The writing.
Every Build Notes article: what I've built for real businesses, including what didn't work.
You don't need a strong model to build
The businesses getting real value from AI are not using better models. They are using the same models, wired differently. What "agentic" means in plain English, three real examples, and a ninety-minute exercise.
25 Sept 2026 · 5 min
AI helped me message 239 people. One in seven said yes.
I tested Jev, a small AI model, on my own LinkedIn outreach: 239 personal messages over two days, and one in seven said yes. Plus GPT-6 Astra vs Opus 5.5.
24 Sept 2026 · 7 min
Voice in the car, actions in the calendar
Four steps and no software: a phrase I say every time, one folder, a file handed from one model to another, and me deciding what reaches the calendar.
16 Sept 2026 · 4 min
What kind of model is GPT-6 Astra?
Frontier models launch as opportunity models and end up efficiency models. Astra rebuilt my 2011 building, and the tables show which model does which job.
10 Sept 2026 · 5 min
Three AI models, one brief: what each build actually cost
Fable 5.1, GPT-5.6 Sol and Gemini 3.8 Flash each built the same site from the same CV. The runs cost $23.57, $10.20 and $1.48. The harness still decides.
3 Sept 2026 · 4 min
Language models reason. Code calculates. The distinction that saves you
A CFO's spreadsheet added up perfectly and answered the wrong question. The rule that prevents it, and the harness that makes any model worth using.
26 Aug 2026 · 5 min
In a room of 2,300 people, one is building with AI
Eighteen in a hundred use AI. Three of those pay. Eight of those build. That is one builder in every 2,300 people, and that is where the leverage sits.
15 Aug 2026 · 6 minGet Build Notes by email
A few emails a month.