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.

🎟️ PRIZE: FREE SEAT IN THE LYCEUM 🎟️ Pick your cohort. Technical, Business, or Creator. Your call. ---- 🇺🇸 Quick note first. This post is going up Today because we took Memorial Day off yesterday. To keep things fair, you've got until Sunday May 31st at 12:00 PM EST to submit. Same week of build time, just shifted. ---- 📋 THE CHALLENGE Build a folder-based AI researcher for a specific topic or industry. You pick the domain. This week's deliverable is one researcher folder that someone could drop into a Claude project and use as their personal research partner for whatever domain you've built it for. ---- 🎯 PICK YOUR DOMAIN The domain is yours. Pick something specific. Pick something you'd actually use. A few sparks to get you thinking: - 🏦 M&A activity in one industry (fintech, healthcare, defense) - ⚖️ Court cases in one area of law (employment, IP, immigration) - 🧬 Scientific research on one health condition or treatment - 🏘️ Real estate market dynamics in one city or asset class - 🥊 Competitive intelligence for one product category - 📜 Historical research on one period, place, or movement - 📚 Academic literature in one specific subfield - 📋 Regulatory developments in one sector - 📰 Journalism research on one beat (climate tech, AI policy, biotech funding) The more specific, the better. "Research assistant" is too broad. "M&A research analyst for early-stage fintech deals in the US and Europe" is right. ---- 🗂️ THE METHODOLOGY If this is your first comp, welcome. Here's what you need to know: This week (and every week) you're learning interpretable context methodology. Folders as architecture. Each file does one job well. Your researcher is a folder with five things: - 📄 identity.md (who the researcher is, what domain they cover) - 📐 rules.md (how they research) - 💬 examples.md (what good looks like) - 📚 reference/ (frameworks, source lists, key concepts) - 📖 README.md (how to use it)

I've built folder systems for week 3 Competition (My first), Week 4 (Honorable Mention), Week 5 (I won) and currently finishing off Week 6 (I built one system, tested it and it didn't land), and each week I've learnt so much. Having a specific system to build with a solid brief certainly makes it easier. I've learnt about form and structure. I've learnt more about what Claude and I are capable of doing (still so much more to learn). i've learnt that even though I've never written a line of code myself before, and only started vibe coding about 2 months ago, when you apply the right structure, "anything" is possible (Even winning $500 in an ai building competition). I've learn't that Iteration is key. Each week, (and actually every time I start building something) I use the lessons from my last build to update my methodology. Literally I will get Claude to write it into the files so we don't make the same mistakes (hopefully), and we iterate (adjust/build on) on what we did last time. I've learnt to spend time in the planning phase, nutting out the details with my buddy Claude. Both last week (wk 5) and this week (wk 6) I actually rushed into building, and didn't spend enough time interrogating the planning phase. this meant that both weeks I built 2 specialists because i really wasn't happy with the 1st. essentially it just didn't fit the brief tightly enough. But this also helped me to understand the brief better, and also by understanding what wasn't right, it helped me get clarity on what I did want/need. Each week, I feel like I am stretching my knowledge and understanding of what's possible, so much further. if you're still unsure if it's worth entering the comp, I'd encourage you to do it. Not just for the possibility of winning (but it's a good motivator), but because you'll learn so much just by doing it. And of course, if you do want to win, you need to be a paid member of the community, which is definitely top value! happy Building friends!

Yet again making this SO hard to decide, I am bringing together a rubric just to be able to really break these down its getting so close. OVER 37 ENTRIES. Spent all day today looking at YouTube Videos, testing apps, reading through markdown files. Going to spotlight six (no particular order), then a few thoughts on where this is heading as well as the winner out of everyone. 🥊 @Ariel Ortiz , The Praeceptor Honest read: if Ariel had been premium last week, he was the winner and again this week easily can take home the prize but more importantly they are premium now! He went premium and somehow raised his own bar. Idea for a Native iOS app in Swift 6 , three YouTube videos including a 4:28 behind-the-build, voice mode pipeline, 17 operator extractions (Grove, Munger, Walsh, Aurelius, Naval, more). Hero copy reads "A room. Not an app." which was really a great hook, one of those opening lines that makes you very curious right off the rip. What I'd take from Ariel beyond this comp: he treats every brief like a product launch. Even the video stack alone is a walk towards the idea that distribution matters as much as tech now. 🔗 https://praeceptor-web.vercel.app 🔗 https://github.com/orteug/the-praeceptor 📹 https://youtu.be/Cfs1KAC2Ry0 🔥 @Ruby Sparks , The Gut Mechanic Ruby's a monster. Every week crushes it without a doubt. The landing pivots from consumer pain into a B2B sales pitch in one stat (the $530B-lost-to-employee-health number) and her voice across the entire page is sharper than what most paid brand consultants ship. She also created an ENTIRE skool community for it. Which is a win in its self. Twenty years of chronic illness in the founder story. IG, Skool, a 14-minute course, B2B framing layered into the consumer hook so the consumer side does discovery and the B2B side does monetization.

I need to walk back this morning's announcement before anything else. @Ariel Ortiz is not a Premium or VIP member. The competition was Premium and VIP only, stated in bold in the original brief. That eligibility check should have happened before judging and it didn't. That's on me. The $325 and the Week 4 title go to @Ruby Sparks. The rest of the writeup stands. Repeating it here so the corrected results live in one place. ➖➖➖ 🏆 WINNER: @Ruby Sparks 🏆 🔗 Repo: https://github.com/sparkles-inc/agency-os 🌐 Live site: https://agency-os-tan-five.vercel.app/ Ruby was within an inch of taking it on the original call. The judging call between her build and Ariel's was the longest I've sat with on any comp. She earned this on the work alone. The Loom video she recorded for this submission is the cleanest voice work I've heard on any community submission. Full-on infomercial quality. Voice acting level. If you haven't watched it yet, go watch it. It's a master class in how to present a build. Beyond the voice: an animated handoff explainer on the companion site, a WRITEUP.md that compresses the entire submission into three paragraphs of clean argument, and a design philosophy made explicit. She refused typed schemas in favor of human-readable Handoff Cards with seven sections including a required Gaps field ("if Gaps is empty, you're not looking hard enough"). One continuous narrative thread runs through all 27 files of her repo. Ruby takes the $325. @Sonija Quinn will reach out to Ruby directly for payment details. Remember: in a world where AI is making it easier to build, it's the unique opinions and styles that become valuable. ➖➖➖ I thought last week was hard to judge. This was the hardest comp to judge so far. Not even close.