So, starting completely from scratch...
The first thing I did was actually not build anything. 😄
I looked around. I started with the Classroom, specifically Getting Started and the first lessons of The Foundation. If you are completely new here, go and do that. It’s time well spent. Then if you want come back here. When I approached Module 4 in The Foundation I had a few questions. Mind you, at the time it was not as nicely organised as it is now. It has improved. Thank you Anyway, the questions appearing in my head went something like this:
How do I pick the right folders? Where do these .md files come from? Do I write them? How would I know they have everything inside them that my project needs? What even is my project? Can I have multiple CLAUDE.md or AGENTS.mdfiles? Where is my real folder root? Do I have multiple projects in the same folder? Can I add more stuff later?... Sound familiar? 😄 In the end, it all boiled down to one question:
How are people actually doing this?
🔎 So I stopped the Classroom for a while and the search bar became my best friend. The more I searched and the more I looked around, I slowly but surely figured something out:
There seems to be more than one way of building an ICM.
Some members loaded Jake’s & David's ICM material/research paper into their LLM of choice and built from there. Other members started with the icm-architect skill. Others did a combination of both. And yet another group used the icm-architect together with something called the Workspace Blueprint.
The bottom line for me was: ❗Many roads lead to Rome. Pick one. ❗
While combing through the group with my best pal, the search bar, I also came across some really interesting videos and posts which helped clear things up for me. Some were easy to find. Others were hidden away somewhere in the dusty abyss of the Skool community posts. 😄
In hindsight, I think searching around for a while was actually very useful. It helped me connect the dots and, more importantly, stopped me from immediately jumping into building something without really knowing what I wanted.
Eventually the more important question became: What do I actually want to build?
For me, that became a little Knowledge System MVP. The initial idea was actually pretty simple.
I have files in various formats. I want to find useful information in those files. I want to be able to ask questions and get useful answers back. And I wanted to see whether I could wrap some ICM around that and learn something while doing it. There was also a practical reason for choosing it. It was something I could see being useful for myself later, and I had previously discussed a similar need with a client. So it felt like a good project to experiment with.
But that’s obviously just my project. Yours might be something completely different. Maybe it’s a workflow you repeat every day. Maybe research. Content creation. Project work. A business process. Or just something that annoys you enough that you’d like AI to help you with. 😄 And if you genuinely don’t know what to build yet, I’d actually just talk to your AI. Have a brainstorming session.
Tell it what you do, what you repeat, what takes too much time, what information you keep losing, or what you’d like to make easier. You don’t need the perfect idea before you start. But you do need to start. If you don’t trust me, just go and ask . 😄 The other thing I found useful was writing down what I actually wanted the project to do before worrying too much about the architecture. And we’ll talk about that in the next post.
Until then, here are some links to some of the content and resources mentioned above.
Have a look, have a read and enjoy.
Videos
Reference Materials mentioned above
The workspace blueprint can be found in the Vault which requires Premium or VIP membership. You can start without it though.
Here are also some people I found during my search for that have brilliant ideas and even little practice modules or GitHub skills. (not an exhaustive list - feel free to add in the comments):
The video producers above already mentioned
....