A question for all the builders out here. When building your ICM structures, I'm keen to find out who among you uses ChatGPT, who here uses Claude, and what you feel is the best one. What are the alternatives to look at, like Grok, for example?

Most free AI courses are a teaser. A few videos. Then a paywall. Anthropic’s Academy is not that. Thirteen courses. Listed at $0. Built by the team that ships Claude. No subscription. No upsell after the last lesson. That is worth an evening. Not because a certificate will hire you. Because the work teaches how the model fails, not just how to chat with it. If you just landed in Clief Notes and you still treat Claude like a smarter search box, start here. You do not need to be a developer. You do need one loop you can finish. Three tracks - AI Fluency. How to think with the model. Where it lies. Where it helps. Everyone starts here. - Developer. API, Claude Code, MCP. User to builder. - Specialized. Students, educators, nonprofits, AWS, Google Cloud. Only after 101. The instinct to kill: skipping Fluency and jumping to agents. That instinct is wrong. You will ship slop faster. Where to start tonight New to AI: Claude 101, then AI Fluency: Framework and Foundations. Want to build: Building with the Claude API, then Introduction to MCP. Education or nonprofit: Claude 101, then your specialized course. Most courses are 1 to 4 hours. Two in a weekend is enough. How you get in 1. Open Anthropic Academy on Skilljar. 2. Make a free account. 3. Pick a course marked $0. 4. Finish the lessons. 5. Download the certificate if you want the paper. https://anthropic.skilljar.com/ The certificate is a bonus. The useful part is a working sense of when Claude is wrong. That is the skill that compounds. Do Claude 101 this weekend. Bring back one thing that broke your current prompt habit. Drop it under this post. I want the boring version, not the certificate screenshot.

It seems like one of the big advantages of ICM is that it can be used with any model. How are you leveraging this? If you are using multi-models what systems are you using and how are you deciding what is being fed to which model? I'm asking because I'm very interested in Qwen and trying to figure out how to incorporate that as a local AI.

I’ve just started my journey with CM, and I’ve been loving the learning. I have experience in building automations and agentic flows in n8n, but struggling a bit with wrapping my head around ICM. Can you still give an agent access to tooling i.e. Google docs etc? And can you run automations through it like you do with n8n? Or does ICM fit on top of all that and n8n etc can be used to execute automations still? I.e. a lead comes in and n8n triggers an automation to capture it in my CRM and that triggers the agent that uses ICM to read query and compile a draft email response. Hope I am making sense with my question

Apologies for the off topic post but something extraordinary happened today while using my AI systems. My download folder on my Mac got wiped and no idea how it happened: half my life was in that folder and not sure what impacted this will have. Has anyone had anything like this happen to them while using AI / ICM I thought that it was being backed up on iCloud but not all of it was! Gutted