The 60/30/10 rule, and why the 10 is the part that matters least in the mix! When I first learned how to actually think about an AI build I was not thinking ratios, ICM change that. Sixty percent infrastructure. Thirty percent orchestration. Ten percent AI. And I’ll be honest, when I first heard it, I assumed the AI would be the big number. That’s the part everybody’s chasing, right? It’s the smallest one on the list. Once that clicked for me, it changed how I look at everything I build. Here’s how I understand each piece. The 60% is infrastructure: This is the foundation. Your folder structure, where your information lives, how it moves, the plain deterministic scaffolding that holds the whole thing up. None of it is glamorous. It’s the part people want to rush past because it feels like setup instead of real building. But this is the building. Get this part wrong and nothing you stack on top of it stays standing. Almost every time something I’ve built keeps falling over, I trace it back here. The 30% is orchestration: This is how it all moves. The workflow logic, the order of the steps, where the gates are, where your quality checks happen, how one step hands off to the next. The if this then that. This is where your actual thinking lives. The infrastructure gives you the shape. The orchestration is what makes the shape do something. The 10% is AI: This is the piece everybody obsesses over, and it’s the smallest slice of the whole thing. It’s the generation, the analysis, the part that runs at the very end once everything underneath it is already solid. When the ninety percent below it is sound, the AI looks brilliant. When it isn’t, there is no prompt on earth that saves you. So which matters more, the 60 or the 30 I went back and forth on this for a while, trying to decide whether the structure or the logic carried more weight. I finally realized that’s the wrong question. The 60 and the 30 are both the real work. They’re the deterministic part, the stuff you actually have to sit down and think through. The honest divide isn’t 60 against 30. It’s the 90 against the 10.

TLDR: My co-worker has been manually extracting data from 100s of files one at a time and manually managing files for years. This is a longterm client with set workflow. Usually takes him 2 days and I set up a workflow that will do it in a few minutes. Showed my boss and CEO and got the ok to get a Claude MAX seat. Context: I'm a sound designer and work at a post-production audio studio that also does games. The post engineers work on a lot of projects that require manual setup. They were griping at lunch about how they have to open hundreds of text files to find 1 single line of data that they need during their edit session and then manually qa it against the session when it's setup. It sounded like hell to me so I asked if they wouldn't mind showing me what they have to do and they literally manually open each folder, find the text file, write down on a piece of paper the number and then enter it by hand in the computer later. I spent 10 minutes and described to claude what I needed a python file to do. It gave it back to me and the script was able to extract the data they needed in seconds. But that got me thinking, I know there's a python library that works with Pro Tools (our audio editing software), and the current weekly contest is about making a specialist... COuld I make a specialist in Protools Python scripting that can tailor workflows to any engineer? So I spent about 4 hours speccing an ICM folder that specializes in Python Scripting for Pro Tools. Brought it to work today and --- it didn't work -- immediately at least. IN practice discovered there were errors in the documentation for the python library, so we had to fix the documentation. But after that was able to create a contained python script anybody could run and showed my co-workers and ceo. They were super excited about the possibilities and when I asked if I could go ahead and get a Claude Max subscription they said yes immediately. Might also be showing the wider company the setup and what's possible next Monday. Was totally worth staying up all night yesterday to get this out 🤣