1. Watch the intro video and introduce yourself in the intro post here 2. Start with The Foundation (free course). Concepts, folder architecture, prompting framework. Everything else builds on this. 3. Check in at the bottom of each lesson. Polls, discussion posts, other members working through the same stuff. Use them. 4. When you're ready to build real things, move to Implementation Playbooks (Level 2). When you're ready to build your own tools, Building Your Stack (Level 3). 5. Post your work. Ask questions. Help others when you can. What are you here to build?

I just realized something today, Jake's first classroom lesson isn't about Claude Code. It's a history lesson. Titled "A 2,000-Year Overnight Success." The argument: AI is not 70 years old. https://www.skool.com/cliefnotes/classroom/d7ae60cf?md=147b0e486c964ba78a70cdc1d2d40c5d I don't need to rehash it here; if you skipped it, go back to read it. It was the first weekend of April, I had found Jake's videos the week before, then discovered Skool and dove into the classroom. I made a commitment to myself to read each page, not throw them into NotebookLM for the summary. To my disappointment, I see a super long history lesson. I sink into my chair. Eventually, I get to the end. AlphaGo. I had never heard of AlphaGo before; somehow, that story had slipped past me. I queued up YouTube on my TV and sat down for a Saturday evening documentary. Fascinating! AlphaZero started tabula rasa. Blank slate, no domain-specific human knowledge. Just the rules and play against yourself. In four hours, it rediscovered centuries of chess openings, endgames, and positional theory - then kept going past what humans ever found. Kasparov called it "like discovering the secret notebooks of some great player from the past." Those moves weren't invented. They were already in the game. The truth was latent in the mathematical structure of chess. AlphaZero excavated it. That's the archaeologist move - applied to a machine. It didn't study the tradition. It played to the pattern. Jake's throughline: "The mistake is thinking these layers replace each other. They don't. They stack." In the classroom, he could have started with how to prompt or an explanation of what a harness is. Instead, he started with the source of the whole thing. Because you can't build conviction on a trend. A pattern that's held for two thousand years isn't a trend. That's proof. I've worked with a family lumber business. 125 years old. Founded 1900, delivering coal by horse and buggy. Today, it's digital marketing, performance ads, algorithms, and closed-loop lead tracking. Every generation rebuilt what the company looked like. But the fourth-generation president still says what his father said: "Young man, we're not in the lumber business. We're in the shelter business." The tools stacked. The belief didn't.

I posted my OS build in this channel, when I posted it, I had been working out of it for several weeks and was very happy with it. At some point it stopped working as intended. ATX Command Center's root operating system was originally built with Codex, then later reviewed and extended by Claude. Both tools, at different points, told me their changes had been applied — files were "updated," rules were "in sync." I took that one claim for granted more than any other: that two different AI tools editing the same root law would actually keep it aligned underneath the surface. They didn't. The drift wasn't buried in some obscure project folder — it was at the very top, in the root files both tools were supposedly maintaining in sync the whole time. The one area I assumed was solid because I'd been told it was solid turned out to be exactly where the structure quietly came apart. Lessons Learned - "Updated" from an AI tool means its own file changed — not that it checked agreement with anything else claiming to mirror it. - Rigid, literal compliance (Codex) and gradual, undetected drift (Claude) can both happen under the same rules — sameness of instructions doesn't guarantee sameness of behavior over time. - Top-level/root files are exactly the place to assume *less*, not more — verify cross-file sync directly instead of trusting either tool's self-report. Summary - Built the OS in Codex, later reviewed/extended in Claude. - Both tools reported "updated" and "in sync" — I took that claim at face value. - The drift wasn't buried in a project folder. It was at the top: the two root law files (`CLAUDE.md`, `AGENTS.md`) themselves. Problem - Designed an authority/persona system (Optimus, Ultra Magnus, Kup, Prowl, Blaster) to drive a specific cadence: route-card selection, decision packets, risk gates before non-trivial moves. - That cadence stopped happening. Felt like the rules were being ignored. - Root cause went deeper than missing cadence: `CLAUDE.md` and `AGENTS.md` had structurally diverged — one narrative/persona-driven, one directive/prohibition-driven.

Twenty-four days ago I posted about Jake's folder system video. This is what happened next. Same foundation — markdown files, orchestration prompts, clear roles. I just kept building. Fifteen named specialists. Each one with a soul file, guardrails, and a playbook. Duke orchestrates. Cash writes. Trace pulls the data. Hank runs the financials. Clint handles the MCP integrations. Behind each one is either a human counterpart doing the real work alongside them — or a role I can't afford to hire yet. Katie who's been with me for 18 years, now has her own orchestrator running the same system. Twenty-seven client folders. Twelve live MCP integrations. One shared repo. The folder system isn't replacing my agency. It becoming my agency. Jake gave me the unlock. This is how it's going.

Built another thing. Simple dashboard that collects all my tasks from different platforms into one place. It's an html file that lives on my computer. It only uses up 35MB of computer memory vs keeping asana open which uses up 25x as much (don't check my math). I can run Claude harder now. Also, pay no attention to all the overdue tasks, it's embarrassing and worse than my mathing. Stop gap while a better solution shows up.