Hey everyone, pointing me to an existing thread is enough if this was already asked. I am confused about how ICM connects to Grok Bot and Hermes Agent bots. I went through the course and talked it over with an agent, but I seem to be missing something foundational and I keep going in circles. My concrete question. I want one orchestrator in Hermes Agent, with specific workflows running on different subscriptions. I have a few of them. Writing on GLM 5.3, coding on Grok 4.7, that kind of split. With a single agent per subscription the ICM setup is crystal clear to me, I have built the folders and seen the results. But I have no idea how to wire it that way inside Hermes Agent. Related confusion. What is Grok Bot versus Hermes Agent bots. Is it an alternative to ICM, a part of it, or something done differently. And what is the point of multiple agents talking back and forth. I genuinely try to understand this and I would welcome any help. Thanks.

Someone posted a few days back that they were still confused about ICM — like, actually confused, not "give me the elevator pitch" confused. Got me thinking. That's what got this made. There are many resources here, though I would ensure one also went through and built a "folder structure" like Jake shows in Foundation 2. Once you build, it can support you along your learning and building process. This short video was inspired after I had an epiphany about playing with LEGOs as a child. Not because ICM needs a gimmick. When something isn't clicking, changing how you're looking at it usually does more than saying the same explanation louder. The video's really trying to land one thing: think about it in pieces, not all at once. Two central ideas specifically, before anything else matters. One stage, one job. A folder should do exactly one thing. Plain text as the interface. Everything's just files. Open any of it in a plain text editor and you understand exactly what's going on. That's not an accident. It means you're never stuck if a tool changes, and it means anyone — you, a teammate, an AI — can pick it up without needing the same software you used to build it. Those two concepts, more than the rest, are the ones worth sitting with before anything else clicks. If you want the fuller version of how I simplified it — what the actual folder structure looks like, worked through with a real example — there's an article that goes further than the video does. Article: https://thequietai.com/writing/icm-as-lego What part of ICM is still fuzzy for you?

I'm curious: who here is using Obsidian for their knowledge management and integrating it with an ICM setup? I'm looking to combine my local markdown vault with AI agents to build a permanent context layer, and I'd love to get your thoughts: 1. How do you integrate them? (e.g., using the MCP filesystem server, specific Obsidian plugins, or custom local scripts?) 2. What is your honest opinion on this? Is it seamless, or does the AI get bogged down once your vault grows and files get messy? Any tips on folder structures (like separating an /Inbox from a /Core folder) or system prompts that keep the agent from messing up your notes would be highly appreciated. Thanks!

1. Go check out 📚Navigating The Course to see how to get around and what's here. 2. Start with The Foundation. 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 join in on our Biweekly competitions and win some real cash. ⭐ Competitions Mega Thread 5. If you are wanting to dive into the masterminds, grab all the past templates, artifacts and resources. Upgrade and head into the The Vault for Premium and The Drawing Room (VIP) for VIP 6. Post your work. Ask questions. Help others when you can. What are you here to build?

It’s live. Starting today, everyone in Clief Notes has access to the new Clief Notes AI. The easiest way to use it? Don’t overthink it. Ask it the question you would normally ask me. “Where should I start?” “What should I focus on next?” “Where did you talk about [topic]?” It’ll use what’s already inside Clief Notes to help answer you and point you toward the right lesson or resource when there’s something worth going deeper on. The goal isn’t to give you another AI tool to play with. It’s to make everything already inside this community easier to actually use. If you want Access to it Comment "READY" and we'll send you access to it!