So you know: All of this was by learning the free courses off Clief Notes A few weeks ago, I started building something small: a tool to help my girlfriend study for her psychology degree. She has ADHD, and most study platforms are built for people who don't have it — walls of text, no structure, no immediate feedback. She'd open a PDF, read three paragraphs, and lose the thread entirely. Not because she wasn't trying, but because nothing was built with her brain in mind. So I built Acarito. It started as a love gesture. It turned into a full platform. What it actually does Acarito is a free educational tool aimed at psychology students, though the core idea generalizes to anyone who learns better with structure. It's not a static library of notes — it adapts. It watches where you get things wrong, adjusts the material to fit your pace, and reshapes itself around how you actually learn rather than how a textbook assumes you learn. It currently has five modes: - "Quizzes" — generate a personalized quiz on any topic, one question at a time. - "Ensayos" — guided essay writing with feedback as you go. - "Lectura Guiada" — guided reading broken into digestible chunks, with questions woven in instead of dumped at the end. - "Audio to Notes" — turn spoken content into structured study notes. - "PPT to Notes" — same idea, starting from a slide deck. The design principle underneath all of it: one question at a time, short instructions, immediate feedback instead of a wall of text you have to hold in your head. That's not a UX preference — it's the whole point. For someone with attention deficit, "immediate feedback over eternal paragraphs" is the difference between finishing a study session and abandoning it ten minutes in. Building it I built and iterated on Acarito with a lot of help from AI pair programming — actually watching the tool understand the shape of the project well enough to suggest its own architectural and design improvements was, honestly, the most interesting part of the process. It's still evolving. I'm currently working through a round of visual polish and expanding the gamification side — more achievements, more avatars, more personality.

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!

I explain the details about it on today's high tea . I built a Claude skill that turns a process, an idea, or a messy folder into an ICM workspace. The folder structure does the orchestration. Numbered folders carry the order, the hierarchy scopes context, and plain markdown files hold state. One agent walks the right files at the right time and does the work a multi-agent setup would. Repo: github.com/RinDig/icm-architect 📦 What it does Two modes. 🔨 Build. You describe your work and it pulls out the structure already sitting in how you talk about it. The stages, the points where you stop and check, what stays the same every run versus what is new. Then it picks one of five proven forms and scaffolds the smallest workspace that carries the job. ♻️ Restructure. Point it at a folder, repo, or vault you already have. It reads every file, sorts each one by role, shows you a migration map, waits for your yes, then moves and checks the result. 🧩 The five forms Pipeline, umbrella, record library, knowledge bundle, context map. They mix and nest, so most real workspaces use more than one. ✅ The walk test Every result gets checked cold. An agent with no memory has to open the root, find its way, act, and report status from the files alone. If it can't, the structure gets fixed until it can. ⚙️ How to use it You can honestly just tell claude to download it from the link, but if you're using codex or something else it will just have to restructure the claude.md to agents.md Or if you want to do more Hands-On install Claude Code: drop the folder in ~/.claude/skills/icm-architect/, then say "ICM this" or "build me a workspace for X." Claude apps: zip the folder and upload it under Settings, then Capabilities. Fork it, break it, tell me what you built. 👇

After watching the video and reading the companion: Vote below, then tell us in the comments: what is one task in your work that feels robotic? If AI handled it tomorrow, what would you do with the time?

After watching the video and reading the companion: Vote below, then tell us in the comments: where are you on "raise the bar" in your own work or teaching?