🔥 @Bas Rosario took the top spot this week. 🇬🇧 Quick note first. Apologies for the late post today. Jake and I are deep in prep for London Tech Week coming up. Thanks for your patience while we get everything dialed in. 🙏 🎁 What Bas wins: He was already a Premium member, so we're converting his account. ✨ Free Premium for life. ✨ No more monthly charges. Ever. ⏰ The 7-day clock just reset. Next Monday we crown the next winner. Could be you. 🎯 How it works: - 📝 Post bad ass stuff - 💬 Help people in the comments - 🛠️ Share what you're building, what's working, what's breaking - ❤️ Engage with other members' posts The leaderboard tracks all of it. Whoever sits at #1 next Monday wins. 🎁 The prize, depending on where you're at: 🆓 Free member? You get lifetime Premium, free ⭐ Already Premium? We convert your Premium so you stop paying 👑 Already VIP? We convert your VIP so you stop paying Either way, you stop paying. Forever. Bas, congrats. You earned this. 👏

This week @James Mackellar took the whole thing! Mayston is a research partner for UK neurophysios prepping stroke-rehab CPD. That's the kind of work where you walk in ready for the pushback or you don't walk in at all. So Mayston holds the debate for you. It won't open the discussion until it knows your current teaching position, it keeps the rival treatment schools apart so they don't blur into mush, and it hedges every claim on the GRADE evidence scale. Deepest folder in the comp. But here's why it won. This is productionize your opinion all over again. Mayston is built on a working UK physio's decades on the frontline. His dad. The follow-up calls are logged right there in the repo. James didn't research a persona, he built his father's life work into a tool, then shipped it like a launch. Landing page, a 60 second overview, a full walkthrough, annotated diagrams. Same lesson as last week, said a little different. YOUR expertise is the value. And when it's close to home, a son building his dad's craft into something other clinicians can actually use, you feel it. People trust that. You stay passionate because you care whether it's right. That's the whole game. - 📺 60-second overview: https://youtube.com/shorts/uDZyiZ-aD8w - 📺 Full walkthrough: https://youtu.be/gzHoSpZPWS0 - 💬 https://mayston.pages.dev - 🔗 https://github.com/JamesMack05/mayston 🎯 Honorable Mentions Six builds, no particular order, that made this so hard to call. 🇳🇱 @Arjen Stet , Lex Dutch worker-classification law, built for the exact enforcement wave the Belastingdienst just restarted. What got me, it refuses to cite a court ruling it hasn't verified, so no made up ECLI numbers, and it splits the sources that lead (statute, the High Council) from the ones that only signal (blogs, tax-authority posture). Every conclusion gets labeled settled, in motion, or not-yet-law. Bilingual EN/NL readme so the rest of us can follow it, plus a short intro video. This was my runner-up, and it was close.

Gosh, feeling lost in this one. Problem would be that I started setting up my workspace, not as a clean state, but as everything that I have been doing that's saved on my desktop / Google Drive and just dumping them into folders, without actually putting in the time and effort to understand what each folder is for. It doesn't help that I am wearing 3 hats in the organisation, part of being in a family business you see? and the context is lost even within my own head. Essentially there was little thought behind it - and that is my own issue to get through. WIN: The automation project I am working on via n8n for work is going extremely well, I am happy with the AI Output that is being called, now working with our in-house dev to get the output into our own software and it is very exciting, because it will probably be saving around 2,500 minutes a month across the whole organisation, and more as we scale - so I am happy there. Things to Improve: What I am not happy about is that I've been using ChatGPT online, rather than codex and using the ICM Structure. So there's been a lot of back and forth, of context loss, and repushing. My own fault I know. Next Steps I tihnk the next step for me, after I review the Foundations again, is to actually start my workspace small, start it with the basics - speerate the folders into my roles, then within those roles, sperate the folders into businesses, then go into the layers from there. Or is that too much, again, lack of foundational knowledge - I see that. Anyway, just wanted to ramble, wil go back through foundations get my head on straight! Over Arching Goal: How do I deploy these automations that I am creating, for the business to run more efficiently, so that the whole team can use them? - That's where I get stuck (Because I am jumping ahead, that can be figured out eventuially). Thanks for the community for being awesome - appreciate you all.

Wondering how to effectively screen for malicious stuff in AI beyond just reading the .md files and stuff because there can be a lot of them. And for some of the opensource tools being installed via Node.js npm commands, how do you screen those before they get installed? Saw a thing going around about the Shai Halud worm and it looked new enough to be concerning but old enough to not be sure if it was fixed already. But definitely feels like the era of early internet where you had to be careful of trojan horses and image files with .exe endings.

I spent two years on ChatGPT thinking I was the smartest person in the room. I was not the smartest person in the room. A few weeks ago I fell down a rabbit hole - Interpretable Context Methodology. People building things I didn't have words for yet: doctrine documents, persistence layers. So naturally, I did what any sensible person does when they encounter something they don't understand. I started building it immediately. I had cement. No foundation. No walls. No idea what I was constructing or why. Just a bag of cement and a lot of confidence. Two to three days. Four to five hours a day. I built a system I couldn't explain to anyone, including myself. Same energy went into my first brand voice doc. Wrote it, handed it straight to Claude, thought the output was genuinely brilliant at 12 at night. Came back the next morning to start recording - Sounded nothing like me. Turns out you're supposed to test a brand document before you generate from it. Nobody tells you that. They assume you already know. I did not already know. Which is crazy to think about but we will side table this for now 👀 😂. Here's what two weeks of learning the hard way actually taught me: The tool isn't the problem. The thinking is the problem. And fixing the thinking - slowing down long enough to understand what you're building before you build it - changes everything about what comes out the other side. I'm just another business owner in South Africa. Not a crazy developer. Not super technical. I can occasionally English - and, well apparently, that's enough. There have been a few people in this community that have really changed the way I approach my day-to-day and I just want to again say thank you for helping me level up, and always being willing to lend a helping hand. @Bas Rosario @Curtis Hays