My setup now is pretty simple: claude.ai for working through problems, drive.google.com for files I actually want to keep, and floment.ai for the projects and tasks I'm actively executing. Models will change, prompts will change, probably half my current tools will change too. But having a clear place for knowledge vs actual work feels way more durable. Where does your useful AI output go after the chat is over?

Hey Clief Notes fam! 👋 I'm Amy Johnson and I'm happy to be here. 🙋 A little about me: I am a franchisor of a donut business. I have over 50 franchisees and am working on building AI systems for all of us to make business easier. 🎯 My current goal: Building an AI Franchise Kit Biggest Struggle right networking and finding people who can talk ICM with.

I don't want a progress percentage today. I want to know what's actually changing. If you've been working through Building Your Stack, what is one decision you've made because of it? - Maybe you added something. - Maybe you removed something. - Maybe you realized part of your current stack makes absolutely no sense. 😂 Whatever it is, post it below. What did Building Your Stack make you rethink? And if you've been flying through the lessons but skipping the quizzes or accountability posts... Go back. Those are there to make sure you can actually explain and apply what you're learning rather than just consuming it. Drop your biggest realization below. 👇 And keep going. New roadmap next Friday, September 25th.

I read Jeff's post about coming up with ideas and bouncing them off of Claude and blinked really hard several times. His idea is clever and he has a neat Remotion video to show it. My problem sits adjacent to this. I can't wrangle all the ideas that my brain produces... every single day. It's insane. I think I have ADHD and OCD combined. I'm everywhere all at once and obsessing over every next cool concept. Granted, some of the ideas are lame (plenty of them in the archives), but quite a few are really good and should be pursued. The problem is that there is only ONE of me. How do you decide what is worth pursuing? Do you use any kind of metrics? Do you bounce your ideas off of someone else? Do you wing it? (my current approach) Or does it come down to how much money an idea could make? How much it would cost to build? How quickly you could ship it? For many of us there is an added layer. What can I build that will genuinely make a difference for someone else? That question ends up carrying a surprising amount of weight for me. An idea can be profitable, technically interesting, and perfectly viable — but if another idea has the potential to solve a real problem for someone, I have a hard time ignoring it. Which, unfortunately, does absolutely nothing to solve my too-many-ideas problem. So I’m curious: how do you decide which ideas earn the right to become a real project and when to just say, "No"? Jeff's post: https://www.skool.com/cliefnotes/youre-not-out-of-ideas-youre-out-of-someone-to-say-no-to

For a long time, my biggest AI problem was not a lack of models. It was fragmentation. My knowledge was scattered across ChatGPT, Manus AI, Perplexity, Claude Code, Hermes Agent, and other systems, with each one effectively operating as its own island. I had tried to unify everything inside an Obsidian vault using a Karpathy-style flat wiki structure, but it was still fundamentally static knowledge management rather than a true contextual memory system. Then my CMO told me, "John, you should watch @Jake Van Clief 's video. He explains how to do this simply." I watched one ICM explainer, immediately went down the rabbit hole, joined this community, read the ICM paper, and started building. 📚 And for context, I'm a doctor with no coding background. 😂 I started vibe coding because I kept running into problems I wanted to solve myself, and I found that iterating directly with AI often got me much closer to the system I actually had in my head than trying to explain every little requirement to someone else. 🧠 The architecture The difficult part was that I was not starting from scratch. I had multiple existing knowledge stores to reconcile, and I wanted the same ICM to serve two completely different agent harnesses: Hermes Agent, running on a VPS so I can access it from anywhere, and Claude Code, running locally on my Mac. But Hermes itself was not just one simple agent session. On the VPS, the same Hermes engine runs three persistent profiles: my main Hermes environment, a separate staff profile connected to my assistants through Slack, and an ICM pilot profile. On top of those, Hermes can dynamically spin up multiple temporary sub-agents for parallel work. Those environments can reach Hermes through several independent paths: my Mission Control interface, Slack, mobile/web access, n8n automations, and a live two-way bridge between Claude Code on my Mac and Hermes on the VPS. So the real problem became concurrency. I effectively had multiple Hermes personas, execution paths, bridges, users, automations, and temporary sub-agents all capable of interacting with the same underlying memory architecture.