Most AI workflows fail for the same reason: they treat context as a blob instead of a structure. ICM solves part of that problem by staging context through folders, markdown files, and step-by-step workflow design. But ICM becomes much more powerful when you add ontology, because ontology gives the workflow a shared semantic model: what the entities are, how they relate, and which concepts belong in each stage. That is the difference between “a well-organized prompt system” and “a structured reasoning system.” Why ontology matters Ontology is not just vocabulary. It is the relationship layer that tells an AI system how to interpret a domain. For example, in a hospital policy workflow, ontology can distinguish: - Policy - Goal - Constraint - Regulation - Requirement - Evidence - Workflow - Approval - Audit Without ontology, the model may understand these as related words. With ontology, it understands them as connected concepts with specific roles. That makes reasoning more reliable, especially when the task requires multiple hops across a domain. Why this matters in ICM ICM already helps by loading only the context needed for the current stage. Ontology makes that staging meaningful. Instead of loading everything at once, the workflow can load a scoped ontology for each step: - Intent stage: Policy, Goal, Stakeholder - Compliance stage: Regulation, Requirement, Evidence, Violation - Operations stage: Workflow, Role, Approval, Audit Now the model is not just reading context. It is traversing a domain structure in small, controlled steps. That reduces noise, improves traceability, and makes each intermediate reasoning step easier to inspect. Concrete example Imagine a demo project that analyzes a hospital AI policy. Stage 1 extracts the policy intent. Stage 2 checks compliance against regulations. Stage 3 translates the findings into operational guidance. Each stage uses a different ontology slice, but all three stages share the same semantic backbone. That means the model can move from “what is this policy trying to do?” to “does it meet the requirement?” to “how should the team implement it?” without losing meaning between steps.

Stop README-shopping. Start scoring the repos you actually trust. Most of us still pick open-source like restaurants. Stars. Nice README. Maybe a glance at the last commit. That friction is real, and it's how vibe-coded slop ends up in the stack. New classroom piece is live: Git Repo Security: Why It Matters, and How We Actually Do It https://www.skool.com/cliefnotes/classroom/c7f102c7?md=43a45577d5cb4096b040770491d87b50 Why this hits us: we pull public git constantly. Agents clone third-party skills. Volunteers don't have an AppSec team. Stars are a weak signal. The article folds OpenSSF / SLSA / CISA-style checks into two portable skills so the discipline gets cheap and repeatable. How you run it (newbie path) 1. Open the article and download the zip. 2. Drop the zip into your harness (Claude Code, Cursor, OpenCode, Grok, etc.). 3. Prompt the agent like a colleague: run repo-scorecard Egonex-AI/Understand-Anything (github username/repo) or run repo-eval Egonex-AI/Understand-Anything ============================================================= Here's what you get from repo-scorecard: Scorecard: Egonex-AI/Understand-Anything Score: 9.50 / 10.00 — healthy, well-run project What's good: • Actively worked on — last update was yesterday. • Very busy recently: 355 commits in the last 90 days. • Many people involved — about 70 different contributors this year (though one person still does most of the commits). • Has a clear license, a README, and a security contact policy. • Has automatic quality checks and tests set up. • Ships tagged releases (8 tags) and keeps a fixed parts-list for its building blocks. Things to know: • No automatic updates for the building blocks it depends on. Score based on publicly visible project activity and housekeeping. It does not include a security scan of the code itself. ==============================================================

Come chat about your goals for the week! If you are new here, this is a chat room for general talk about the past week and the week ahead. Share what you’re working on and network with others! If you‘ve been here before, you know the drill. Leave a comment below. Some ideas to get the juices flowing: - What you’re working on - Something you hope to ship - Blockers you’re running into at the moment - Where you’re looking for help currently - Anything else you’d like to share Have fun and enjoy your week everyone! This week’s poll: Do you feel like you have the fundamentals down at this point or are you still learning any basics? If you feel you’re missing something, comment it below 👇

Hi, I was wondering if anyone who works with AI using ICM has encountered restrictions regarding security. I was discussing this with a friend of mine and at some point I did not have anything else to say, because I genuinely don’t know. I don’t know how to deal with companies, I can imagine that much of the data they have is sensitive to some degree. How do people that create workflows with AI for companies deal with such constraints?

I came across this today. Watching it hit that itch of something I kinda do already. It also ties to how Jake's looking to the past to guides how things work with LLM. The second brain, how things are linked, etc. Just sharing as something that may help people think about LLM in tools and such. I'll leave it with to quotes from the description and the talk. "Nothing is a mistake. There is no win, no fail. Only MAKE." " An ontology is just typed entities, relationships, and constraints, expressed with old and boring standards like RDFS and OWL, that let you say a payment status must be one of three values, that a customer and a support rep are different things, that an order can only be refunded once. Wrap a Claude tool use loop with a validator: when the model proposes a tool call, check its types with Pydantic and its results against the ontology, and only then let it act. The catches that are painful to write in English become a few lines of logic."