My weekly limits roll over in about 9 hours. I have a bunch of Fable tokens left that I do not want to use. But I’m also at ~96% of my 5 hour usage window and I need to go to bed. Doesn’t reset for an hour. So, I did what anyone would do, I asked Fable what my options are. Apparently it has a timer. It has set one for 80 minutes and that will wake it so it can fire what we have queued up… I guess I’ll find out what does or doesn’t happen to that branch come morning…!!! Fable has immense confidence that all the results will be ready for me to review over a coffee… ☕️

I am kicking off my weekly planning workflow for next week. At the start of last school holidays, this was a brand new system and I was just moving from a set of saved prompts and skills to ICM. (Hey, it’s been an 11 week term - in ICM time, that’s a few lifetimes!) So, to say I had a little bit of trepidation was an understatement. I have to say every week when I kick this stage off in desktop (I am currently on NotePlan - the connector only works on Desktop) it makes me happy to see Claude go in and say “this is a well-structured system”. Honestly, every week, and I still get the warm fuzzies. I’d done extra context set up and everything. And I knew I already had school holiday templates… Turns out Mira back in April had taken the time to put in a holiday mode to the system. Did I remember this? No, not at all. Did my system make sure that Claude had everything and it went smoothly? Of course it did. Honestly, thank you past me. I didn’t even remember the skill’s holiday mode and my *goodness* does that make my life easier for the next 3 weeks.

Most ICM setups I see here are single-operator: one person, one agent, one context tree that's basically externalized working memory. We're running it differently — as the shared know-how of a small engineering firm (~15 people: industrial automation, control-panel building, light EPC). That one shift, from personal to organizational, changes the whole problem. In a company, the context isn't just my memory — it's the procedures everyone has to follow, and procedures have to be governed, auditable, and improvable by people who will never open a terminal. Here's the core of what we've landed on. One markdown source, three readers. The ICM KB — plain markdown in GitHub — is at the same time: - the agent's operating context (what it reads to act: load costs into the ERP, build quotes, enforce the process); - the company's procedure manual, rendered into a navigable wiki — search, cross-links, the graph of how procedures interconnect — which is what employees actually read; - the ISO 9001 controlled-document system, because Git already is change control: versioned, attributed, diffed, immutable — stronger than the Word-on-a-shared-drive most small firms limp along with. No parallel copies, so nothing drifts. Git is the evidence vault; the wiki is the auditor's reading room. (Worth stating for this crowd: ISO 9001 mandates control — identification, approval, versioning, availability of the current version — it mandates no specific format. A git-backed static site clears that bar cleanly.) The agent is the abstraction layer — this is what makes it survive in a company of non-technical people. Nobody learns markdown, Git, or pull requests. They talk. The agent enforces the current procedure while they work; and when someone says "step 3 is wrong, we do Z now," it turns that into a proposed change to the controlled document. The quality lead gets a plain-language summary and approves or rejects. Proposing is frictionless and open to everyone; approving is a controlled human gate. The Git/PR machinery stays invisible underneath.

I Don't talk to Sonnet 5. My model does (Opus). I sit with one Claude. I direct it, I review what it hands back, I take the call when something's ambiguous. That's the seat I'm in. What I don't see directly is what that Claude dispatches to when the work is execution, not judgement. Loop tasks, cron jobs, every UltraCode fan-out. That's a different seat, one level down, and until now it ran on whatever was cheap enough to risk unattended. Sonnet 5 just moved into that seat. Near-Opus reasoning, full context, Sonnet pricing. I didn't upgrade my model. My model's model did. Who's dispatching for you, and did you notice when they got better? //A<3

Hey everyone, Paul here. I wanted to share where I'm at and lean on the collective brain in this room. By day I'm a clinical data science lead in pharma - the kind of role where my "job description" is basically a small anthology. I'm across clinical data management, EDC builds, protocol and CRF work, SDTM datasets, sponsor interactions, and a lot of cross-functional fire-fighting. It's a mission-driven organization and I care a lot about the work. On top of that, I'm trying to really learn the sponsor management side of the industry while leveling up on AI/ML and agentic workflows so I can bring more structure and leverage into our development programs. Here's the honest part: I'm genuinely excited about all of it. The possibilities feel huge. I'm also struggling to focus, and I've gotten a bit gun-shy about shipping my first real ICM build. I've been playing with a bunch of ideas, drafting files, sketching workflows, and spinning up partial architectures... but I keep stalling right before I commit to, "this is the first build I'm going to ship and actually use." It's not lack of interest. It's that my world is wide, and every time I pick one use case, ten others raise their hand. Then I start second-guessing whether I chose the "right" one. I see how people here go from foundations to real systems, and it's both inspiring and a little intimidating. So instead of staying in my own head, I'd love to ask directly: Q: What actually keeps you focused when your work covers a lot of ground? (Vote below, and share more in the comments!)