learning in public

Notes from building with agents.

Public notes on business-facing agents, workflow automation, memory, approvals, and practical AI systems. Less theory, more what survives real use.

current notes

Start here

7 July 2026 The skill isn't prompting. It's management.

A working note on what six months of building with AI agents has taught me: the scarce skill is not magic prompts, it is managing work.

29 June 2026 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.

28 June 2026 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.

20 June 2026 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.

14 June 2026 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.

5 June 2026 Why I am rebuilding the site around agentic systems

The short version of the current direction: ship the useful pieces, learn enterprise agent platforms, and apply the lessons to real workflows.

Business-facing agents

What agent platforms are actually useful for once you leave demos and hit business workflows.

Human approval

Where autonomy helps, where it creates risk, and where people need clear handoff points.

Agent memory and tools

How agents keep context, use systems, and become useful without becoming a mystery box.