This site is built to be read by your agent, not just you.

One thing I keep poking at is whether texture, the orientation behind your words, is the layer AI keeps dropping. So I encoded mine here. Copy a prompt, point your agent at it, and see if it unlocks anything you've been working on.

notes / 2026

Don't build the $100M system. Build the thing that gets you to next month.

mar 27 2026

I got a good step-back today. I was deep in designing this sophisticated, self-improving system, the version that scales to a hundred million. The reframe: you don’t need the thing that takes you to a hundred million. You need the quickest thing that gets you to your real near-term goal. The grand engine is seductive precisely because building it feels like progress while you’re not actually actioning anything.

The other piece is quality. You can have the most beautiful database in the world, but if you’re just using it to pump out generic volume, it’s noise. The interesting question isn’t ‘how do I automate more,’ it’s ‘how do I use a human-in-the-loop to make the output genuinely higher quality than slop.’ Build the data asset that compounds for you over time, but start with action, not architecture.

What’s the smallest version of your big idea that would actually move something this month?

working notes, loosely kept email · victoria, bc