Field Notes
What the work teaches, written down while it is fresh.
Short pieces from building AI products in production, split two ways: perspectives on how the work is changing, and tactics you can apply to a live product.
Open for contributions
Reach out to contributeField Notes is open to other builders. If you are building with AI and have a note worth sharing, reach out.
Perspectives
How the work is changing, and why it matters.
How We Used Agent Fleets to Build This Site
The picture of building with AI is one person and one chat window. This site was built the other way, with many workers running at once and a person setting the brief and judging what comes back. That is the real shape of the work once the scale is real.
What We Built for This Site and Then Deleted
Some of the best decisions here are things you will never see, because we built them and then cut them. Deciding what to throw away is the same judgment as deciding what to make, and it is harder when the making was cheap.
How We Used Preview Labs to Design This Site
Almost nothing here went straight to a single answer. Each piece started as a set of options in a preview lab, because when a tool hands you ten finished-looking versions in a minute, the work is no longer making one, it is choosing the right one.
Strategy Used to Be a Document. Now It's a Discipline.
In late 2023, a single ChatGPT update turned a whole cohort of startups' only differentiator into a checkbox. This is what strategy has to become when the ground can move on the platform's schedule, not yours.
Taste Is a Muscle, Not a Gift
For twenty years, making one good option was the hard part. Now ten arrive in a minute and the whole job is choosing, which means taste, the muscle that does the choosing, is the one you most need to build.
The Missing Layer
AI put building in everyone's hands. A thin layer of knowledge still decides who ships and who stalls, and it is the most learnable gap there is.
Tactics
Concrete moves you can apply to a live product.
How We Used Loops Instead of One-Off Prompts
Using a model one prompt at a time makes you the loop. The better structure hands the loop to the system: an objective, a metric to score against, and a boundary for when to stop. These are the loops we ran to build this site.
The AI-Native PM's Ownership Map
The AI-native PM owns the product's behavior, not its model, and a lot of that ownership goes unassigned until it shows up as the incident. This is the working map of what you own across Shape, Ship, and Track, the move that delivers each one, and how you know it is done.
Access Control Is a Product Decision, Not a Security One
When an AI product pauses to ask "Send this?" or fires the action silently, that single screen is the whole product. What your AI is allowed to do, on whose behalf, and with which data is the trust contract the user feels, and the people who treat it as a backend chore are the ones who ship the headline.
How We Caught AI Mistakes With a Second Agent
When workers run in parallel, each hands back something that looks finished, and finished-looking is not the same as correct. Every draft on this site met a second worker whose only job was to take it apart first.
Why We Added a Dark Mode to This Site
We did not add dark mode to look modern. We added it because of who reads this and when, and that reframe, from fashion to the reader's real situation, decided how we built it.
Why We Told the AI to Disagree With Us
The most useful instruction we gave the assistant building this site was not a task. It was a standing permission to disagree, because a collaborator who only ever says yes tells you nothing.
The PM's Toolkit for AI Behavior Design
Two teams point the same base model at the same task and ship products that behave nothing alike. The difference is a set of levers, and the work is turning them with intent.
Why We Replaced Our Clever Navigation With a Plain One
Twice we built a clever navigation and twice we cut it for a layout readers already knew. Every new mental model is a tax on attention, and on an education site that attention belongs to the lesson.