Long time no see everyone. I wonder if I’m a late starter and everyone uses my newly explored trick for my team or if it’s a revolutionary idea 😊 I build AGENTs for my team and started using .files for things they shouldn’t see. Not because I wanna be secretive but because they can’t break what the don’t see (if it’s protected of course) and their view is clear for the things that matter. Simple example: Project folder —— .AGENT.md —— .logo.svg —— .style.css —— TEMPLATE.html —— 01_inbox —— 02_output In that case the template - is filled with data from the inputs copied to the output for instance. The output html the can open and print as pdf, like a contract we use over and over again and is branded. They don’t need to see css, logo or not even the AGENT. Not even use an AI 😊 Magic ❤️ What do you say?

Hi everyone, I know that security is a large constraint for companies that are skeptical around AI workflows and I was wondering if anyone has any experience in this field. I am trying to set up a consultancy agency and I want to be able to reassure future clients that what I’m doing is secure. Right now, I have no clue whether it is secure or not. I would greatly appreciate it if you can share your experience (if you have it) as well as possible book recommendations so I can become proficient in this area. Thanks in advance 🙏🙏

🎟️ 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.

A few days in. Starting to see where the Clief Notes AI is actually becoming useful. Some of you are using it to figure out where to start. Others are asking specific questions and getting pointed back to lessons or drops they didn’t even know existed. And some are basically using it as search: “Have we covered this before?” That last one alone saves a lot of scrolling. @Anthony Brady shared a really good example of how he’s been using it. He said the agent has been helping him find the right lessons, figure out where to go next, and actually apply the material to what he’s building. He’s even been pushing it with harder questions, and when it doesn’t know something, it tells him instead of just making something up. What I really liked was how he described using the tools together: The agent helps him navigate. NotebookLM helps him go deeper. And Decster keeps him moving through the course, completing assignments, and staying active in the community. That’s exactly what we want this to become. Not another AI tool you open once and forget about. Something that actually helps you use everything already inside Clief Notes and keep moving forward. We’ve also caught a few questions where the agent could’ve pointed somewhere better. Keep sending those. The more you use it, the better we can make the experience. This thing should get more useful as we see how you actually use it. If you haven’t tried it yet, start simple. Ask it the next question you would normally post in the community. Have you tried it already? If not, comment “Navigator” and I’ll send you access to it.

A model reviewing its own work is not a review. It is the same judgement run twice, and it agrees with itself both times. - Maker and checker are separate passes - whatever produced the work does not get to grade it. - Fresh context, not just a fresh prompt - a different chat, ideally a different model, carrying none of the reasoning that built the thing. - A number it cannot argue with - a test, a diff, a count. Prose review on its own will find reasons to approve. The failure mode is not that a model lies to you. It is that it is still holding every assumption that produced the work, so asking whether the work is good just reasons forward from those assumptions and lands where it landed the first time. I have had this go wrong with real stakes on it. Folder bloat that survived an adversarial review and two further passes on the strongest model I had. A multi-repo restructure proposed off one of three files the model had actually read. A Git migration recommended on the grounds that we had a backup, which we had made ourselves an hour earlier. Every one of those cleared a self-check first. What changed it was making the check structural rather than something I remember to do. In my YouTube workspace no finding enters the register until it has been surfaced to me at the close of the query that produced it, so the system proposes a belief and a human commits it. In phronesis the distillation pass runs behind an eval gate allowed to reject the commit outright, so the pass that writes the profile is never the pass that decides the profile is good. Metrics carry the other half. A verdict written in prose can always be argued into place, a count or a failing test cannot - if the only evidence something worked is a paragraph the model wrote about its own output, there is no evidence. Where has a self-review waved something through that it should have caught, and what do you actually use as the outside check - a second model, a fresh chat, a test, someone else in here? More interested in the practical setups than the principle.