🎟️ PRIZE: FREE SEAT IN THE LYCEUM 🎟️ Pick your cohort. Technical, Business, or Creator. Your call. ---- 📋 THE CHALLENGE You are the client this week. No fictional Marcus. No fictional Sarah. No fictional Devon. Pick a real problem in your own life or work. Build the folder-based specialist you wish you had. This is the capstone of Month 2. The challenge flips. Instead of building for someone else, you write your own brief and solve it for yourself. ---- 🎯 THE TWIST The hard part isn't building. The hard part is scoping. Picking the right problem is harder than solving the wrong one. Most people pick problems that are too small or too vague. The skill this week is treating yourself like a real client. Be specific about what's broken. Be specific about what you need. Don't pick "I want to be more productive." Pick "I waste two hours every Sunday night writing the same kind of LinkedIn carousel posts and I need a folder that handles 80% of the draft work so I can focus on the hook and the visuals." That's a real brief. Specific problem. Specific scope. Specific desired output. ---- 🗂️ TWO DELIVERABLES THIS WEEK This is the only week with two pieces: 1️⃣ Your own client brief. 250 words or less. Describe the problem you're solving for yourself. Treat yourself like a real client. What's broken? What have you already tried? What do you need? 2️⃣ The folder system that solves it. Same structure as every week: - 📄 identity.md - 📐 rules.md - 💬 examples.md - 📚 reference/ - 📖 README.md Your brief lives at the top of the repo as brief.md so judges can read it before they look at the folder. ---- 🔥 THE ANGLE THIS WEEK Anyone can follow a brief. Writing your own, then solving it, then shipping it as a usable folder is a portfolio piece that demonstrates judgment, not just execution. This is the skill that separates "AI hobbyist" from "AI builder." Anyone can prompt their way through a problem someone else handed them. Scoping a problem, designing the solution, and shipping it as a system is what real work looks like. 💪

When deploying an ICM folder structure to an actual client, asking them to drop it into their claude seems reasonable for us techy people, but some of my clients are not technical enough to even do that. What other options are people using? I'm a traditional web app guy, so deploying a cloudflare worker with some backend code and a database etc is what I would traditionally try and do. That model is not as clear cut as a winner as it used to be! Is it time to look at agentic systems to be able to deploy ICM so my clients can actually use it in their day to day? Or do we simply train them up to use claude? Or is there something else that people are doing?

Looking at the numbers in this group got me thinking about how we measure engagement around here. Coming from the hair industry, social media analytics are basically life or death for us to keep our chairs full, so I always notice this stuff. We have like 39,000 people in this group, but the highest response I saw on a survey was around 7,000. I think a lot of people see that gap and think it's bad news, but honestly a 17% engagement rate on a single post is kind of insane. From what I've had to learn about marketing just to run my own business, you are usually lucky to even get 1% or 2% of your audience to wake up and click a button on regular platforms. But at the same time, it does feel like the daily comments come down to the same 20 or 30 people, and a massive chunk of the group is still sitting at Level 1. They probably just jump in to grab the classes and then ghost the social side completely. In my line of work you learn that there are always tons of people who are getting value from what you do but they just stay quiet. They don't have the social energy or the confidence to post. Especially in a tech heavy group like this, it is so easy for a beginner to scroll through, feel some major imposter syndrome, and just decide to stay quiet. I'm super curious, for anyone who actually made it past Level 1, what finally broke the ice for you? Was it wanting to rank up in the levels, or did you just wait until you had something cool to share?

🎟️ PRIZE: FREE SEAT IN THE LYCEUM 🎟️ Pick your cohort. Technical, Business, or Creator. Your call. ---- 🇬🇧 We're back. Good morning from London. 👋 Thanks for the patience last week. Jake and I needed a few days to breathe before London Tech Week kicked off, and you all responded with nothing but support. We don't take that for granted. Now let's get back to building. ---- 📋 THE CHALLENGE Build a folder-based AI operator that handles ONE operational workflow end-to-end. You pick the workflow. This week's deliverable is one operator folder that someone could drop into a Claude project and use to handle a real business workflow without babysitting. ---- 🎯 PICK YOUR WORKFLOW The workflow is yours. Pick something specific. Pick something you'd actually use. A few sparks to get you thinking: - 🎫 Customer support triage (which tier handles this ticket?) - ✅ Content review and approval - 📨 Lead intake and qualification - 💸 Refund request handler - 🤝 Partnership pitch evaluator - 🎙️ Podcast guest pitch sorter - 💼 Freelance project intake - 📄 Resume screen for one specific role - 📅 Meeting request triage (book, decline, delegate) The more specific, the better. "Customer support" is too broad. "Refund request triage for an ecommerce store doing under 200 orders per month" is right. 📎 If you want a fully written client brief as a reference, the attached PDF walks through one example. Don't build the example. Use it as a template for how to think about scoping your own operator. ---- 🗂️ 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 operator is a folder with five things: - 📄 identity.md (who the operator is and what workflow they own) - 📐 rules.md (the decision logic: criteria, edge cases, escalation rules) - 💬 examples.md (decisions in action, including at least one edge case) - 📚 reference/ (checklists, templates, rubrics) - 📖 README.md (how to use it)

Man, I just started learning markdown! I can't keep up! ICM in HTML? "It started with Thariq Shipar, Engineering Lead on Claude Code at Anthropic. On May 8, he tweeted: “HTML is the new markdown. I’ve stopped writing markdown files for almost everything.” His argument: when AI writes the content, Markdown’s “easy to write” advantage becomes less relevant. HTML gives you richer layouts, interactivity, and visual hierarchy. Why he thinks HTML wins: Shipar backed it up with a companion site showing 9 categories where HTML artifacts beat Markdown: - Interactive dashboards - Styled code reviews - Inline SVG illustrations - Arrow-key presentations - Collapsible explainers Things that are impossible in a flat .md file become trivial when AI generates HTML. But there was pushback. Developer Kutis Redux published a direct rebuttal: “The Unreasonable Ineffectiveness of HTML” His argument: the switch to HTML creates visual gloss at the expense of source readability, security, ecosystem compatibility, and reviewability. His core point: HTML’s raw source is hostile to human eyes. Markdown stays readable whether rendered or not, which matters when you’re reviewing what an AI just wrote. Then Andrej Karpathy weighed in and went bigger. He called it an evolution: raw text → Markdown → HTML → neural interfaces His advice: Add “structure your response as HTML” to your prompts. He confirmed: “It works really well.” The endgame? AI outputs will not be static documents at all. They’ll be interactive simulations." Sources: - Thariq Shipar on X, May 8, 2026 - thariq.github.io/html-effectiveness - Kutis Redux on Medium, May 2026 - Andrej Karpathy on X, May 11, 2026