Writing
Notes from building and operating agent systems — business-facing agents, workflow automation, memory, approvals, and practical AI. Less theory, more what survives real use.
I built pinball to relax, never had time to play it, so I trained an AI to play it for me
Agent Pinball began as Space Cadet nostalgia and a way to unwind. Then I got busy building it, so I taught an AI to play it instead, which was harder than it sounds.
Archive
A prompt is not a permission system
OpenAI's investigation into an agent-driven intrusion at Hugging Face shows why capable agents need hard boundaries, not better-behaved prompts.
The skill isn't prompting. It's management.
A working note on what building with AI agents has reinforced: the scarce skill is not magic prompts, it is managing work.
One folder to autonomy
The companion to my Claude Community lightning talk in Perth. The terminal is not as scary as it looks, and a single folder can climb a surprisingly long way.
What does computer mean in the modern age?
From a job title held by women doing calculations, to room-sized machines, to the personal computer, and now to always-on agents. A reflection on where computing is heading and what to build for it.
The agent stack I keep coming back to
The parts of an agent system that actually matter once the novelty wears off: memory, tools, workflow, approvals, audit, and escalation. Now with the real examples behind each layer.
A warning shot for AI sovereignty
Fable 5 arrived, unblocked weeks of hard engineering, and was pulled almost immediately. For builders outside the US, that is the shape of the next problem: 'just use the best model' is not a strategy.