Your ICM works. So why is it getting expensive to run?

Gabriel Azoulay

2d • 💬 General discussion

Quick recap, because this is "part 3" following

@Bas Rosario

'cake' post and my first follow up.

Thank you

@Brendan Tucek

Your post is what got me thinking about this 3rd part.

Bas taught us to break the cake into ordered steps, one instruction per folder.

My follow up post zoomed in on the step that checks the cake — the toothpick, the gate.

This one is about the part nobody warns you about until it shows up on the bill: cost.

Here's the symptom. Someone in here recently posted a folder system that genuinely works, doing real work in their business, and then admitted the part most people don't: it burns a lot of tokens just figuring out where to look. 🪙

If you've built anything past a toy, you've felt this. The structure is fine.

It's getting slow and expensive anyway. 💸

Here's where it comes from.

In most ICM setups there's one file the AI reads before every single task. The map. The "you are here" file. Every word in it gets paid for on every interaction, whether the task needed it or not. And that file has a way of growing. You add a rule, then a note, then the whole folder tree, then some history, and one day your always-open page is a 3,000-word document. Now the model re-reads a small book before it cracks the first egg. Every time. 🥚

The fix is the oldest trick in any real kitchen: 'mise en place'. 🧑‍🍳 You don'tdrag the whole pantry onto the counter to make one cake. You bring out what this step needs, and everything else stays in the cupboard until it's called.

For your folders, that means the always-loaded file is an index, not the recipe. It points. "Buyers live here. Follow-ups here. Voice guide here." 📇 One glance, then jump. The actual detail lives down in the step folder that only opens when the AI is standing in it. Whoever needs the frosting technique walks to the frosting folder. They don't carry the frosting instructions around all day in case it comes up.

So the through-line of all three posts is one discipline pointed at three different things.

The cake taught you every step earns its folder.

The toothpick taught you which steps earn a check.

This one: every word that loads every single turn earns its place, because you pay for it every single turn. 💡

Most people try to make their AI cheaper by reaching for a smaller model. The bigger savings is usually sitting in plain sight, in the one file you never stopped making it re-read. 👀

Bake the cake. Just don't reread the cookbook to find the oven. 🎂

Three posts deep in Bas's kitchen now. Thanks again for baking that cake for us, Bas ❤️‍🔥

22 comments

Your ICM works. So why is it getting expensive to run?