Writing
Field notes from inside the first 90 days of a subscription product.
Field notes and build logs on subscription product, retention, onboarding, pricing, and activation. Written for Performance Health founders and PMs building toward Series B — the same surface the engagements work on.
Topics: Retention · Onboarding · Pricing · Activation · AI workflows
Build Log 03 — I built my AI agents a code review team
Never let a model grade its own work. I gave my AI build pipeline a planner, an engineer, an adversarial reviewer on a different model, a design critic, a brand critic, and a QA agent. Here's what the setup caught, what it missed, and the rule that only exists because it missed.
Read →
Build Log 01 — A daily AI briefing that writes itself overnight
Hours of podcasts and feeds for one usable insight. So I built a scheduled AI task that does the extraction overnight and ships a six-section briefing to my inbox by morning. The build decision that mattered: a written spec, not a clever prompt.
Build Log 02 — Vibecoding as a PM: what I built, what broke, what I'd do differently
Built an AI prototype for aiEDU almost entirely with AI. The product thinking that held up, the bugs that didn't, and the loop that turned every break into a permanent rule.
Subscription churn is an onboarding problem — the first-90-days fix
Most subscription churn isn't a retention problem. The 20–40% LTV leak founders blame on retention traces back to four onboarding mechanisms baked into the first 90 days — pricing, activation, paywall, and the first invoice.
Forthcoming
Field Note 02 — in draft
Forthcoming