Before ICM I called it a "Prompt Modifier". At it's core, a markdown file, instructions to tell AI how to operate with the task at hand. This isn't building agents, it's the how, with a handful of instructions. At a high level, the Orchestrator manages handing off work to subagents. Built to be LLM agnostic, drop in to any chat, point to the file, or wire it into ICM with a trigger when needed. The main chat stops doing all the work and instead organizes, delegates, and manages communication. I've seen this catch a lot of errors, assumptions and hallucinations. Plans are better. Execution is improved. This also allows higher level model usage, without all the token costs. I'm usually using Opus, on high effort. --- An analogy I used when sharing with my brother-in-law, military vet. Think of Claude like a Team Leader. - Claude manages the agents instead of doing the work himself - A "research agent" is sent out to get the information and bring it back - Claude writes up the assignment, then sends a "worker agent" to do it and report when it's done - Then a "verification agent" checks that the worker actually did the job right - If it didn't, Claude keeps working the agents until it passes So if you're not getting what you want, talk to the Team Leader and tell him to fix his sh*t. --- I've used a version of this over the last 3+ months, it has helped cut down on token usage, while getting what I need done quicker. Building this into my ICM system has been a force multiplier. If you use this I would love some feedback to add to my backlog, still iterating on it. *Attached slide with some additional detail.

I had the privilege of attending the Ai4 conference in Vegas this week, and boy am I glad I joined this community before going. It felt extremely good sitting in the technical sessions, keynotes, and vendor fireside chats with the prior knowledge Jake and this community teach and preach. You can only imagine how nearly every booth had the word "AGENT" slapped on it, but it was fun picking their brain and occasionally dropping "oh interesting... have you read Jake Van Clief's research paper?" The most validating part, and it came up over and over, was CFO, CTO, and C-suite level folks harping on the fact that you can no longer just roll out "AI" with no plan. You need to understand usage, and most importantly you have to understand and track the ROI, or no business leader is going to feel confident making the investment. The hardest part for most businesses seems to be mapping out their own processes and the steps to get there. That makes implementing AI incredibly difficult, because they don't understand their true business processes to begin with. Which is exactly why I love the ICM process. It forces you to work out what it actually takes to complete a task from start to finish, and to map that out on purpose. Cheers and happy building everyone!

Tell us three things: 1. What you do (job, industry, student, career-changer, whatever) 2. What brought you to Clief Notes 3. One thing you're trying to figure out right now related to computing or AI I'll respond to every single one. And read each other's intros too because the person who's stuck on the same problem as you might already be in this thread. I'll go first I am Jake, I have been working in tech for 15 Years, building with Generative AI for 3 Years straight now! Excited to teach and learn! That's it. Simple, scannable, gives you data on who's joining and what they need, and keeps the feed clear for content that retains people past week one.

I explain the details about it on today's high tea . I built a Claude skill that turns a process, an idea, or a messy folder into an ICM workspace. The folder structure does the orchestration. Numbered folders carry the order, the hierarchy scopes context, and plain markdown files hold state. One agent walks the right files at the right time and does the work a multi-agent setup would. Repo: github.com/RinDig/icm-architect 📦 What it does Two modes. 🔨 Build. You describe your work and it pulls out the structure already sitting in how you talk about it. The stages, the points where you stop and check, what stays the same every run versus what is new. Then it picks one of five proven forms and scaffolds the smallest workspace that carries the job. ♻️ Restructure. Point it at a folder, repo, or vault you already have. It reads every file, sorts each one by role, shows you a migration map, waits for your yes, then moves and checks the result. 🧩 The five forms Pipeline, umbrella, record library, knowledge bundle, context map. They mix and nest, so most real workspaces use more than one. ✅ The walk test Every result gets checked cold. An agent with no memory has to open the root, find its way, act, and report status from the files alone. If it can't, the structure gets fixed until it can. ⚙️ How to use it You can honestly just tell claude to download it from the link, but if you're using codex or something else it will just have to restructure the claude.md to agents.md Or if you want to do more Hands-On install Claude Code: drop the folder in ~/.claude/skills/icm-architect/, then say "ICM this" or "build me a workspace for X." Claude apps: zip the folder and upload it under Settings, then Capabilities. Fork it, break it, tell me what you built. 👇

We just shipped the alpha of Ledger 📋 —https://ledger.eduba.io the talent platform we've been building on top of this community. Free for VIP and Premium Members. Here's the idea, plain: every other job board matches on a resume. Ledger matches on ICM. Every candidate in there has been through the methodology you're already using here — that's the whole point. Companies aren't guessing whether someone "gets it." They know it going in. 🎯 It works kind of like a job board, but more anonymous — right? 🕶️ Employers see an anonymized profile: skills, bio, portfolio, a short video intro if you want one. No last name, no email, no current employer. Every conversation runs through the platform's relay instead of real inboxes, so nobody's exposing contact info before they're ready. Two doors in: - 🏢 Company hiring — freelance or full-time — sign up and get access to a pool of people who already speak ICM fluently. - - 🙋 Candidate looking for work — freelance or full-time — list yourself. Takes a few minutes: profile, skills, a short video if you've got one. We're vetting both sides before anyone gets full access — companies and candidates — so the quality holds up on both ends. ✅ That means it's not instant approval; you might wait a beat while we look at it. Bear with us there. It's alpha 🧪, so: things might be rough around the edges, we're watching it closely, and if something breaks or feels off, tell us — that's exactly what this stage is for. Be nice to us and we'll be fast about fixing it. 🙏 Sign up: https://ledger.eduba.io 👇