Hey folks 👋 Packaged an icm-builder skill — helps scaffold projects, generate routing tables, and track what needs updating when you change a contract or reference file across stages. GitHub: https://github.com/carloswecare/icm-builder WARNING: Not a substitute for the courses and fundamentals — just a helper for when you're already building. First attempt, open-sourced on GitHub. Would love PRs, issues, or a "you're solving the wrong problem" if that's the case 😄 — Carlos

Hey everyone! 👋 I’ve been spending a lot of time thinking about how we build, and Loop Engineering have been popping up lately... I’m really curious to see how you all view the relationship between Loop Engineering and ICM. I’d love to get your quick thoughts on a few fundamental questions: 🤝 Do they naturally intertwine? To me, Loop Engineering is all about how the agent acts—creating autonomous cycles of execution, verification, and self-correction. On the other hand, ICM is about where the agent lives—using transparent folder structures and markdown files to manage context. Do you see them as a natural duo? Does a great autonomous loop need a clean file structure like ICM to keep from losing its mind? 🏗️ Can Loop Engineering be the framework FOR ICM? Instead of looking at them as separate tools, can we use the concept of Loop Engineering as the actual structural framework to drive an ICM workspace? For example, using the agent's looping logic to systematically move files from a 01_inbox to a 02_processing folder? Or do you think keeping the looping logic and the context methodology strictly separate is a better approach? 🤷‍♂️ Or are they just for completely different use cases? Are we trying to force a connection that shouldn't be there? Do you use Loop Engineering for heavy task automation, but prefer to leave ICM strictly for human-in-the-loop, highly readable research workspaces? 💬 What’s your take? - How do you define the connection between Loop Engineering and ICM? - Are you combining them in your current builds, or keeping them completely separate?

Earlier this week I confessed in here that I'd scoped about $60K of work for a client who paid me under $20K, and that she'd capped it off by sending me a "you didn't deliver" email at 11pm. A bunch of you commented. Some to encourage me. Some of you, I'm pretty sure, just pulled up a chair and grabbed the popcorn. Either way, you wanted to know how it ended. So here's the sequel. Nobody died. I'll lead with that. ------------------------------------ What I walked into ------------------------------------ Monday she blew a gasket. Strongly worded, escalated, the kind of email where you can feel the caps lock breathing through the screen. I did not respond like a calm professional. I spiraled. Half of me concocted a plan to pull up every receipt and go twelve rounds. The other half, the half I'm less proud of, came up with a half-baked plan to just roll over, apologize for stuff that wasn't even mine to apologize for, and turn myself into a doormat so the discomfort would go away. Running on no sleep, nursing a bruised ego, two bad plans and the stress of not having a newborn baby in the house yet... (wife's at 41 weeks, if she hits 42, she's gonna make that baby come out.) ------------------------------------ Then my COO blew up my whole game plan ------------------------------------ The day before the call, I got on with my fractional COO and word-vomited both of my terrible plans at her. She shut them both down. Didn't tell me to fight. Didn't tell me to fold. She handed me an actual plan. First, homework. Go build a point-by-point breakdown of all three agreements. Every deliverable, what's done, what's not, the percentages, and a whole separate column for the work we did that was never even in the scope. That document was her idea, not my heroic late-night brainwave. I didn't have it. She told me to go make it. Then the move. Don't walk in defensive, don't hand her the wheel. Lead with the full picture, so much clarity up front that she can't steer the thing somewhere sideways. She doesn't actually know what a finished marketing blueprint is supposed to look like, so I shouldn't be handing her the power to define "done." Show the whole list first, then talk.

That is the whole thesis of the thing it documents. The docs were built the way everything here gets built. I directed background workers and reviewed what came back. The method has a shape you can learn in an afternoon. You sit in one seat and run a loop. Brainstorm the outcome, plan the steps, dispatch the work, review what returns, ship what passes. You keep the judgement steps. The doing runs in the background, with or without you at the desk. The rule under all of it is short. Direct, do not do. The piece I lean on most is a memory that lives on my own machine. It remembers across sessions, so a new chat starts from what I last decided, not a blank page. Local-first. Nothing leaves the machine. This is not magic. Nothing builds itself, and I review every result. The discipline is judging, not doing. Version 2.0.0 is open-source and sits on top of Claude Code. The difference today is that the method is written down, so you can learn it instead of reverse-engineering a repo. Overview: https://www.aris-space.com/documents/ari-os/overview Install: https://www.aris-space.com/documents/ari-os/install Repo: https://github.com/PUSHINGSQUARES/ARI-OS That is the line under all of it. AI accelerates, it does not generate. So here is my question. What is the one task you still do by hand that you should be directing instead? //A<3

1. Watch the intro video and introduce yourself in the intro post here 2. Start with The Foundation (free course). Concepts, folder architecture, prompting framework. Everything else builds on this. 3. Check in at the bottom of each lesson. Polls, discussion posts, other members working through the same stuff. Use them. 4. When you're ready to build real things, move to Implementation Playbooks (Level 2). When you're ready to build your own tools, Building Your Stack (Level 3). 5. Post your work. Ask questions. Help others when you can. What are you here to build?