💰 $500 CASH 💰 Win this and you've covered a year of Premium with $175 left over. 📋 THE CHALLENGE Build a folder-based AI coach for a specific domain. You pick the domain. This week's deliverable is one coach folder that someone could drop into a Claude project and use as their personal coach for whatever 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: - 🎤 Public speaking coach for new managers giving their first big presentations - 💼 Salary negotiation coach for tech workers at Series A startups - 📞 Cold call coach for first-year SDRs in B2B software - 🎯 Interview prep coach for product manager roles - ✍️ Writing coach for one specific genre (sci-fi short stories, college essays, op-eds) - 🏋️ Fitness form coach for one movement (squat, deadlift, golf swing) - 🌍 Language learning coach for one use case (medical Spanish, business Mandarin) - ♟️ Chess coach for one specific opening or endgame pattern - ⚽ Youth athletics coach for one sport and age group The more specific, the better. "Life coach" is too broad. "Salary negotiation coach for tech workers at Series A startups" 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 the foundation of interpretable context methodology. Folders as architecture. Each file does one job well. Your coach is a folder with five things: - 📄 identity.md (who the coach is) - 📐 rules.md (how they coach) - 💬 examples.md (what good looks like) - 📚 reference/ (frameworks, drills, source material) - 📖 README.md (how to use it) Drop the folder into a Claude project. Claude becomes the coach. Reusable. Shareable. Portable. 🔥 THE ANGLE THIS WEEK A coach is NOT a knowledge base. A coach gives feedback. Pushes back. Asks better questions. Holds people accountable.

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.

Claude Projects doesn't accept folders, only files. So the usual ICM layout (CLAUDE.md at root, /protocols, /reference, /templates, /examples) won't upload as is. What I did: - Flattened everything into a single folder. Renamed each file with its folder as a prefix, e.g. protocols/guardrails.md became protocols_guardrails.md. Keeps the origin visible in the filename. - Updated every internal reference inside the files so the File Map and cross-links point to the new flat names. - Pasted the body of CLAUDE.md into the Project's Custom Instructions field. CLAUDE.md has no special status in Projects (unlike Claude Code), so the orchestration rules need to live in the instructions box to actually govern behaviour. - Uploaded the other files as Project knowledge. Done. The File Map still works as a routing index. Early days but the structure holds. BEFORE: ├── CLAUDE.md ├── CONTEXT.md ├── protocols/ │ ├── protocols_guardrails.md │ ├── protocols_de-identification.md │ └── protocols_voice-guide.md ├── templates/ │ └── templates_All_Letters_Templates.md ├── references/ │ ├── reference_Work_Flow_Chart.md │ ├── reference_NOTES_TEMPLATE.md │ └── reference_NOTES_EXAMPLE.md └── examples/ ├── examples_CUSTOMER_LETTER_EXAMPLE_1.md ├── examples_CUSTOMER_LETTER_EXAMPLE_2.md └── examples_LETTER_FOLLOWING_CONSULTATION.md AFTER to work and reference within CLAUDE Project: ├── CLAUDE.md (pasted into INSTRUCTIONS) ├── CONTEXT.md ├── protocols_guardrails.md ├── protocols_de-identification.md ├── protocols_voice-guide.md ├── templates_All_Letters_Templates.md ├── reference_Work_Flow_Chart.md ├── reference_NOTES_TEMPLATE.md ├── reference_NOTES_EXAMPLE.md ├── examples_CUSTOMER_LETTER_EXAMPLE_1.md ├── examples_CUSTOMER_LETTER_EXAMPLE_2.md └── examples_LETTER_FOLLOWING_CONSULTATION.md

Like many young people today, I started my AI journey with ChatGPT. I am not a software engineer and have always preferred less tech in my life in general, I still prefer to read physical books today. For me, ChatGPT was first just a fancy Google, helping me find information a little quicker and answering random questions that I would think of. But it also turned into a gateway drug for what AI could do, and it wasn't until a friend told me about agentic AI that those lightbulb moments started to happen. Suddenly I could create my own website or app. I could create specific things to make MY life easier. And then it hit me, NOW I CAN DO THIS FOR SOMEONE ELSE... AND GET PAID! And like that I dove head-first, oblivious and clueless, but motivated and excited about the possibilities. Did I find Grok or Claude? NO I found MANUS AI, and after 4 months, 6 websites and 2 apps, I decided it was time to learn about Claude, I mean, all the "techies" I see can't stop talking about it! So I find Clief Notes... Now I'm realizing just how much this agentic AI has been doing for me... And I can also see how easily it could make AI models like Claude obsolete. Could I be wrong? ABSOLUTELY! But while the right person could do everything in Claude that Manus can do, I'm left wondering what happens when the next update just destroys everything else and if I should solely focus on agentic AI instead. I know I seem like a "doomsdayer", and I am no engineer or AI expert, but I can't help wondering what Claude can do that some of these high-end agentic AI models can do I would love to know your thoughts and PLEASE prove me wrong so that I can know!

How did i do?