https://www.loom.com/share/a5437be6951c406586be39b5633c879c I spent most of today rebuilding how I organize my work, and I wanted to share it with you guys. The problem I was solving: I've been building production systems with Claude Code for over a year now. My process has always been the same -- use Claude Chat as the architect to brainstorm, build blueprints, figure out the technical approach, then hand those blueprints to Claude Code to execute. That part works great. But my project folders were getting messy. Context was scattered. Every new project started from scratch with no structure. And the stuff I learned on one build wasn't connected to the next one in any useful way. After going through Jake's material on workspace organization and the three-layer system, the light came on. What I built: A single folder structure on my desktop that does three things at once: 1. Obsidian reads it as a knowledge vault -- clients, pipeline, patterns, daily logs, reference materials. The stuff that compounds over time. 2. Claude Code reads it as a structured workspace -- each project has its own CLAUDE.md, its own planning folder with blueprints, its own source code directory. Claude Code knows exactly where to go and what the conventions are. 3. It's the onboarding manual for anyone I bring into the business. My daughter is ramping up to help with prospecting. She reads the client CONTEXT files and the pipeline folder. She doesn't need me to explain everything verbally. The flow: - I architect in Claude Chat (inside a Claude Project with all the client context loaded). The output is a requirements doc and a technical blueprint. - I duplicate my project template into the builds/ folder, rename it, fill in the CLAUDE.md, and drop the blueprint into planning/. - I open Claude Code in that project directory. It reads the CLAUDE.md, reads the blueprint, and starts building into src/. - As I code and add features, I come back to Claude Chat to architect new blueprints, and Claude Code updates CLAUDE.md along the way. It's a living document. - After delivery, I update the client folder, write a retrospective, and extract any reusable pattern back into my patterns library. Next project that needs a similar approach? The blueprint references the pattern instead of re-architecting from scratch.

I use, but I'm thinking about switching my IDE for a change of pace and to explore new workflows. I'm curious if any of you use alternatives like Cursor, Antigravity, or something else entirely. If so, which one do you prefer and why? I'd love to hear your experiences and recommendations before deciding on a switch.

Tell us three things: 1. What you do (job, industry, student, career-changer, whatever) 2. What brought you to Clief Notes 3. One thing you're trying to figure out right now related to computing or AI I'll respond to every single one. And read each other's intros too because the person who's stuck on the same problem as you might already be in this thread. I'll go first I am Jake, I have been working in tech for 15 Years, building with Generative AI for 3 Years straight now! Excited to teach and learn! That's it. Simple, scannable, gives you data on who's joining and what they need, and keeps the feed clear for content that retains people past week one.

1. Watch the intro video and introduce your in the intro post here 2. Start with The Foundation (free course). Concepts, folder architecture, prompting framework. Everything else builds on this. 3. Check in at the bottom of each lesson. Polls, discussion posts, other members working through the same stuff. Use them. 4. When you're ready to build real things, move to Implementation Playbooks (Level 2). When you're ready to build your own tools, Building Your Stack (Level 3). 5. Post your work. Ask questions. Help others when you can. What are you here to build?