I've heard a few people in High Tea and the community say the concepts aren't fully clicking yet — the videos make sense, but don't stick. Thought I'd share something I do, not just with ICM but with almost anything I'm trying to understand better. I load the source material into NotebookLM — research papers, videos, transcripts — and generate an Audio Overview. Then I listen while I'm driving, mowing the lawn, or in the shower. 😊Not as a replacement for reading it. As a way to let my brain chew on the ideas without being at a screen. I do it with my own podcast, too. Before an episode, I'll load my production notes and prior transcripts into a notebook and generate a conversation about the topic. Hearing two voices debate the ideas out loud does something for how I think about it later. The topic solidifies before I have to articulate it. For ICM specifically: Jake's videos + the research paper as sources, generate a podcast episode, put it on while you're doing something with your hands. See if it lands differently than sitting at your desk reading. Does anyone else use NotebookLM's podcast feature to learn? Or found other formats in NotebookLM that help — study guides, FAQs, anything?

This post is not for the ICM pro, there will be no talk of gates, scripts, or orchestration! This is for the person just starting out! @Karli Rosario Yes, I mean you! (And anyone else who may just be starting out with ICM) Seriously, I'm glad you found ICM. Let me give you the simplest version of it I know. ICM is a system of structured folders. Yes, the same folders you have been using on a computer for most of your life. The ones you stored photos in, & pirated music from Napster and LimeWire. That's it. I will take you through the process below. When working with AI, a lot of people are doing this 👇 You take a long prompt, feed the entire thing to AI at the beginning of your interaction, and spend time going back and forth with AI trying to get the outcome you want. (I'm not coming for you Karli, you are exceptionally good at this, but ICM will make your outcomes exceptionally better!) What is different about AI and prompting with ICM 👇 You take that same really long prompt and instead of giving it to the AI all at once in the beginning, you break it into steps, and each step gets its own folder, each folder gets its own piece of your large prompt, just 1 step from it, and you ordered the folders by when the steps happen in the workflow. You got it? Good 😊 ❤️‍🔥 -------------------Still a bit unclear, let's bake a cake. 💡 Here's an analogy I have success with (I picked this up way back in my VB programming days): Imagine teaching AI to bake a birthday cake. 🎂 The way most people do it: 👇 One giant prompt. "Bake a cake, here's the recipe, the frosting technique, the decorating style, the candle placement..." Then they hit enter and wait. The AI is juggling 40 instructions at once, and by step 30 it's forgotten step 3. The ICM way: 👇 Break the prompt/workflow into steps. Each step gets a folder. The first folder is your first step. Then you point the AI at the first step, and the first step is 00-birthday-cake: (Point the AI just means giving access to the folders to the AI, through uploading or direct local access, don't worry about that now, let's keep building our cake.)

Hi guys! I am in a doozie, got about 700 pages of text I am trying to parse and extract knowledge from. Right now: - Corpus: hundreds of messy, multi-topic text pages where useful knowledge is scattered throughout and topics drift. Pages are grouped into "review packages". - Packaging: each is turned into a compact "bundle" + manifest, then handed to an LLM extraction worker that reads only that bundle (no raw DB access) - Extraction: the worker writes a standardized "lean note" — a TL;DR - Compilation: notes are merged into long-lived, topic-based knowledge files ("epics") via targeted inserts, with a processed-index ledger for idempotency and capped epic fan-out so facts don't get duplicated TLDR I got 700 pages of text I want summarized, and getting through 10% of it took two session limits of my Codex pro plan. Any ideas, tools to help? Thanks fam!

Twenty-four days ago I posted about Jake's folder system video. This is what happened next. Same foundation — markdown files, orchestration prompts, clear roles. I just kept building. Fifteen named specialists. Each one with a soul file, guardrails, and a playbook. Duke orchestrates. Cash writes. Trace pulls the data. Hank runs the financials. Clint handles the MCP integrations. Behind each one is either a human counterpart doing the real work alongside them — or a role I can't afford to hire yet. Katie who's been with me for 18 years, now has her own orchestrator running the same system. Twenty-seven client folders. Twelve live MCP integrations. One shared repo. The folder system isn't replacing my agency. It becoming my agency. Jake gave me the unlock. This is how it's going.

Fable made me start using Codex. Well, actually Claude, Codex, Kimi and MiniMax M3 together. Not because Fable is weak. Because it is the first model strong enough to run the others properly. The shift: stop asking which model is best. Start matrixing every model to the task it performs best at. - Claude (Fable): the seat. Orchestration, judgement, context. - Codex: the coding powerhouse. - Kimi: long-video understanding. - MiniMax M3: the looping build system. For the first time the multi-model workflow is truly effortless. Local models included. It all just works. The model at the top is not doing the work. It is routing it. All of it, loops included, lands in an ARI-OS update. The intelligence is the routing, not any single model. Read the deep-dive: https://aris-space.com/documents/workflows/fable-made-me-start-using-codex [[EDIT]] I wanted to just clarify what I said of in this post by saying that the infrastructure I've built with Fable and the way that it can solve problems when you give it a tight brief and the thoroughness of the model allowed me to create a seamless system. But ultimately, every step of this has been tiered with the model we had. //A<3