.
Who
I used to be scared of building. Not the building itself, the being wrong afterwards. Change was expensive, so I spent more time controlling chaos around my code than shipping the product.
That block is gone. I run an agent factory from a server in my basement: a fleet of AI agents and services with their own metrics, monitoring and self-healing, so I spend my time on what gets built rather than on keeping it alive. The most useful tool I own is a fleet controller that is one HTML file past 10,000 lines. It is not best practice. It works.
Now
- CAIO, Pengefix
- AI Champion & Senior Product Engineer, Mobai AS
- GP, investor and network board member, CTO Roundtable
Before this: CTO at Diwala, consultant at Bekk, CS at NTNU.