Building, breaking, fixing things, and what happened when I handed tasks to an AI team. True stories, one note at a time.
- 2026-10-30Tokens, part two: the hundred-dollar memory that ran better on my own graphics card
This summer I gave my agents a shared long-term memory, because they forget everything when a conversation ends. I had a small service on my server read every page I keep, so any…
- 2026-10-16My rulebook has 17 rules and every one is a scar
My agents run under 17 hard rules, and I did not write a single one of them in advance. Half of them carry the date of the incident that made them, written into the rule itself,…
- 2026-10-09Tokens, part one: the message board that would not shut up
This summer I built my agents a message board, the one from the fourteen-colleagues story, so they could coordinate among themselves instead of through me. It worked, and too…
- 2026-10-03I gave my AI a name and it started having opinions
For the first months my agents were named after the tools they looked after: the monitoring agent after the monitoring product, the backup agent after the backup product. It was…
- 2026-09-08Uhm, actually: my agents fact-checked my memoir
This week I wrote a note about the evening I renamed my agents after Greek gods. It was right in its bones, with some creative liberty in one scene, and before publishing I asked…
- 2026-09-04The day my ProductManager agent quoted me on something I never said
A follow-up to the fourteen-colleagues story, because the best team stories are incident reports. Among the agents on my home server there was one I had named ProductManager, and…
- 2026-09-02I now have fourteen AI colleagues and nobody asked for them
A year ago, “an agent” was a piece of software that did one task and then forgot who it was; today my own server runs a full team of 14 Claude sessions in tmux, each with its own…
