So I've been vibe coding with claude for a few months and actually got a decent working mvp for a technician helper app (I work in appliance repair). Sometimes my mind races with so many new ideas that I don't know how to handle haha. It's kept me up at night before because in one way I can see a path forward to so many of my ideas if I can implement a good system and make ai work for me. I want to know how you guys plan for and implement large scale coding projects? I think my most ambitious was creating a full field service suite with invoicing and dispatching and "smart parts" and some other stuff. Building from the ground up with AI in mind. But I feel like this is too big, even chunked down into smaller portions. I've taught myself a little bit of coding, but nothing on the scale for my ambition, and I honestly don't have time to do that (in a reasonable amount of time in my mind anyway haha). How do you decide what's feasible?

Howdy friends :) What path have you taken after starting here? 1. Thrown Jake's folder architecture into claude + your project needs to get something fast 2. Used Jake's folder architecture as a template, editing it line by line to plan, think, and produce what you need I'm starting to build a folder architecture with the aim of being able generate brand assets for my company to use across digital, social, and print. In doing so, I'm finding that I have to THINK! 😂 I also sense that this slow trudge is helping connect the dots from the classroom lectures. It feels slow, like hiking through a bog, but I believe it'll solidify some lessons. What do you all think about moving slow to go fast (with AI)?

Some of you are building right now. You're building a workflow, or an app, or an automation. If you're not a scaredy-cat, tell us what you're building!!!! I'll go first... MY PASSION PROJECT: I am building a free app for independent house cleaners everywhere, so they can professionalize themselves. MY REAL WORK: Otherwise, I'm building automations in my company that are were previously being done manually by an administrator. We're in a hiring frenzy, so I just built workflow automations that tracked where every candidate was in our pipeline, while simultaneously assessing them on communication and skills and moving them forward if they responded. My main admin was actually so happy I figured this out, because she usually has to go through resumes one by one to filter out all the obvious NO's, which takes many hours. I can't wait to know!

Spent a few hours this week trying to set up a custom MCP server for ImportYeti inside Claude's Cowork mode. The goal: let Claude query live US import data directly — no copy-pasting, no manual steps. The MCP server itself worked fine. The problem? Cowork doesn't load custom MCP servers from config files. It uses its own isolated connector system. So no matter what I patched, the tools never showed up. After going through mcp version conflicts, a JSON parse bug on Windows, a broken bash sandbox, and three different config file locations - I pivoted. Wrote a 150-line Python script that hits the ImportYeti API directly, dumps results to a JSON file, and lets Claude read it. Took 10 minutes. Works every time. The lesson I keep relearning: the elegant solution and the right solution aren't always the same thing. Sometimes a script that runs in CMD and writes a file is more useful than a perfectly architected MCP server that never loads. Takeaway (and you/you're is really just me reminding my future self) If you're building AI workflows, match your tool to your actual constraint, not the constraint you wished you had. Already used it to pull competitive intel on a competitor - and then run comparative analysis on others using the same or similar manufacturers. It built an interactive live artifact so I can quickly see all the data. That part worked great. KISS - Keep It Simple & Sustainable... Github for the curious (and the posting process is a nice revisit through everything to reinforce my own learning) https://github.com/FiSimply/importyeti-tools

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.