Skip to content
AI-Native PM
How this site was made

How We Built This Site

We built this the way we teach you to build with AI: not in one long chat, but by directing fleets of agents, reviewing what came back, and deciding what to keep. Here is the honest record, by the numbers.

How the site was built, drawn as a loopThree boxes read left to right. We, who direct and choose, sending 324 prompts. A fleet, which builds in parallel, running 788 agents. The site, what got made, 154 thousand words. A return arrow runs underneath from the site back to us, labelled review, correct, repeat. Caption: about one in five of our messages was a request to do it differently.THE BUILD, IN A LOOPreview · correct · repeatWEdirect and choose324 promptsA FLEETbuild in parallel788 agentsTHE SITEwhat got made154k wordsAbout one in five of our messages was a request to do it differently.

Underneath the writing sits the machinery: 50,584 lines of code, 212 components, and a 33-rule voice spec we held every sentence to. The numbers below are grouped by who did what.

What we built

153,826
words of original writing
about two books' worth
77
teaching chapters
across 3 levels and 9 parts
168
custom diagrams
every one in the house style
13
field notes
plus 4 framework essays

How we worked

100
days, start to here
from the first idea with Claude
324
prompts we wrote
one conversation, start to finish
65
commits
every one our call to make
300+
hours at the desk together
ideation onward, with Claude

The fleet that did the building

~788
agents run in parallel
a fleet, not a chat
40
multi-agent workflows
fan out, then verify
~64.7M
tokens generated
the work the AI produced
11,977
turns in the build
refreshed its memory 16 times

Staying in the loop

~1 in 5
of our messages was a correction
“simpler,” “revert,” “none of these”
~60
rewrites and redirects we asked for
the first version was rarely right
7
times we stopped the AI mid-task
the human kept the brakes
55
times we decided when to save
nothing shipped on its own

The number we keep coming back to

Of everything here, the last group matters most. About one in five of our messages during the build was a correction, a “make it simpler,” or a “none of these.” The first version was rarely the right one. What made the site good was the choosing and the cutting, done over and over, which is the whole argument of Taste Is a Muscle, Not a Gift.

We wrote about the method while we were using it: How We Used Agent Fleets to Build This Site, How We Caught AI Mistakes With a Second Agent, and How We Used Preview Labs to Design This Site.

← About the buildersField Notes from the build →