A few days ago I shared the ICM Teacher, the thing that makes you build an ICM instead of reading about one. The feedback here already changed it, so thank you for that. If you haven't run it, it's about 15 minutes: https://claude.ai/code/artifact/124bbba4-afa6-4bef-9922-35c0f35d6d08 . Tell me where it falls short. Now I'm building an advanced version to follow it, and I want to share the idea behind it, because it's the part that stuck with me. The first one has you build an ICM for your own process. That proves you can do it once, and that felt like enough for a while. But going through it I realized that's not really the test. The test is whether you can take what you understood and use it on something you've never seen. Following a template isn't owning the method. Owning it is being able to shape it to something new. So the advanced version drops you into a situation you didn't build, one that's new to you, and here's the trick, it looks like a pipeline but it isn't one. The instinct you picked up in the first module falls apart. To find the shape it actually needs, you have to go back to the principles, not the template you memorized. That's the whole thing. ICM isn't one folder pattern you copy. Learn the principles deep enough and you can apply them to something that looks nothing like what you practiced on. Applying it to the new and the novel, that's the real skill, and that's what I want this one to build. More soon, and keep the feedback on the first one coming. It's shaping this.

🎟️ PRIZE: FREE SEAT IN THE LYCEUM 🎟️ ($4,750 Seat) Pick your cohort. Technical, Business, or Creator. Your call. 📋 THE CHALLENGE This is a weird one, and you may feel lost at first. But it's up to you to make a map for those who come after and if there is no map, you must get lost to make one. Build a folder-based cartographer that can walk a body of work and leave a map a later reader can wander and show what that map is. The later reader is often an AI. Sometimes it is a new person. Same map. Same job. Not why it failed. Not how to fix it. Not a tour of how the week goes. What the nouns are. How they move. What else moves if you touch one. What is live, what is leftover, and what is a ghost with a name and no wiring. This week's deliverable is one cartographer folder someone can drop into a Claude project, point at a real body of work, and get back a map a cold reader can enter without reading the whole thing. 🎯 PICK YOUR TERRITORY Pick a body of work you have actually been inside. Something a new person or a cold model would get lost in. Something someone will change, not something you will only describe. A few sparks: 💻 A repo you own. Even a small one. The map is for the next developer, or the next session, that has never seen it. 📂 A client delivery folder a VA or a contractor has to inherit next month. 🧩 A Make, GHL, or n8n pack someone else will edit without you on the call. 📒 An Obsidian or Notion vault a collaborator has to add to without breaking the spine. 🧾 The live records behind how a job gets quoted, approved, and invoiced in your shop. The files. The objects. Not the story of a bad month. 🎓 A course or L&D library someone will update after you. 🏭 The asset and work-order objects in a plant system you actually touch. The more specific, the better. Maps how our business works is too broad. Maps the five objects a new hire has to understand before they touch the invoicing folder is right. 🧠 WHAT YOU ARE ACTUALLY LEARNING ICM has six forms. You have been living in the first ones. Pipeline. Coach. Editor. Diagnostician.

📦 EVERY ENTRANT GETS A FEEDBACK FILE 📦 🔍 HOW WE READ THESE We cloned every repo and pinned it to its last commit before the deadline, so nobody got judged on late work. Only two repos had any post-deadline commits at all. Cleanest field this competition has had. Then we read file by file. Identity, rules, examples, the reference layer, the code. We ran every checker in the field on our own machine. Three would not run. For eleven entries we went further. We cloned the territory, or the entrant shipped it, and checked the cards against the source. Eleven is all the field allowed. Everyone else pointed at something private, unpinned, or gone. Two of those eleven were public codebases nobody in this community controls. On one gate we planted a bad citation to see if it would fire. Comments got you through the door. The judging happened inside the folders. 📚 WHAT THE FIELD TAUGHT Three lines split forty builds: ✅ The one rule held. The brief was blunt: a README that tells people to add every file has failed. Not one entry made that mistake. Every search hit was either a rule against it or a fixture broken on purpose. Name a failure precisely and this community stops doing it. ✅ Enforcement is now the baseline. Sixteen entries ship a checker that runs offline with no API key. Last cycle that was the headline. This cycle the checkers got better. One broken fixture per gate is now normal, and the best gate also ships a clean fixture to prove it stays quiet on honest prose. ✅ The cold walk decided the round. About half the field shipped a receipt of a reader entering a catalog, opening one card, and stopping. The top of the field is almost exactly that set. A map can be accurate and still hard to walk. This week we scored the walk. 🥇 THE WINNER @Adam James The Cartographer, a map of a live GoHighLevel account, built so a VA can change one message without guessing which of a dozen lookalike workflows owns it. He wrote down his test method before any test ran. Then he did what almost nobody does. He handed his work to people who could make him look bad, and let them.

