(New to ICM?) ICM, explained with a birthday cake 🎂

Bas Rosario

🔥

7d (edited) • 💬 General discussion

This post is not for the ICM pro, there will be no talk of gates, scripts, or orchestration!

This is for the person just starting out!

@Karli Rosario

Yes, I mean you!

(And anyone else who may just be starting out with ICM)

Seriously, I'm glad you found ICM. Let me give you the simplest version of it I know.

ICM is a system of structured folders.

Yes, the same folders you have been using on a computer for most of your life.

The ones you stored photos in, & pirated music from Napster and LimeWire.

That's it.

I will take you through the process below.

When working with AI, a lot of people are doing this 👇

You take a long prompt, feed the entire thing to AI at the beginning of your interaction, and spend time going back and forth with AI trying to get the outcome you want. (I'm not coming for you Karli, you are exceptionally good at this, but ICM will make your outcomes exceptionally better!)

What is different about AI and prompting with ICM 👇

You take that same really long prompt and instead of giving it to the AI all at once in the beginning, you break it into steps, and each step gets its own folder, each folder gets its own piece of your large prompt, just 1 step from it, and you ordered the folders by when the steps happen in the workflow.

You got it? Good 😊 ❤️‍🔥

-------------------Still a bit unclear, let's bake a cake.

💡 Here's an analogy I have success with (I picked this up way back in my VB programming days):

Imagine teaching AI to bake a birthday cake. 🎂

The way most people do it: 👇

One giant prompt. "Bake a cake, here's the recipe, the frosting technique, the decorating style, the candle placement..."

Then they hit enter and wait.

The AI is juggling 40 instructions at once, and by step 30 it's forgotten step 3.

The ICM way: 👇

Break the prompt/workflow into steps.

Each step gets a folder. The first folder is your first step. Then you point the AI at the first step, and the first step is 00-birthday-cake: (Point the AI just means giving access to the folders to the AI, through uploading or direct local access, don't worry about that now, let's keep building our cake.)

👇===Look at this birthday cake workflow, notice the steps, 00, 01, 02, 03, 04 and so on. Each step has its own context.md file which hold 1 instruction and the directions to the next step.

🎂 00-birthday-cake/

├── 📁 01-gather/

│ └── context.md👇

│ "Your one job: gather the ingredients.

│ When done, go to 02-preheat."

├── 📁 02-preheat/

│ └── context.md👇

│ "Your one job: preheat the oven to 350.

│ When done, go to 03-mix."

├── 📁 03-mix/

│ └── context.md👇

│ "Your one job: combine ingredients in this order.

│ When done, go to 04-bake."

├── 📁 04-bake/

│ └── context.md👇

│ "Your one job: bake for 30 minutes.

│ When done, go to 05-check."

├── 📁 05-check/

│ └── context.md👇

│ "Your one job: toothpick test. Clean = go to 06-cool.

│ Not clean = back to 04-bake for 5 more."

├── 📁 06-cool/

│ └── context.md👇

│ "Your one job: cool completely.

│ When done, go to 07-frost."

├── 📁 07-frost/

│ └── context.md👇

│ "Your one job: frost using this technique.

│ When done, go to 08-decorate."

├── 📁 08-decorate/

│ └── context.md👇

│ "Your one job: apply the decorating style.

│ When done, go to 09-candles."

└── 📁 09-candles/

└── context.md👇

"Your one job: place the candles. When done, you're finished."

✅=========End of workflow, and you have Birthday cake! 🎂

One focused instruction, in the context.md in each step, gets executed, then on to the next.

Do this and your accuracy goes up, rework goes down. Not because the AI got smarter, but because you stopped asking it to remember the whole cake while it's still cracking eggs. 🥚

You are helping the AI determine what to do at each step, no guess work, real instruction, every time.

Mix. Bake. Frost. Decorate. One folder at a time. 🎂

We learn together, we grow together, we win together!

🤓💪🏆

Bas

25 comments