Step-by-step interactive guide from idea to output. Design an ICM workflow alongside Maya, one decision at a time, and watch a messy process become something an AI can run again and again. Right now, Maya has to try to remember what needs to be done and where each piece of information is kept. She needs a better solution. https://claude.ai/public/artifacts/7c9618f4-8324-4048-902c-cbcf77c9c102 Let’s build one with her. 😀

most of my work is done in Claude Cowork sessions. I almost never use Claude code (CLI) and the challenge I have is that regardless of what I’d like to do unrelated to my work, Claude always defaults to my work profile. So if I use a Claude code, create a folder just for the specific unrelated search or idea, my .md file should be delivering all that knowledge about me separately with a proper context! Am I thinking correctly?!

📋 The brief I wanted to run a basic data exercise: take one dataset, organize it three different ways, and measure what each structure actually costs an AI agent to search. A controlled comparison I could point to instead of arguing about it in the abstract. Three versions of the same data: 1️⃣ Raw — the dataset exactly as downloaded. One file, no structure, no metadata. 2️⃣ ICM — files and folders. A mechanical breakdown into a directory hierarchy, the kind of structure I've been building into ICM workspaces for a while now. 3️⃣ "Second Brain" — an Obsidian-style vault. Same content, but with per-item notes, cross-linked [[wikilinks]], character/theme pages, the whole living-notes treatment. Then I built a small tool that fires the same question at all three, using a real agent for each run (not a canned lookup), and logs tokens, time, and cost per stage. Point the same question at raw, ICM, and Obsidian, and see what each structure actually buys you. 📚 Why I chose Shakespeare I needed something big enough to be a real test, public domain, and — critically — already broken down at a fine grain (act, scene, sonnet) so I wasn't inventing structure that wouldn't exist in a messier real dataset. I looked at the U.S. Code first. It's the right shape (title → chapter → section mirrors book → chapter → verse almost exactly), but it's enormous. Shakespeare's complete works are a fixed, known-size corpus (5.4MB, Project Gutenberg, public domain) that will never change, never need re-downloading, and never go stale. That "always useful" property means this test is reusable as a reference point for other structure comparisons later, not a one-off. 💰 A bit on the cost of setting up The ICM layer cost almost nothing to build. It's a mechanical script — split on ACT/SCENE headers, extract speaker names by regex, write files. No model calls. 1,579 files, and the token footprint came out at 1.01x the raw file's size. Structure that's this close to free is easy to underrate.

Alright, here’s what we’ve been sitting on. We’re past 2,700 posts and 40+ lessons now. The number one thing we hear on Wednesday onboarding calls is some version of: “Where do I start?” “What should I do next?” “Did someone already answer this?” Fair. There’s a lot in here. So we’re bringing in an AI trained on the Clief Notes library. Every lesson. Every Afternoon Tea. Every High Tea drop. It actually knows what’s in here. 🧭 Tell it what you’re stuck on, and it points you toward the right lesson or drop. 🗺️ Tell it where you’re at, and it can help you figure out what to focus on instead of just telling everyone to “start at The Foundation.” 🔍 Ask it about something we’ve covered before, and it helps you find it without scrolling through months of content. And when we launch it, everyone gets access. More on that very soon.

I automated my LinkedIn pipeline so the posts are basically a byproduct of work we were already doing. Here is how it works: - Everything gets captured raw → Meeting transcripts, voice notes, messy half-thoughts: they all get dropped into one inbox folder. Zero formatting, zero cleanup. Capture first, structure later. - An AI agent parses the inbox → It reads every drop and sorts what it finds into people (CRM update) , tasks, decisions, ideas, and content angles. Every single meeting gets asked " is there a LinkedIn idea in here?" ( I have flows for what is considered "content" , aligned with the brand) - I approve every item → The agent proposes, I decide. - Approved ideas land as drafts from a template, each one linked back to the meeting it came from. - The words come from a voice fingerprint → I fed my own transcripts into a profile of how I actually talk, so the drafts sound like me. - Once a month I sit down with the agent for a proper conversation → It brings what the industry published that month and what our own meetings taught us, and together we draft the company posts. - I edit, pick the visuals from a small set of templates, and schedule. The end goal: capture once, decide once, and let structure do the rest. If you want to build this yourself, start with the inbox. One folder where everything raw lands. Everything else grows from there.