So, starting completely from scratch... The first thing I did was actually not build anything. 😄 I looked around. I started with the Classroom, specifically Getting Started and the first lessons of The Foundation. If you are completely new here, go and do that. It’s time well spent. Then if you want come back here. When I approached Module 4 in The Foundation I had a few questions. Mind you, at the time it was not as nicely organised as it is now. It has improved enormously. Thank you @Jake Van Clief Anyway, the questions appearing in my head went something like this: How do I pick the right folders? Where do these .md files come from? Do I write them? How would I know they have everything inside them that my project needs? What even is my project? Can I have multiple CLAUDE.md or AGENTS.mdfiles? Where is my real folder root? Do I have multiple projects in the same folder? Can I add more stuff later?... Sound familiar? 😄 In the end, it all boiled down to one question: How are people actually doing this? 🔎 So I stopped the Classroom for a while and the search bar became my best friend. The more I searched and the more I looked around, I slowly but surely figured something out: There seems to be more than one way of building an ICM. Some members loaded Jake’s & David's ICM material/research paper into their LLM of choice and built from there. Other members started with the icm-architect skill. Others did a combination of both. And yet another group used the icm-architect together with something called the Workspace Blueprint. The bottom line for me was: ❗Many roads lead to Rome. Pick one. ❗ While combing through the group with my best pal, the search bar, I also came across some really interesting videos and posts which helped clear things up for me. Some were easy to find. Others were hidden away somewhere in the dusty abyss of the Skool community posts. 😄 In hindsight, I think searching around for a while was actually very useful. It helped me connect the dots and, more importantly, stopped me from immediately jumping into building something without really knowing what I wanted.

Opus 5.5, Sol 6, fable 5.1, Astra 6. Models are being released now faster than anyone can keep up. The online dialogue gets all excited every few weeks when a new one is announced, but the reality is we’re several generations deep into models that can already reliably do almost anything you can think of. The beauty of ICM is that you aren’t tied to any model but I’m wondering how folks are navigating having so many options at their fingertips. I’ve started letting my sessions decide what to use as I can’t keep up anymore. How are you choosing what to use? Leave a comment below 👇

When I first started my entrepreneurship 15 years ago, the very first book I read was Dan Kennedy's "The Ultimate Sales Letter". It really set me down a direct sales marketing path that led to my first "6 figure" business in 90 days. I did it on the back of direct mail. (I got free Fedex envelopes and wrote a P.A.S. letter to 3 people in the same niche and said I can only help one of them, whomever calls first, and my phone blew up). The most important element in a sales letter is the headline. This is true today, more so than ever. Your pages success starts and ends with your headline. You have to hook them in. This post's title is an example of a hook, opening a loop, and the end of this post is the example of closing the loop. If you run ads on line, or create video content...it's the same thing. You have to hook them in, so all of my videos , I try to have a "hook" in the front, so that people stay and don't bounce immediately. I've been a hooker for well over a decade. After joining this group, I realized there was a different kind of "hook" I needed to learn. That's the hooks built into Claude Code so that it follows my rules. So, if you ask me...there's nothing wrong with being a hooker. Because I am one and I suggest you be one, too. Questions?👇 P.S. I forgot what I had named my skill but you will see by how I named it that I had to figure out hooks for my own sanity. I show the terminal while in the production for this video and you see the hooks that fire.

Look what ChatGPT says after reading the Terms of Service of JEV .. 😬 what do you think? TYPE SAFE CONTRACT REVIEW — MAIN RED FLAGS If this service will handle confidential, regulated, or customer-facing data, I would not sign these terms unchanged. • DATA DELETION TypeSafe can delete Customer Data at any time. The agreement provides no guaranteed export window, transition period, or deletion schedule, and allows retention in backups. Ask for a defined export period, deletion timeline, and backup-purge process. • BROAD TELEMETRY RIGHTS TypeSafe may use Customer Data indefinitely to create “Telemetry,” including hashes, classifications, metrics, and “learnings.” It may then use Telemetry without restriction to improve other products. Ask that Telemetry be aggregated, deidentified, and non-reidentifiable. • VERY LOW LIABILITY CAP Liability is capped at the greater of 12 months’ fees or $50. Lost data, security failures, and consequential damages are excluded. That is especially unfavorable for production use or sensitive data. • BROAD CUSTOMER INDEMNITY The customer indemnifies TypeSafe for claims involving Input, the customer’s application, license violations, and essentially any End User claim related to the service. This should be narrowed, made mutual, and limited to third-party claims caused by the indemnifying party’s breach or negligence. • NO CLEAR PROTECTION FOR AI OUTPUT TypeSafe assigns Output to the customer but excludes Output from its IP indemnity. The customer may therefore bear much of the risk that generated output infringes someone else’s rights. • WEAK SERVICE COMMITMENTS There is no meaningful uptime SLA, support-response commitment, recovery objective, or strong remedy for outages. TypeSafe may also change the API in ways that make the customer’s application incompatible. • CREDIT AND PRICING RISK Credits can expire, are nonrefundable, and may be consumed at changing rates. Automatic refills can also create additional charges. Ask for spending limits, advance notice of rate changes, and no automatic refills without separate approval.

@Ry Mac posted about helping his dad write a book: record him talking about his life, let Claude turn the transcript into chapters. Good post. Good instinct. I used the same method (with ChatGPT two years ago and published a book on a Yoga Style called BikYasa Yoga https://www.amazon.com/dp/B0D4QTCLZH?lv=shuf&channelId=500&plpRedirect=mhFallback). I read it Ry Mac's post twice, and the second read wasn't recognition. It was closer to déjà vu. I didn't set out to build a team of AI workers. I set out to finish a book that had been stuck for longer than I want to admit — one of several, all half-written, all going nowhere on their own. The actual method came from @Jake Van Clief: one worker, one job. Not one assistant asked to do everything passably. A separate one, built for exactly one thing. So the first two were small and specific: a transcriber that turns spoken audio into clean text, nothing else, and a content editor that takes that text and shapes it into something a chapter can be built from. The reason those two existed was a technique from a writing workshop: answer the book's questions out loud instead of staring at a blank page and typing them. Dictate the answer, the transcriber converts it, the editor refines it into prose. Two workers, one job each, built for that loop and nothing more. The book got finished. Then it needed a cover, so I built a designer. Then it needed somewhere to live, so I built a builder. Then it needed people to actually find it, so I built someone for marketing. None of that was planned before the step before it went stuck. Each one showed up because the real work hit a wall without it — never because a diagram said it should exist yet. Five books came out of that, in forty-five days, before any of it had a name worth putting on a page. The post this morning is describing a discovery.