On April 10 I was trying to clean up my Instagram.Tighten the cover graphics. Build a repeatable system. Stop redesigning the same template every week. A one-afternoon job. What actually happened was the first real test of an architecture I had been sketching for writing work — and I tested it on design. I built a sandbox, gave it a governing file, separated references from working material, wrote one clean brief… and let it run. Fifty covers came back in minutes. Same palette. Same typography. Same visual language. None off-brand. That was the moment something shifted. Not because of the output — but because of what it proved: Once an architecture is clear enough, the question is no longer “what can I delegate?”It becomes “what is now worth building?” In 21 days, that small test turned into: - Three working teams (orchestrator, content, design) - Four books shipped or shippable - A new website - Two additional teams already scoped Same operator. Same hours in the day. For those who asked about mindset and process — this is the real answer: 1. I stopped thinking in prompts and started thinking in systems.The model is not the asset. The structure around it is. 2. I separated thinking from doing.The orchestrator doesn’t write. It reads, structures, briefs, and validates.The workers execute. They don’t improvise outside their lane. 3. Everything moves through briefs.No direct “do this” requests. Every handoff is:task → context → scope → acceptance → return checklist.That alone removed most iteration cycles. 4. Context is layered, not dumped.Reference material lives separately from working material.The model doesn’t have to “figure out what matters” — it’s already decided. 5. The human sits outside the system.Not inside prompting.Outside — validating outputs and deciding what ships. The clearest proof this wasn’t theory came from the hardest task I’ve ever tried to coordinate: Mapping TCM meridians, Thai Sen lines, and Anatomy Trains on the human body — in one consistent visual language.

So, after people's comments about longer breakdowns and more graphics in my posts, I decided to make a site where I can share downloads and more visual breakdowns of work I'm doing. 8 hours from concept to live site. 5 sessions. None of them above 50% context. The site is https://www.aris-space.com/ Built on Next.js 15, Tailwind v4, MDX, Zustand and react-rnd, deployed on Vercel. Full breakdown here VVV https://www.aris-space.com/documents/discipline-and-process/building-aris-space I architected. Claude executed. // A<3

Following up on my previous post about automating month-end, I want to pull back the curtain on the project that really started it all. It involves a massive company reconstruction, a "manual hell" task, and a midnight breakthrough that tripled my productivity. The Problem: A Reconstruction Hangover On January 1, 2026, our company underwent a major reconstruction. Customers were assigned new sales reps, but the final list of who owned which account wasn't finalized until April. In the meantime, we kept invoicing as usual. The invoices were correct, but the Sales Rep field on the historical records was now wrong. To fix it, we had to go back and update thousands of already invoiced sales orders. The Manual Workflow (or: How to lose your mind): 1. Search for the Sales Order. 2. Click Invoice. 3. Click Rebill. 4. Change the Sales Rep. 5. Click OK. 6. Hit Esc to exit. 7. Repeat... hundreds (or thousands) of times. Enter Claude Code & Playwright I had just started using Claude Code on March 19th after watching @Jake Van Clief ’s videos. Two weeks later, this assignment landed on my desk in the middle of my usual accounting duties. Since I didn’t have backend API access to D365 F&O, I turned to the Playwright MCP. If I couldn't talk to the database directly, I’d have Claude "drive" the browser just like a human would. The Automation Logic: - Open Chrome to the D365 Sales Order URL. - Open the filters tab. - Add filter information (Customer account, dates for Q1 2026, and identifying which sales orders had the wrong rep). - Execute the "Rebill" click-path automatically. The "Aha!" Moment at 00:30 AM It worked, but it was real slow. D365 isn't exactly a speed demon. My boss was happy ("as long as we don't have to do it, I don't care how slow it is"), but I knew we could do better. Earlier that day, I was running it in one browser and it was taking forever. While the kids were finally asleep that night, I had an idea: Can I run this on more than one tab?