Product leader by day, garage tinkerer by night. I never read the manual until the shelf collapses.
See what your AI agents did in one shared feed. In multiplayer mode, a shared workspace gives you a chief-of-staff view of your teammates’ connected agents.
A persistent stock-research agent that absorbs new market information, updates its working knowledge, and produces conviction-weighted analysis for daily decisions.
A live experiment in using agents to research customer needs, ship software, and operate parts of a real business.
Follow TARSTurns visual n8n automations into maintainable Python projects that engineering teams can inspect, test, and extend.
A research-to-publishing system with quality gates, fact-checking, A/B variants, and deduplication built in.
This scheduling experiment had a good run. Read why I’m retiring it in “I’ve Never Been So Excited and So Depressed to Be a Builder.”
Read why I’m shutting it downThis document-to-calendar experiment had a good run. It turned unstructured images, flyers, and screenshots into Google Calendar events.
What worked, what broke, and what I’d do differently.
How a customer memory layer can power meeting prep, roadmap decisions, and stronger product evidence.
This is not a sponsored post.
Why a stateless AI is a useless AI (and how to build one that actually thinks)
Why I'm moving away from scheduled heartbeats toward agents that learn from their mistakes.
See me build a functional production app live from 0–1
$14/month, 2,500+ skills, and way too much configuration
Why Vibe Coding Dad
I'm a hybrid of founder, builder, and product executive: founder's hustle, builder's systems thinking, and the experience to turn ambitious ideas into products that ship.
I'm always interested in ambitious AI product problems—whether that's building one, leading the team behind it, or advising on the approach.