34 entries. Jake, Don, David on isolated piles, then a panel. This one was hard. A few of you built things that would have won a different competition, and you should hear which one. Every entry got feedback, link at bottom of post! 📋 What we actually judged The post asked for one folder a stranger can drop into a Claude project. identity.md, rules.md, examples.md, reference/, README.md. It reads something broken and says why. Not how to fix it. Four questions, from the post: 1. Does it diagnose? One cause. Not a list. Not a prescription. 2. Is the domain specific enough to be useful? 3. Does each file do one job? 4. Can a stranger figure it out? That is an outcome. Can a person who is not already in your head use this to see why something in their world broke. A lot of the field went further. Refusal paths. Verifiers. Blind runs. Preserved failures. Those are real, and they are extra. We did not pick a winner on the extra. We picked a winner on the ask. If the outcome had been different, the name on this post changes. 🥇 Winner: Colm Whelan — Inbox Autopsy https://github.com/RockfieldIT/inbox-autopsy A stranger holding a bounced invoice can drop the folder in and see why it bounced. That was the assignment. 🔄 Where someone else wins 🔧 If the outcome was "the instrument that can prove itself wrong" — Sergey Manevitch, Radix https://github.com/sergeymanevitch/Radix Why a machine failed in a plant that already has notifications, rounds, and historian trends. Fourteen cold runs. He left the breaks in his own claims standing. A plant engineer is holding something serious. 🧪 If the outcome was "every claim reproduced, including the one that failed" — Pemmy Broke, Visual Momentum https://github.com/hoodwanders/visual-momentum-diagnostician Why an AI explainer lost momentum. She published the run that broke her own doctrine, changed the rules, and the re-run abstained. That is the standard the rest of the field should steal from.

You all mean a lot to me. I truly enjoy this community. Everyone is so excited about using AI and building things that matter. I love how people show up here to help each other and celebrate the wins. Goodness knows, I have learned so much from each of you and I thank you. That said, some of what I am reading, both posts and responses, is mostly generated by AI (if not entirely) and it makes it harder for me to connect with them. I’ve used AI in my own responses too, so I’m not throwing stones. But I do try to make sure it still sounds like me. I’d love to see more of people’s real voice, even if it’s less polished. Yes, ChatGPT assisted me in creating this post - but it's MY voice. ;) You're all amazing!

Nope... Do people think I am... Yes (except for a discord group I am in, or literally anyone in this group🙄) Am I speaking at my first conference today about AI? ...Yes Is it in front of a lot of people... Hahahahahahahahahaha... Nope... Am I excited.... YES! Today I am teaching teachers about AI - not just another tool, building a system that lasts. #SuchFun

https://github.com/RinDig/icm-architect Most AI tools try to understand your project by stuffing as much of it as they can into one chat. That is slow, expensive, and they still miss the thing that matters: if I change this, what else breaks? The new System map form walks a repo (or a notes folder) and writes a small catalog instead: - What the pieces are — in your words and in the code’s words (“Chat” is actually called Incubator) - What is real vs leftover vs fake — so nobody builds on a feature that only exists in an old doc - If you change X, what else moves — and what looks related but is the wrong thing You do not get a 40-page audit report. You get index-card pages. A later agent opens the catalog, one card, and the file it points at. That is it. Same idea as the rest of ICM: the folder is the map. A person can open it. An agent can walk it. Nobody has to hold the whole system in their head. Ask it to “map this repo”

It’s live. Starting today, everyone in Clief Notes has access to the new Clief Notes AI. The easiest way to use it? Don’t overthink it. Ask it the question you would normally ask me. “Where should I start?” “What should I focus on next?” “Where did you talk about [topic]?” It’ll use what’s already inside Clief Notes to help answer you and point you toward the right lesson or resource when there’s something worth going deeper on. The goal isn’t to give you another AI tool to play with. It’s to make everything already inside this community easier to actually use. If you want Access to it Comment "READY" and we'll send you access to it!