I'm a product manager. I write specs, run reviews, align stakeholders.
Last year I got tired of handing things off and waiting. I picked up vibe coding, designed the knowledge base, wrote the Harness, and shipped a working game AI Agent — with help from the engineers I work with. My front-end and back-end colleagues gave me ideas, pointed out problems, and occasionally pulled me out of rabbit holes I'd dug myself into. But the product decisions, the Harness design, the debugging loop — those were mine to own.
That process changed how I think about the PM role. In an AI-native stack, the gap between "I have a product idea" and "it's running in production" has collapsed. A PM who can design model behavior, engineer context, and debug Harness failures doesn't need to wait for engineering bandwidth — they just ship. And when they do need engineers, they can have a real conversation instead of throwing a spec over the wall.
That's what I'm building toward. Some call it FDE — Field Development Engineer, or Founding-level engineer who sits at the product-engineering boundary. Someone who owns the full loop: requirements, model behavior, Harness design, deployment. Not a PM who codes a little. A builder who understands the product deeply enough to make the right engineering calls.
