I’m building out an ICM architecture for a PE firm catered towards making due diligence easier and more efficient, I wanted to reach out and see if anyone here is in that space or worked close to it and even any tips you’d have for the correct folder structure/processes. I know a bit but knowing more on your guys’s process would be unreal thanks!

I've been building my second brain for a a couple of weeks now. I'm trying to use it to help me be more organized in my business but I feel like I'm getting more distracted. Does anyone have some tips on this situation? I'm sure it's happened before to somebody else.

After months of building, I decided to finally separate my dashboards. A clean cut between the ones that are shared, the ones I work with, and the one that is meant to oversee the systems that power it all.. I'm surprised by how much it revealed about the underlying system. Lots of it was cleaned up in a follow-up audit. Processes with where nothing reads its output were retired. Processes that had no clear reason for being were investigated and either patched or retired. But the bigger reveal at the moment is how unmanageable it all is.. or how unstructured rather. Each subgroup is sort of like the workfolder managing a folder... and the folders, well they're just not well defined. It's all ICM but it lacks structure and separation - so that the visual clues and actually inform about the health of the processes beneath it. This is how it looks today.. Tomorrow it should be a little more clearly defined. How do you keep tracking of all of your scheduled tasks and automated processes?

Hey Clief Notes fam! 👋 I'm Yasuko (pronounced yas-ko) and I'm inspired to be here. 🙋 A little about me: I'm a techie (AI, networking, cyber, infosec) and an identity level transformational coach 🎯 My current goal: Levelling up my business to do more with less of me. 💪 What I'm currently building/working on: I'm busy converting my AI course for non techie female founders into an ICM structure and use skills rather than chatbots so they can use their own AI to build their ICM and agents. Building a dashboard and content app that creates content that is so authentically you. 🤔 My biggest struggle or question right now: How to structure the interview questions to go into the content app to get the depth of the person using it. How to use JEV to classify the different content cards which the app is built on to create content. And after the last Afternoon tea call when Jake talked about JEV, I managed to get into transform.ai by completing the questionnaire they prompt you with, yeay!🙌 Let's get it! 🚀

Files carry the words The next agent reads the task No more copy-paste I’m a novice at building software and learning as I go. I run a CNC workshop, and on a long project I had Claude Code doing the work and Codex independently reviewing it. The reviews were useful, but I was copying every handoff between them. So I built Looper. One agent leaves a request in a small folder of readable files. A second agent answers it. If that run fails, the request stays waiting. A fresh session can read the folder and pick up from there. It started with code reviews, but I’ve since used the same handoff for testing, research and getting a second agent to check things the worker couldn’t. Claude and Codex have taken both roles. I’ve also run a local Qwen model through OpenCode and Ollama for a review. That local route has only had limited testing, but it showed me the point: the files hold the job, so Looper isn’t tied to one model or agent runtime. The approach came from what I’ve learned about ICM here, especially the work of Jake Van Clief and David McDermott. The sessions can come and go; the folder keeps what they need to continue. And yes, Looper is partly a nod to the film. During development I jokingly called it Bruce. A job arrives, someone deals with it, and eventually the loop closes. I’ve found it genuinely useful and have made it public and MIT licensed. If you’re carrying messages between agents, or want another agent to check work without losing track of what’s been reviewed, give it a try. It works with plain files, and there are optional helpers to automate the handoffs. https://github.com/shedstalker/looper I’d love to hear what you use it for, what breaks, and what you’d simplify.