I outsourced my own role in a simulation I was building — and it worked better without me. That made me wonder what's left for humans when intelligence is no longer our edge.
I assembled a panel of four AI experts — a consulting strategist, a market analyst, a financial planner, and a Jungian psychologist — and had them interview me across five rounds to figure out my actual career strategy. Here's the pattern, the conversation, and what it changed.
Everyone talks about what AI agents can do. Nobody talks about what it feels like to use them — the identity shift, the new flow state, the 10x mistake problem, and the uncomfortable truth that we're getting paid for work we no longer do.
How our enterprise chatbot evolved from GPT-3.5 with chunks in the system prompt to a full AI agent — and why every RAG trick we built along the way became obsolete.
How I built a novel UI-tree capture pipeline — browser bookmarklet, tree server, and AI generation — that produced 715 structured RAG actions where months of manual work had yielded 3.
How I built a Model Context Protocol server that gave AI agents full codebase understanding — cutting task completion time by 4.7x on a 500k+ LOC legacy system.
I built a production trading system in 8 days — 223 commits, Rust FFI, multi-connection WebSocket architecture. The interesting part isn't the bot. It's how structuring a repository as an interface for AI agents makes that velocity possible.
What 8 years of architecture decay actually looks like in a 500k-line enterprise monolith, how I diagnosed the root causes, and the four options I presented to the client — one of which was deliberately provocative.
How I built a distributed bot fleet that farmed MMO gold, listed it on eBay, extracted buyer names with GPT-4o, delivered gold in-game, and confirmed fulfillment — all without a single human in the loop.