I've been tinkering with a question. Some of the applications I'm building might use specialized agents deployed online. Think off a customer service agent. My whole process is built with ICM and that agent or agents have their whole structure, it works locally, they have their context, reference files, rules, all the good stuff. However, they live in my folders in my PC. And I know how to deployed apps online, I mean there's a whole bunch of examples here on how to do it. But how do I do that for agents? I know it is a play of the Claude API embedded into the website or whichever place I need it into. But how do I direct that API to work though my whole ICM architecture for that specific agent so it knows the right context? Example: Customer asks about product A, the agent knows through the context.md that all product A info is in Product A's folder so it needs to go there and read the relevant files. All that is great and works locally but how do I deploy it online?

I have a client in Australia who's looking for someone who understands ICM and can help him work on his software. Obviously he would prefer someone a bit more technical, but he's happy to have some people who are trying to learn as well. It's a pretty large software, but he's created a pretty good automated system and obviously he's using my methods so it's very well organized. Anyone out here looking for a project to take on the practice or learn more? Or is there anyone in the morning to get a little bit more work done at a higher level? He's looking for multiple skill levels.

Most of my reference layer is facts the agent treats as true: this contact prefers X, that endpoint lives here, this rule still applies. the trouble isn't wrong facts, it's facts that were true when I wrote them and quietly went false. nothing errors, the agent just confidently uses a dead one. I've tried an expiry date per fact and a re-check pass at the start of a session, but expiry is mostly a guess and re-checking everything is slow. for anyone keeping a real knowledge layer and not just live workflow state: do you delete a stale fact, overwrite it, or keep it and mark it superseded so the old answer still explains a past decision? and how do you pick what's worth re-verifying versus what you just trust? curious what's actually held up for you.

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!

Ran a four-stage audit pipeline (my first real ICM build), assuming each stage got a fresh window. Nope. After the full run: 302.8k tokens — 281.3k of it transcript. Everything I engineered (CLAUDE.md, contracts, skills) was 25k. My architecture: 8% of the window. The chatter: 92%. One /clear: down to -282k. Messages: 137 tokens. It picked the run back up from the stage output folders without asking me anything, because my CLAUDE.md tells a fresh session to orient from artifacts, never from the conversation. (Protocol block in the comments if you want it.) So the files hold the state, but to run /clear, I have to do it between the stages? How are y'all automating the clear between stages? By hand at every gate? A wrapper running each stage as its own `claude -p`? Something else? Or does it not matter?