Someone here has been trying to run an icm shaped system on gemini bc IT wont hand out api keys, and hit the wall where gemini code assist in vs code forgets the instructions and only takes one md file, and a Gem holds ten docs but cant write back to itself. gemini cli is the piece that closes this. u sign in with a google account over oauth, no api key involved at all, and the free tier is 60 requests a minute and 1000 a day. the reason it matters for icm specifically is that it loads context files hierarchically, the same shape the methodology assumes. it reads ~/.gemini/GEMINI.md, then the GEMINI.md at ur project root, then ones sitting in subfolders, and merges them in that order. u can pull other markdown into a context file with @path/to/file.md, so ur tree stays a tree instead of one pasted blob. /memory show prints the combined context that actually loaded, which is how u verify it rather than hoping. /memory refresh re-scans after u edit. and it writes back to disk, which is the bit a Gem cant do. for sharing with the team it just becomes the repo. they clone it, they get the same context files, nobody is hand maintaining a Gem. one honest caveat, the free oauth tier is tied to a personal google account, so if ur work account is locked down u would be putting work context thru a personal login. worth clearing that with IT first instead of finding out later.

The feed is a terrible index. Clief Notes AI is the librarian for it — not a second Claude, not a folder-builder, not a replacement for a Check-In. Free is three prompts. Total. DMs and the sidebar both count. After that you’re back in the classroom, which is still where the work lives. I wrote the map so you don’t spend shot one on “what can you do?” What’s in it - What this agent is (and what it will never do) - Chromium install, Student portal, same email as Skool - Three Getting Started shots and three Foundation shots you can paste - How to talk to it with the five-part prompt so a sloppy ask isn’t 33% of your budget Do this now 1. Classroom → Getting Started → watch Navigating The Course (2:51) 2. Open How to Access your Clief Notes Agent & Roadmap and install 3. Read the guide: Comprehensive Guide to Clief Notes AI https://www.skool.com/cliefnotes/classroom/c7f102c7?md=144082eaf875446eba04fa1db90fcc90 4. One DM. Then open Foundation 1.1. Check the box. The agent is a map. Your folder is the architecture. If the agent writes the system, you didn’t learn the system. Paste this if you only have one shot left: I just joined as [beginner / daily AI user / developer]. Give me the three-step start, the first Foundation lesson title, and what “done” looks like. Do not invent a custom curriculum. If three shots already feel tight, that’s the product working. Foundation stays free. Paid keeps the librarian on.

When a friend asks for thoughts and research about a given topic, I take it very seriously. I used perplexity deep research alongside Kimi K3 High Thinking to generate him a clear and understandable PDF document outlining whether he should or should not purchase a crockpot after his urgent message. It turns out that dictation fails again. On the upside, when I realised he meant grokbots, I was able to point him to my article about them. And now I have 12 million tokens worth of research about crockpots for anyone who needs it. //A<3

Crazy concept... What if you used icm, all of the ai tools and all the contacts at your disposal to Live build a Cult fashion brand by xmas ❤️‍🔥 Stay tuned for the ride as I breakdown how I build the universe around a brand. The tools I use, The workflows I build and the Ai infa I set up. cun7.uk //A<3

Folders, not frameworks: how Taurus makes Claude repeatable for a whole team Giving an AI agent the right context at the right moment is still the hardest part of using coding agents like Claude Code in real, daily work. We've all felt it: the agent is brilliant when it knows where it is, and frustrating when it doesn't. So how do you give it that context — reliably, for more than one person? A small team will work but what happens when you try to on-board 100+ people? The popular answers don't scale. Elaborate memory systems help a single power user, but in an enterprise they become a liability: they're hard to curate, easy to pollute, and brittle the moment you add more people and more projects. And anything built around one person's bespoke setup — their servers, their wiring, their mental model — is expensive to onboard a whole team onto. Honestly, the wheel hasn't been invented yet. Nobody has a clean, proven answer for how context should work at enterprise scale. This is where the Interpreted Context Methodology (ICM) changes the conversation. Its core idea is deceptively simple: folder structure as agent architecture. Instead of orchestration code or a sprawling memory store, the context lives in the folders themselves. A workspace is just numbered folders for each stage, with markdown files (CLAUDE.md, conventions, reference material, working artifacts) that load in layers when an agent starts there. The agent reads downward and stops when it has enough — typically 2–8k tokens instead of 30–50k. You "configure the factory, not the product": set the workspace up once, then every run reuses it with new inputs. Outputs are plain text, editable, reviewable at every step. ICM is elegant because it's filesystem-native and human-readable — a non-developer can reshape a workflow by moving files. But it has one practical dependency that's easy to overlook: When you add more and more folders agents begin to skip information. Guidelines are missed, rules are overlooked. What worked for one person doesn't work for another because the model scans economically and thinks it knows enough. The solution is again simple, the agent has to actually start in the right folder. Start in a central place and the layered context never loads; start in the right place and the agent is instantly grounded. In a team, "just cd to the correct directory" is exactly the kind of invisible, error-prone step that breaks repeatability.