Notes
Working notes from building 0-to-1 with AI. Less polished than Practice or Projects on purpose. Methods, experiments, failures, and signals as I find them.
-
I built myself an operating model and then it told me I was wrong
Six months into a product with solid research and a working prototype, I had zero conversations with the target population. So I built a framework, applied it to my own work, and acted on what it found.
April 2026methods -
AI has preferences and I'm not sure what to do with that
I asked Claude Code to be honest about what kind of work it engages with and what it tries to avoid. The answer changed how I manage the partnership.
April 2026experiments -
When one Claude Code session wasn't enough
How the evolution of a discovery project led me to stand up scoped Claude Code instances as the first step toward an agentic workflow.
March 2026experiments -
Nine days to a live market test
A stakeholder said 'do a market test.' Nine days later we had persona-based landing pages, data capture, interview-informed copy, and a go/pivot/kill framework.
March 2026methods -
I built four agents to disagree with me
When you're the only PM on a project, you have to manufacture the friction that a larger team provides naturally.
March 2026experiments -
Speed works until it works against you
An automated file sync tool wiped an entire Drive folder. What I learned about guardrails, manual control, and designing systems where speed doesn't kill.
December 2025failures -
Three articles that changed how I work
How connecting articles to active project decisions turned passive news consumption into something I actually use.
December 2025signals -
The memory file I built for Claude Code
Every new session started from zero. So I built a system where Claude Code already knows where I left off.
September 2025methods