Field notes
Field notes on installing AI capability one human at a time. The four layers. The retrieval contract. What a brain you own looks like in practice.
Pulled from M.L. Sebastian on Substack. Subscribe there to get them in your inbox.
June 20, 2026 · Latest
For about an hour on a Tuesday, I was certain the problem belonged to Cloudflare. Thanks for reading! Subscribe for free to receive new posts and support my work. It didn’t. The problem was mine, wearing Cloudflare’s face. And the hour I spent being wrong taught me more about …
June 2, 2026
There’s a concept gaining traction in the agent-building world called SOUL.md. The idea: your AI agent needs a structured document describing who you are, how you work, what your operating rhythms look like. He built an elicitation workflow, a 45-minute structured interview th…
Read essay →This essay is a course chapter in disguise. Start the free course
May 29, 2026
I was writing a memory file at 11pm on a Wednesday in April. Richardson, Texas. Third bourbon. The file was titled feedback_andres_copy.md and it contained three rules about how a specific client’s website hero section should handle language. Not the client’s rules. Mine. Rule…
Read essay →This essay is a course chapter in disguise. Start the free course
May 28, 2026
I run a persistent AI agent. Her name is Opelia. She manages my calendar, triages my inbox, drafts outreach, monitors my clients’ uptime, and runs overnight research jobs while I sleep. I built her from scratch. 40+ custom skills, a job queue, a Convex database, launchd schedu…
Read essay →This essay is a course chapter in disguise. Start the free course
May 27, 2026
The audit was the hard part. Or so I thought. Recently I published my AI dependency assessment, the five-layer breakdown of how deeply Branded Mayhem is wired into Anthropic’s infrastructure. The numbers were uncomfortable. Two to three months of focused migration work. Six ad…
Read essay →This essay is a course chapter in disguise. Start the free course
May 26, 2026
I've spent the last two posts pulling threads. The first one used Star Trek to explain why Anthropic's leaked always-on agent should terrify anyone building on AI platforms. The second one turned the microscope on myself — a formal risk assessment on my own AI dependency, publ…
Read essay →This essay is a course chapter in disguise. Start the free course
May 25, 2026
I published a post about the Conway leak and what Star Trek figured out about AI ownership thirty-five years before Silicon Valley did. The philosophical argument. The big question. Who owns how you think? Decent post. Got some traction. Thanks for reading! Subscribe for free …
Read essay →This essay is a course chapter in disguise. Course 02: Run Your Own Working Intelligence Audit
April 9, 2026
A graphic designer named Mike Okuda sits down to build control panels for the Enterprise-D. Gene Roddenberry gives him one note: simple. Logical. Throw out everything you think you know about starship consoles. Okuda does. He builds LCARS… Michael, seriously…what the f#$% is L…
Read essay →This essay is a course chapter in disguise. Start the free course
The catalog
br8n
