I spent the better part of the weekend and today trying to teach ChatGPT Work how to create an ICM system. I fed it templates, skills, and example ICMs - the whole nine yards. We mapped out the workflow, and everything seemed crystal clear. We had a great foundation, and it was successfully creating files, folders, and scripts. All was well. Then, I started testing. Inevitably, issues popped up, so we patched the project. When it came time for the final test, everything should have gone smoothly. Instead? Absolute silence. No output was created. Suddenly, the agent jumped completely outside the workflow and started implementing things way out of scope. What?! I started digging through the files to see what went wrong. Buried deep within hundreds of lines of markdown files and scripts, I finally found the culprit. A single line of text read: "Defer creating ICM structure until version 1.0 of the harness." I got so caught up in the excitement of the automation that I did not even realize the AI had completely excluded the ICM from the actual implementation and only built me the coding harness! 😠

We officially launched the new Clief Notes Agent, and I wanted to check in with you. Have you had a chance to talk to it yet? If you have, I’d love to hear how it went. And if you’ve run into any questions, confusion, or issues getting started, drop them in the comments below. The goal is to make it easier to find what you need, know what to focus on next, and get more out of everything already inside Clief Notes. So, How’s your experience been so far?

Searched the new Clief Notes AI, and nothing came up. How are you handling canonical truth in your ICM / .md systems? For example, if pricing, project status, or strategy changes, do you have one .md file that is the authoritative source and have everything else reference it? I'm realizing that even with good context routing, duplicate facts across CONTEXT.md, STATUS.md, memory, and daily logs can create a different kind of context problem. Curious how everyone is handling this?

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. this does not mean extra is not better, in many cases I LOVED the solutions created. If the outcome had been different, the name on this post changes honestly 🥇 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.

The amount of posts that are nothing more than copy paste of other peoples work for like farming makes for another facebook or x. the fact that there are real incentives to gain points in the community only makes this worse. as someone who produces genuine novel content i find it very frustrating to see all the copy paste thats nothing but point farming.