Hey all looking for architecture advice from anyone who's been here. I'm automating the back-office side of a sales role on Claude — AR/collections, order entry, statement sends, reorder follow-ups, and more workflows being added. The setup is skill-based: I invoke workflows by command (e.g. "Submit orders"), Claude handles the steps, stops for my review before anything sends or submits. Building toward full orchestration with dispatch routing the right workflow automatically based on triggers. Problem: I'm on Max 5x and a few planning chats plus ONE order through Cowork already hit ~26% of my usage before reset. That math doesn't scale once everything is live. The bigger issue: Cowork is currently slower than submitting orders manually. It runs a screenshot-and-click loop through a web UI, and the latency is real. Has anyone found a way to speed this up or get off the vision loop entirely? Questions: 1. Is moving automated execution to the Agent SDK / metered API the right architecture — keep the subscription for interactive work, run agents on the credit pool? 2. For UI-based tools with no API access, did you find a way off the screenshot loop or just accept the cost and speed hit until a native integration exists? 3. Self-capping usage meters on subagents — is that SDK-only or doable another way? 4. Should I be building workflows in Cowork first then graduating to Claude Code, or is it worth starting in Code now? Trying to get the architecture right before I scale this up. Appreciate any wisdom thanks fam.

You built your first folder. Vote below, then drop a screenshot in the comments so we can see what you came up with.

As I’m beginning my journey in AI, I’ve built out my own learning roadmap. Within the roadmap I have added some lessons of python and json. Does anyone think this is required learning? I was informed that with Mythos coming out from Anthropic it would be pointless to learn.

I’ve been all in to local ai, but for some reason I had stayed away from image gen… Wow! This is flux2-Klein-4b.

Update!! New Visual Report Attached. Also here for direct Claude design file! https://claude.ai/design/p/a4493151-285d-4ae7-8ae7-a62cee37319a?file=index.html&via=share I've been spending a lot of time in the who's here thread and its been remarkable to see all the different folks coming into this community. The growth is truly something to behold. I had Claude scan the comments of everyone introducing themselves and pump out a fun report of who we are. The results are pretty interesting to look at. @Matthew Creamer there's some good feedback on where everyone is feeding in from too though I'm sure you guys already have it haha. Hope everyone enjoys! --- # 🧠 Clief Notes Community — "Who's Here?" Intro Thread Analysis --- ## 📊 How They Found the Community The #1 source by a wide margin is Instagram Reels. People keep saying things like "your reel popped up" or "I was doom-scrolling IG and..." YouTube is a strong second, and TikTok has a small but real presence. Word of mouth is also a meaningful driver, which suggests the content is shareable enough that people pass it around. - **Instagram/IG Reels** — ~505 mentions - **YouTube/YouTube Shorts** — ~376 mentions - **Friend/colleague referral** — ~83 mentions - **General social media scroll** — ~89 mentions - **TikTok** — ~29 mentions - **Twitter/X** — ~3 mentions (almost zero) --- ## 👩‍💼 Who They Are — Top Professions & Industries The community skews heavily toward tech and business, but the breadth is genuinely remarkable. Some notable counts across 6,300+ member intros: **The big clusters:** - **Software Engineers / Developers** — ~918 mentions (the single biggest professional group) - **Marketing professionals** — ~621 mentions - **Entrepreneurs / Founders / Business Owners** — ~557 mentions - **Students** — ~496 mentions - **Finance / Accounting / FinTech** — ~464 mentions - **Teachers / Educators** — ~401 mentions