Live with Danney Trieu · Four months ago I had never made a single AI video. I'm not a deeply technical person and never done any film in my life before, I'm just very passionate about this space. I figured out where the decisions live — which ones you hand to the machine, and which ones you take back. Then I found Jake & ICM just like many of you. Once I saw his method, everything got easier. More valuable than that, I found this awesome community that keep motivating me and supporting me. I like to give it back 🙏 So this Saturday, I'm hosting a Skool webinar here (Approved by Jake & Sonija) https://youtu.be/dryW_H54Rss This is for people who are not technical. Someone with a normal job who saw something on YouTube and wants to be able to make something similar for practical use. ━━━━━━━━━━━━━━━━━━━━ Here's what I'm covering -> 🪜THE SIX LEVELS OF AI FILMMAKING 1 · PROMPT — you type it, the model decides everything else 2 · REFERENCE — you stop describing the look and start showing it 3 · MEMORY — your world lives in folders, so you stop re-explaining it 4 · BLOCKING — you decide where the camera goes, not the model 5 · DNA — your taste, written down, applied automatically 6 · AUTOPILOT — you point it at your work and it hands you the shot list Most people are stuck somewhere between 1 and 2 — and have no idea there's a 3. ━━━━━━━━━━━━━━━━━━━━ 🙌 WHO THIS IS FOR If you've never done ai video or never gotten one great shot and then couldn't get a second one that matched — this is for you. ━━━━━━━━━━━━━━━━━━━━ 💬 ONE ASK BEFORE SATURDAY Drop a comment below: which level are you on right now, and what are you trying to make? I'm building the second half of the session around your answers — so the more of you who answer, the better this gets. And if there's appetite, this could becomes a regular thing 😉. ━━━━━━━━━━━━━━━━━━━━ 🔗 JOIN THE SESSION Save your seat here → https://us06web.zoom.us/meeting/register/nRitx_4JTzS-5MYKnoETRg

What I'd teach it: Continuity discipline for my festival film. I want it to know which locked set plate and which cast and prop pieces belong in a scene, and catch it before I burn a generation on something that breaks a rule, like a title word sneaking into a name, a character built from scratch instead of pulled from its reference, or video getting made before the still is even locked. Why it matters to me: Right now that all lives in my head. I'm the one checking every time, and if I miss it, I've wasted a generation on a project with a real deadline. I want an agent that actually gets better at not needing me to watch closely. What I'd want it to learn from: Every scene prompt session. What it pulled and where it came from, what it actually checked versus what it skipped, the near misses I catch before we generate, the bad ones we throw out, and whatever I end up fixing by hand. Plus reduce the frustration! How it would improve: Record it, one line per scene, what got pulled and what went wrong. Analyze it every so often, looking for the same mistake showing up more than once, not just one bad day. Patch it by drafting a real fix, a line added to the standard, a new check on the gate, but it doesn't touch anything live on its own. I look at it and decide. Test it by checking the next round whether that specific mistake actually stopped happening. What "better" would look like: The same mistake stops showing up in my review. The rule that used to live only in my head is now something the agent checks itself, and I've got a changelog that proves it actually got better instead of just getting lucky. I looked at building this on the full Hermes Stack, but it's a little bigger than I can handle right now, so I'm starting with the loop on its own.