Sharing my agents.md folder structure with you all, broken into two images. I'm about two months into this, so I'm still learning. Curious if this looks bloated, if there's a cleaner way to set it up, or if anything here could be improved. Would love to hear what the community thinks.

This post is not for the ICM pro, there will be no talk of gates, scripts, or orchestration! This is for the person just starting out! @Karli Rosario Yes, I mean you! (And anyone else who may just be starting out with ICM) Seriously, I'm glad you found ICM. Let me give you the simplest version of it I know. ICM is a system of structured folders. Yes, the same folders you have been using on a computer for most of your life. The ones you stored photos in, & pirated music from Napster and LimeWire. That's it. I will take you through the process below. When working with AI, a lot of people are doing this 👇 You take a long prompt, feed the entire thing to AI at the beginning of your interaction, and spend time going back and forth with AI trying to get the outcome you want. (I'm not coming for you Karli, you are exceptionally good at this, but ICM will make your outcomes exceptionally better!) What is different about AI and prompting with ICM 👇 You take that same really long prompt and instead of giving it to the AI all at once in the beginning, you break it into steps, and each step gets its own folder, each folder gets its own piece of your large prompt, just 1 step from it, and you ordered the folders by when the steps happen in the workflow. You got it? Good 😊 ❤️‍🔥 -------------------Still a bit unclear, let's bake a cake. 💡 Here's an analogy I have success with (I picked this up way back in my VB programming days): Imagine teaching AI to bake a birthday cake. 🎂 The way most people do it: 👇 One giant prompt. "Bake a cake, here's the recipe, the frosting technique, the decorating style, the candle placement..." Then they hit enter and wait. The AI is juggling 40 instructions at once, and by step 30 it's forgotten step 3. The ICM way: 👇 Break the prompt/workflow into steps. Each step gets a folder. The first folder is your first step. Then you point the AI at the first step, and the first step is 00-birthday-cake: (Point the AI just means giving access to the folders to the AI, through uploading or direct local access, don't worry about that now, let's keep building our cake.)

Glad you made it in. Before you go anywhere else, work through the steps below. They will get you set up and ready to start. ✅ Introduce yourself in the comments. Tell us what you do and why you are here. ✅ Watch the Getting Started overview 📚Navigating The Course - Getting Started · Clief Notes ✅ Start with the Foundation course 0.1: Where All Of This Leads - The Foundation · Clief Notes ✅ Fill out your profile so people know who you are ✅ Join the next competition ⭐ Competitions Mega Thread - Getting Started · Clief Notes ⭐ On Competitions (and why I love them) We host a competition every two weeks. These are some of the most powerful places to learn and build here. Also Cash prices (often over $200) for the winners. Learning how to do something is one part of it. The real learning starts when you put it to work. That is what the competitions and the build sessions are for. On top of this they act as a portfolio a place to not just show us but show others (clients, bosses, your best friend) what you have been building and that you really CAN build. In order to win a competition you must be a paying member (It takes me hours to review submissions sometimes days. But if you win ONCE you can pay for a whole year of membership so I think that's only fair!) Watch the videos, then go make something.

Having Claude write powershell scripts feels like a superpower in a way. I'm sure I'm not the only or first person to do or mention this here, but it's cool to me so I thought I'd share it. Am working on a project that has a ton of knowledge files with a strict repeatable format. As I go along I keep tweaking and changing things and pulling files out of folders and grouping them differently and having claude update my router file every time (sometimes doing batch changes too) felt kind of clunky. I'm sure it wasn't too token intensive, but I felt there was a better way. So I had Claude write up a powershell script that runs after every commit to github, scans the entire folder structure, updates the router file with any additions, subractions or changes. Fully automated, saves some tokens I'm sure. Small personal win for me

Most people think AI messes up because the prompt was unclear. But sometimes the prompt is fine. The problem is that your business language is unclear. One word can easily mean FIVE different things. “Client” could mean a person, a company, an account, a project, a payment record, or someone in your CRM. “Content” could mean an idea, a draft, a final post, a campaign asset, or a deliverable. AI will follow whatever meaning is implied in the moment. That is where things get messy. Duplicate files. Wrong folders. Confusing outputs. Systems that make sense once, then fall apart later. A simple way to prevent this is to create a TERMINOLOGY file. Think of it as the shared dictionary for how AI should understand your business. Inside it, define: - The words your business uses - What each word means - What each word does not mean - Which terms are approved - Which terms create confusion - Examples of the right and wrong usage This is especially useful before building SOPs, automations, dashboards, folders, workflows, or AI agents. Because once the language is clear, AI has a much better chance of organizing, writing, and reasoning the way your business actually works. What is one word in your business that AI keeps misunderstanding?