Finding you need a whole second brain to give your agents enough context to be effective? Try building a system that lets them do the work with none. Pure ICM. The answer has been in manufacturing for a century. Separate the job into roles and give an agent only what it needs to complete one role. The product becomes the context as it moves through the production line. The agent sees what stage it’s working in and does that job before handing it off to the rest. No global context, no second brain.

There's something happening in here that I feel like I need to surface. I just cut a short from our conversation with Brian Clark on Bullhorns & Bullseyes. If you don't know Brian, he's the founder of Copyblogger—started it as a one-man site in 2006, before "content marketing" was even a phrase, and it's been called one of the most influential blogs in the world. He didn't invent blogging, but he's about as close as anyone to inventing what blogging became for business. Near the end of the episode, he says... "We're tribal. We can't shake our evolutionary upbringing, where you are attracted to people like you. That used to be based on appearance or geography, and now it's identity. And what is identity? It's a bundle of beliefs." He'd just said belonging is going to be more coveted, not less, as AI floods everything with things we can't tell are real. And the belonging that's left standing isn't geographic. It's not "we live near each other" or "we look alike." It's "we believe the same things." Now, for those of us in this community, we didn't all show up already agreeing on everything, and we didn't converge here because Jake is the guy to follow. We converged because @Jake Van Clief said something true first, and a few thousand of us recognized our own belief in it before we had words for it ourselves. That's how this works—someone has to say it first, most of us here, especially in the beginning, didn't need to be convinced. We were being reminded. This concept isn't new. It takes the same shape as every real reformation does. Belief stops living inside one person or institution and starts living in whoever recognizes it. Jake didn't build a following. He built a mirror, and we all walked up and saw ourselves in it. @Ruben Aguirre already did this in here—put his actual beliefs on the table, not a bio. If you're willing, I'd like to hear yours, too. But I'll go further than that. You've already been doing the belief work if you've built an ICM.

If you’ve been quietly struggling with learning how to build or what to build, you’re not alone. I’ve seen the posts, and I know how frustrating it can feel when things don’t click. I wanted to try to do something about it. I built a custom AI Tutor that has the complete knowledge and teaching style of @Jake Van Clief and @Matthew Creamer’s Foundations courses. Think of Jake as the professor. This agent is your dedicated Teacher’s Assistant who sits with you one-on-one. Here’s why it’s different: • It walks you through every concept step by step, exactly as Jake outlines them • You’re not just chatting or watching videos. You’re actually building files and folders together in Claude • It checks your work in real time and won’t let you move forward until you truly understand • It speaks in their voice and follows their exact methodology This is the hands-on practice and patient guidance a lot of us have been missing. How to try it: 1. Grab the repo 2. Follow the README 3. Open the folder in Claude and let the tutor take over I’m very proud of how it turned out and I want this to help as many people as possible. We just crossed 30,000 members! Let’s make sure every single one of us has the support they need to actually master this stuff. If you try it, please drop a comment and let me know: • Did it help you understand a concept that was confusing before? • What worked well? • What could be better? I want your honest feedback so we can keep improving it together. I’d love it if this could turn into a proper community teaching tool we all build and evolve. Link in comments 👇

I turned my remarkable paper pro (an electronic paper tablet. One of my favorite) into Tom Riddle's journal, but more importantly it's a new interactive surface. I can simply write in normal text and it gets sent directly to the model and the model response directly on the tablet itself in normal handwriting! Pretty cool! Going to see about connecting it to a couple icms! I used Maximes main repo to get it running !

In this interview I sit down with Matt from NLP Logix. He's been working in the AI space longer than most people have been working in general. We dive into what changed and what is it going to be important about the future. This is a three part series, I will be posting another two videos from another two experts in mathematics and Engineering! Please like and comment on YouTube if you have time as well!