I built this project to test Grok Bot and Atomic. I believe I went overboard lol still this is a good sample case of my weaknesses. It is far from over. It does not auto update yet and I'm still working on it. https://battle-harnesses.vercel.app/ 1. What are you trying to make happen? I want to use one real project, **Battle Harnesses**, to learn how a senior developer would frame and organize a software project from the beginning. Battle Harnesses is intended to be a public guide to AI coding harnesses. Behind the website, there is a private research system that gathers and evaluates source-backed information about the products. The website then publishes a useful view of that research. There is also a separate public pack containing only the material that is safe and appropriate to distribute. For this session, I am not mainly asking for help fixing the current repository. I want to reconstruct how I should have thought about the project before building it: - how to turn the product idea into clear system boundaries; - how to choose the smallest useful version; - how to define sources of truth and the data flow; - how to separate private research, public product output, and local AI working memory; - how to decide what belongs in GitHub and what must remain local; - how to define tests and proof before delegating work to AI agents. I would like to leave with a simple project-start method that I can reuse on future projects. 2. What have you tried already? I began by researching the product landscape and building the website with AI coding agents. Over time, the project developed several layers: - source-backed research ledgers and product dossiers; - generated website data; - a React/Vite website with product, comparison, and guidance views; - a private development repository; - a separate public distribution pack; - a local-only `AI_OS` layer intended to preserve decisions, current state, and instructions for AI agents.

The official video is out and the full write up is in the classroom. https://youtu.be/kAR91DlnCKQ

Hi all! First big shoutout to Ray for leading, facilitating, and inspiring us all on this journey!! I'm going to be little transparent here, as Ray DM'd me with encouraging me to share a little about what's happening in my world. Rather than reply direct, I thought I would just put this out as here as an intro... Thanks Ray! Interesting times for me. 18+ years in the software engineering space, moving into management, sr leadership and the last four as CIO of a chemical mfc co., and the last 8 months watched private equity, erase / replace all executive and sr managers, I was the last to be laid off. Now in my 2nd week of being unemployed (but self-employed). BTW, although that was some of the toughest times in my career, I have no hard feelings, this is business. My four years as CIO was extremely successful and valuable for me and the teams I built and worked with. But, I did see the writing on the wall early, and started revitalized my own business, Pinnacle Pathways, www.kalenhowellsr.com. Currently I'm building for a MFC CTR out of Boston Mass, a custom SaaS-like application, that is going very well, with some good opportunities following a successful production launch that should happen in the next 3 - 5 weeks. With all that said, I'm on a tight budget and squeezing everything I can out of ChatGPT 20x Pro and Claude 10x sub. Just yesterday I had to spin up a 2nd ChatGPT (10x) sub. I've been a long-term Codex user, and have always had Claude in the mix to some degree or another. A side from building for clients, I have a lot of other business development work going on, including working to 'agentify' both personal and business operations. Practicing Agentic Engineering - to build scalable, maintainable, production-worthy applications, is where I'm focused. Anyway... its tough to get time to share the internals of my work, thinking, challenges, and evolution in AI... but here ya go... hope to get into some deeper technical topics soon.