Building AI systems, documenting the process, sharing what works.
Last week I wrote about being messy, not sloppy. About stopping to reorganize before pushing forward. About the boring, unsexy work of building systems. This week I built on top of those systems. And something clicked. I spent a morning
Nobody has this figured out. I certainly don’t. But I think I’m closer than most, and what I’ve learned so far is worth sharing , not because I have the answers, but because the journey itself is the lesson. I’ve
Microsoft’s AI leadership just said most white-collar work has a 12 to 18 month expiration date. Paul Roetzer and Mike Kaput broke this down on episode 198 of The Artificial Intelligence Show and I’m sitting here nodding my head the
Two months ago, this wouldn’t have been possible. Website audits. Implementation roadmaps. Site restructuring plans. Developer task lists with exact fixes. The kind of work that used to take days of grinding through tedious, boring, exhausting details. Now? Brain to
I went for a six-mile run this afternoon, and somewhere around mile three, it hit me. I’m a 1990s NBA power forward. Stay with me here. The Dirty Work Guys Charles Barkley. Charles Oakley. Dennis Rodman. Larry Johnson. Alonzo Mourning.
The first week was perfect. I built a team of AI agents. Chief of Staff, Architect, Content Capo. Communication running through Telegram. Everything humming. Things getting done that used to take weeks happening in hours. It felt like strapping rockets
Two days ago I added a second agent. Yesterday I optimized token costs and workflow. Today the crew became something different: an actual team. Not agents running in parallel. A team. With handoffs, collaboration, quality standards, and the kind of
530 pounds. Drinking and smoking for nearly 20 years. I showed up to work. I did my job. I held all my responsibilities. I’m just a massive human being, and for the longest time, things didn’t seem to affect me
Day 1 went well. Day 1.5 is when the bill comes. Nobody skips it – they just don’t write about it. Here’s what token burn taught me about building real AI systems.
I spun up a second AI agent. Here is what I learned about building a multi-agent setup and why the same principles that apply to managing a real team apply here too.