The library on this site is a graph of deep dives. That is great when you are browsing. It is worse when you want an agent to study the corpus, answer a question, and point a person at the right three essays with links. So I built a second shape of the same knowledge: an ICM knowledge bundle. Catalog on top. Episode cards underneath. Full essays still live on the site. The folder is the librarian. The form that fits a public teaching corpus is the knowledge bundle: aris-space-icm-knowledge-bank/ ├─ CLAUDE.md who you are + how to answer ├─ CONTEXT.md one-screen map of the shelves ├─ AGENTS.md pointer for non-Claude seats ├─ _index/ catalog (log + by-topic) ├─ _meta/schema.md card contract ├─ _shared/advice-voice.md ├─ corpus/_index.md what was harvested └─ bundle/ ├─ voice/ always-load orientation ├─ dispositions/ routers by kind of ask └─ episodes/ one card per deep dive / lesson Routing files stay small. They point. They do not store the books. Episode cards hold: Title Live URL on its own line One paragraph of context When to recommend it Related cards in the bank The agent does not invent essays. It opens cards, ranks them, and sends people to the site. Deep dive and download over at: https://aris-space.com/documents/workflows/aris-space-icm-knowledge-bank //A<3

I'm delivering the attached presentation next week at the Austin Claude Meetup. It shows a file-based company brain built around the same principles I value in ICM: simple, portable, and traceable. The practical pieces: - Simple file routes for recall - Workflows stored as reusable Skills or beside the work they govern - Pre-processing email, calls, videos, PDFs, presentations, spreadsheets, and exports before an agent needs them Full credit to Jake Van Clief for popularizing ICM and consistently advocating for simpler solutions. Sharing it here first because this group will catch what I missed. Where does the presentation align with ICM, and where does it need sharpening?

EDIT: WE HAD OVER 100 PEOPLE SIGN UP IN TEN MINUTES....GOING TO BE ROLLING OUT ACCESS ON SLOWER BASIS NOW SO I DONT RUIN MY BANK ACCOUNT WITH TOKEN SPEND FOR YALL (im covering ai costs for everyone) but keep applying we are keeping track and will be letting more people in and reaching out about getting you all access one by one especially VIP. Our Platform is here, the thing a lot of you have been asking for and I have been teasing Take your ICM folders and second brains, put them in the cloud, and work on them together in real time. You upload your folders and files. One strong model with a good harness reads the map and becomes the agent you need. No new agents to build, no zip files to pass around. Each workspace runs in its own container. It renders your markdown, edits your files, installs packages, runs Python and Playwright, and multiple people can work in the same space at once. No Mac Mini needed to keep your data separate either. We're opening it to VIP and alpha testers first, and I'm covering the AI cost while we test so cant do a full role out yet. Free AI use which is great for those users, not great for my bank account haha. ✍️ Sign up for access: https://docs.google.com/forms/d/e/1FAIpQLSdSnToxclxt8EgoB2GizrEvHP7gzOedVcRXdCkpi1SZwR8ZfA/viewform 🔗 Questions, or want to work heavier with this? Email info@eduba.io

Started seeing lots of errors recently so I asked Codex to fix it!! Prompt can be adapted for whichever tool you're using. Reusable prompt: Optimize Wispr Flow from Claude or Codex history Improve my personal Wispr Flow transcription accuracy on this Mac or Windows computer. Wispr Flow is the only speech-to-text application in scope. Use the tools built into the Claude or Codex environment running this prompt. Do not assume access to any organization-specific session index, MCP server, workspace, or external memory system. 1. Find the available session history Determine whether you are running in Claude or Codex. Use that product’s built-in tools for accessing the current user’s past sessions or conversation history. Analyze only history available to the currently logged-in account. Include past sessions that are retrievable through built-in tools even if they do not appear in the current conversation interface. If session-history tools are unavailable, say so and continue with Wispr Flow’s accessible transcript history. Do not search application databases, credential stores, hidden account files, or unrelated filesystem logs. Do not ask the user to export sessions unless no built-in history access exists and the additional evidence is necessary. 2. Analyze the user’s language From accessible Claude or Codex sessions, extract language written or dictated by the user, including: Names of people, companies, brands, products, and projects. Technical terms, acronyms, and specialist vocabulary. Uncommon words and recurring phrases. Words requiring unusual capitalization, spacing, punctuation, or hyphenation. Singular and plural forms the user regularly employs. Similar-sounding words likely to confuse speech recognition. Exclude: Assistant-generated language not also used by the user. Code, logs, quoted documents, and pasted third-party writing unless the user’s own messages confirm the vocabulary. Sensitive terms that are unnecessary for improving transcription.

Hey all! Funny timing on this one! Jake released the awesome ICM Architect. I also wanted a solid reference full of examples, projects, tools and templates. Basically all the stuff served up over Tea and in community posts. So I put together the ICM Field Guide!! - Architect builds and restructures the workspace. - Field Guide is the giant reference shelf next to it. 50 markdown files total structured with ICM - 13 applied patterns - 14 project examples - 12 kits and templates - 8 decision tools - 19 implementation references. Jake's post: https://www.skool.com/cliefnotes/new-tool-icm-architect Field Guide: https://github.com/jonathanmalkin/icm-field-guide Please let me know If I missed something. I'll add it.