Records of thinking.

I’m Aaron Taylor, an engineer based in Norfolk, UK. I work across front-end systems, product engineering, AI workflows, internal tools, and the systems around them.

This site is where I keep public working notes on the things I’m researching, building, and trying to understand. The notes are intentionally unfinished in places. They are records of thinking, not final answers.

What belongs here

Notes about AI and agents, software systems, automation, product thinking, spec-first development, developer workflows, and the personal systems that hold all of it together. If I tried something and learned something, it can be a note.

What does not

Predictions, hot takes, and anything written to perform expertise I don’t have. This is not a portfolio or a personal-brand exercise. If a note can’t say what was actually tried and what actually happened, it isn’t ready.

How these notes are written

I write these with AI assistance, and on a site about working with AI it would be strange not to say so.

The division is roughly this. I choose what to look at, and which question is actually worth asking. I run the experiments and use the tools myself. The conclusions are mine, including the ones that record being wrong. AI helps me draft, surfaces things I would have missed, and argues with me when a claim is thinner than it sounds.

What I don’t hand over is deciding what I think. A note reporting a finding I hadn’t actually reached would make the whole site pointless.

How to read a note

Every note opens with its finding — the short version of what I currently think. Everything after it is the working: the question, what I expected, what I tried, what happened, and where it broke. Read the finding, and go deeper only if the question is yours too.