My mum works in corporate America and is stretched thin. Spreadsheet analysis she has to run manually, a constant pile of emails to draft, life admin on top. She also maps out her processes with mind maps and flowcharts already - the raw material for a second brain is there. The use cases are obvious. She just needs the cognitive load cut. The plan is to wrap her an ICM system she can actually use - one interface on her Claude Enterprise subscription, so she doesn't have to think about what's underneath. I'm 18, built this for myself, and I'm starting to look at consulting for local businesses. This is the first test of translating what I know into something that works for someone else. The scoping process I'll sit with Claude and design the approach. What I'm after is the specific stuff: what would you actually tell someone [me] doing this for the first time with a non-technical user who's already process-minded?

Deep dive will be coming in the next couple weeks after I get back from my vacation next week. Be on the lookout for that. Til then here’s a sneak peak at how I’m building blog posts, shorts, and other content and how I’m also building up to launching long form content as well. Subscribe if you like my content! Let the algorithm know it’s worth watching 😁

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.

Ok. I’m @David Vogel ’s one hit wonder. I’m beavis to his butthead. I had a post that went crazy in here about two months ago: I got a verbal agreement to start an ai transformation. ‘Good news!” Well in the meantime the CFO switched, new employees entered to scene…the allocation of resources became stricter. People went on vacations. I learned a greater depth to how this company needs to pass fees through to entities. It got complicated. Slower. More …who knows…maybe? Well…I signed the agreement with them today. 6mos. Same project I pitched for 3mos but at a slower financial drip for company. A few caveats that weren’t AI related that I’m happy to get as designer… All based around -what does the company I bill…bill this to and measure it against? General AI world communicates and pitches more like, “GAH’ I built a spaceplane and went to andromeda today and yesterday I was just making nachos! “ I’m being extreme to make a point. But, the insight is that decisions and agreements take mutual comprehension and clarity of vision AND performances from many different parties with different perspectives. Yes ‘outcomes’, but it’s a gamble. ‘Potential outcomes’ You have to de-risk your bet—-while you keep studying the table. AI news and marketing mostly is whizbang fomo nonsense. The work and success is in mutual agreements and buy-in. AI is just a tool. The work is finding problems and spending the time with all the parties to create buy-in on solutions. Is a camel a horse by group-design? Yes—- but if everyone wants to live maybe it’s the better animal. Anywho. Get buy in. Listen. Adjust. Listen. Adjust. Listen. Adjust.

Ornith-1.0: the open-source coding LLM that matches Claude Opus 4.7 — and runs on your laptop. This open-weights agentic-coding model hits 77.5 on Terminal-Bench and 82.4 on SWE-bench Verified, beating Claude Opus on both, then ships a 9B size you can `ollama run` locally. MIT licensed, four sizes, and it taught itself the harness.