Okay so it's 12am and I'm building Rooty, the app that's literally about helping stylists stop burning themselves out. And I'm sitting here reworking the same landing page for the hundredth time, slowly starting to hate every word of it. So my AI, the thing I'm building this with, tells me to go to bed. Basically: "you don't hate the work, you're just out of gas. Go rest, it'll look fine in the morning." Then my husband walks by and says the exact same thing. 🙃 So to recap: I'm making an app to help you stop grinding yourself into the ground, and it took my laptop and my husband ganging up on me to close it. The irony is noted. Goodnight, for real. 🌱

When Bas first added me to this group, I could barely have told you what an API was. I've been mostly quiet since, because I was heads down building something, and I finally get to show you. But the win I want to share isn't the one I thought I'd be writing about. A few weeks in, I was at my kitchen table testing a feature, and my own app wrote something back to me. A little message, the kind it sends to a stylist. I read it and I cried. Me. The person who built the thing. It had just made me feel seen, as a hairstylist, and I wasn't ready for that. I'm a solo hairstylist. That's my actual job. The app is called Rooty, a companion for stylists who are tired of being told the only way to stay booked is to become a full time content creator. I built it between clients over about seven weeks. Here's the part I think this group will appreciate, and it genuinely surprised me: the code was not the hard part. The boring receipts: - 212 commits, about seven weeks, built between appointments - One Python file, roughly 8,000 lines, zero dependencies, just the standard library - 132 tests - Multi-tenant, real logins, running live right now with actual stylists signing up - Claude Code did the heavy lifting on the code, Anthropic's Haiku model runs the AI features - I directed all of it. Every product decision, every word of the voice, every call about what it should and shouldn't do. I'm not a programmer. I'm the person who knew what it needed to feel like. That last line is the whole thing, so let me stay on it. The code, honestly, the AI and I got through together. What I could not outsource, what no prompt handed me, was knowing when a message sounded like a brand instead of a friend. When it was technically fine and emotionally wrong. I felt those the way I feel a bad section in a haircut, right away, in my gut. And I sent them back. So the "it feels like it gets me" that people react to, that came from real decisions: - The captions and replies learn from my actual writing, not a formula. They sound like a person because they're trained on one. - Every AI feature is its own little room with exactly one job. None of them is a general chatbot. A tool that tries to do everything feels like nothing. A tool that does one thing warmly feels like a friend. - And me. I was the reject button. I read hundreds of generated lines and killed every one that rang false.

💪 It did not disappoint. 👉TL:DR - It made all AI use cheaper in my environment, made me more efficient, and it increased my memory system usage by almost half. It should be no secret to anyone here: I don't count tokens. 🪙 I'm on a Pro Max plan and I go where the work, and the passion takes me. But I have used Fable before, and I know about the token burn! So I came up with a plan! I pointed Fable at my own setup and pulled the report. 😅 I'm glad I did. Turns out it could've been cheaper and cleaner the whole time. I didn't ask Fable what it thinks. I pointed it at the real thing. My hooks, my handoff files, my subagent config, the actual token counts on disk. Two questions: where does the money go? & how do we spend less? 💡The answers. A silent forgotten tax on every message, A safety hook was injecting around 800 tokens into every prompt I sent. Repeated rules I already load once at the top. And a file that runs at every session start called itself " 450 tokens" in its own header. It was not... it was 7,000. My actual face when I saw this--->🤬 a few moments later--->😆 (Apparently, it's not only AI that is bad at counting sometimes!) My own file lied to me, and I'd read past that number a hundred times with a smile on my face! My long sessions. The ones I'm proudest of. Turns out that hour six is my most expensive and also least impactful at the same time. 💩 I know that models follow instructions worse at higher context. And because the quality was still there, the marathon I read as momentum was being billed to me at top rates for the weakest output of the day. 🙄 My helper agents were all running on the flagship (Most expensive model). These are the agents Claude spins up to send off to do tasks to get more accomplished in a shorter amount of time! This I knew about, and it was by choice, it's my environment and I never hit my 5 hour or weekly cap, so I did not care about this for myself, bigger = better right? Use Fable 5 on UltraCode in my environment, and we find out that logic was wrong....

Quick update on the competition schedule so everyone knows what to expect. 📅 NEW CADENCE: TWICE A MONTH We're dropping comps on the 15th and the 30th of every month. Two chances to compete, every month, on a set schedule you can plan around. ✍️ WHY THIS SCHEDULE Spacing them out this way means we can give tailored feedback on every single submission. Not just the winners. Everyone who enters gets notes on what worked, where it's weak, and what to do next. 🎁 WHAT WINNERS GET Along with the prize, every winner gets a 15-minute one-on-one with Jake. Use it to talk through your build, ask questions, or bring whatever else is on your mind. Two comps a month. Feedback on every entry. Direct time with Jake for the winners. Mark your calendar for the 15th and let's get to work!

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.)