How I Use AI as a PM With a Real Workspace
The useful version of AI for product work is a real workspace that keeps notes, data, drafts, and assets in the same loop.
San Francisco, CA
Writing
Notes on product friction, migration, AI workflows, and how teams actually get work done.
The useful version of AI for product work is a real workspace that keeps notes, data, drafts, and assets in the same loop.
A personal site, GitHub profile, and short notes should route people to the right depth instead of each trying to retell the whole story.
Small side projects are where I test workflow opinions, interface choices, and product taste without pretending every idea needs to become a company.
When thinking is still rough, a one-page artifact usually beats a deck because it forces structure without dragging you into presentation theater too early.
A lot of growth problems are really handoff, pricing, and service-definition problems wearing a growth label.
The hardest part of AI support is usually not the model. It is deciding what the system can do, when it should stop, and how it fits the real workflow.
Trust comes less from the best answer than from what the system does when it is unsure.
Most platform products lose in the first hour, not in the roadmap review.
A registry matters when it can answer what broke, who owns it, and what changed while something is already going wrong.
Migration pain is often designed into packaging, docs, and defaults long before a customer ever starts.
Internal platforms teach product judgment quickly because the users are technical, close to the work, and too busy to tolerate fluff.
Small scripts still earn their keep when they remove one repeated annoyance from the week.