On my mind. On the bench.

A dated snapshot of what I’m building, thinking about, writing and still trying to understand.

Last updated 24 Aug 2026 from Sydney, Australia.

01THINKING

Keeping the agent in proportion

I’m pressure-testing a simple idea: a clear outcome, a small harness and good evidence can be more useful than an elaborate agent team. Complexity still earns its place when responsibilities, context or controls genuinely demand it.

Essay / active questionSignal only / workbench question still forming

02BUILDING

Testing the edges of agent-to-agent trust

I’m exploring what one agent should require before it accepts another agent’s identity, delegated authority or result. The current work is research, trust-boundary models and prototypes—not a claim that the problem is solved.

Research / models + prototypesOpen the workbench

03WRITING

Putting the work where people can find it

I’m turning a growing pile of experiments, notes and working positions into a clearer public record. The latest pieces are about starting with the work before building an AI workforce, and what an AI colleague needs to deliver reliably.

Writing / two new piecesSignal only / workbench question still forming

04LEARNING

The next questions are moving closer to the edge

Spatial computing, local AI and the enterprise network are becoming one system problem. I’m mapping where that changes data, privacy, performance and the experience people actually have.

Question forming / researchSignal only / workbench question still forming

The work behind the questions.

Projects, experiments and the evidence that changes my mind.

Visit the workbench

There is life around the work.

Family, retro consoles, gaming and the occasional track out of town.

A bit more about me