Essays and notes
Writing
Essays from putting AI agents to work, written up when they hold, and shorter notes on what is being read and tested now. Each one says where its numbers come from and what it doesn't know yet.
All essays
Essay · 2 October 2026
Agents are learning. Organisations aren't.
In 2026 an AI agent can build up skills from its own experience and keep them. What it learns still doesn't reach the colleague at the next desk — and, as far as I can find, nobody has built the thing that would carry it there.
Read the essay →Essay · 2 October 2026
Your agents can talk. They can't tell whose opinion counts.
The protocols that connect AI agents can say what an agent can do and which agent handles a task. None of them can say who owns a decision — or get the right person's judgement in before the work is built, rather than after.
Read the essay →Notes
A few hundred words each, dated, with where the thinking stands: reading, an idea, an experiment planned, or a result.