The Origin
I spent twenty years training for this without knowing it.
It started with Duke Nukem and Zelda, then WoW addons where I spent hours tweaking config files and installing mods to make the game work exactly how I wanted. That was my first taste of bending computers to my will, and I was hooked.
WoW raids until 3am, Dark Souls bosses where you die a hundred times and keep going anyway, leading a guild of twenty people through encounters where one mistake wipes the group. Early reps in systems thinking, pattern recognition, and staying calm under pressure.
// the_day_job.sh
My work focuses on making AI reliable in environments where failure carries real consequences. During the Ukraine-Russia war, I helped install NATO's SECRET network at the Pentagon. Today, I manage AI infrastructure for the intelligence community—over 100 GPUs powering 50+ production applications that support active operations worldwide.
Ten years ago, I started pulling cables in data centers. Now I'm deploying frontier AI models on classified networks, having worked directly with Google engineers to bring Gemini and Gemma into air-gapped environments with strict access controls and no direct vendor support.
That's where reliability transformed from an abstract metric into something I feel viscerally. Infrastructure teaches us about observability, deterministic deployments, and graceful failure handling. AI systems desperately need these same patterns.
// the_transition
Ten years building platforms taught me that reliability isn't magic—it's discipline. Capacity planning, validation gates, observability, isolation. These patterns made infrastructure boring (in the best way).
In 2023, I started applying the same discipline to AI agents. Not just using tools—building the methodology that makes them reliable.
DevOps made deployments boring. AgentOps makes AI agents boring—so reliable you leave them running 24/7, like electricity.
DevOps made deployments boring. AgentOps makes AI agents boring.
// going_public()
Then the thesis evolved. It's not agent orchestration — it's context orchestration. The high-leverage problem isn't how agents talk to each other. It's what's in the context window when they start working.
I learned Go to prove it. Built a Kubernetes operator in 11 days. Shipped 27 PRs upstream to Steve Yegge's Gas Town — 8 merged, 2,400+ lines of Go. The invisible builder went public.
19 articles. 5 devlogs documenting every failure. A Go CLI that ships the methodology as installable tooling. Not just writing about it — building in the open with receipts.
I used my own workflow to build the curriculum — Go training with Matrix mythology and infrastructure metaphors, assembled by parallel agents. The forge building the builder.
// building_the_forge
I didn't just learn to use AI tools. I spent $10,000 and 100 days figuring out how they break—and how to prevent it.
The result: 12-Factor AgentOps, the 40% Rule, the Knowledge Flywheel, and a system that closed 1,005 issues in 7 days.
I build the forge, not just the weapons.
“The cave you fear to enter holds the treasure you seek.”
— Joseph Campbell
The Hero's Journey isn't just a story structure; it's a map for growth, and this is mine.
// myth.create()
Campbell gave me the map and the permission: follow your bliss because the hero's journey is real. Jung showed me what the journey actually is, which is integrating the shadow and becoming whole.
I'm writing my own myth instead of waiting for someone else to tell it, choosing the symbols, the language, and the aesthetic that resonates.
The rest of my mentors are in the library, and I'll let them speak for themselves.
// shadow.integrate()
I failed out of Virginia Tech and stopped going in 2014. The wound was specific: I told myself I'm not a real engineer because I can't code like they can.
It took me six years to finish my undergrad, and I got my Masters in 2023. I didn't find a workaround; I did the hard thing the hard way.
Then vibe coding emerged, not as a crutch for someone who couldn't code but as an amplifier for someone who earned it. I didn't skip the boss fight; I beat it and then got the power-up.
I didn't skip the boss fight; I beat it and then got the power-up.
// hero_journey.config
> Puzzles → The Mind → Learning to Learn
My childhood was puzzles and heroes. Games, dungeons, adventures. After I failed at VT, I was humbled—and realized my favorite puzzle was my own mind. That's when I started learning how to learn.
// integration.complete
The puzzle-solving never stopped—it just evolved. From Zelda dungeons to system architectures. From game optimization to mind optimization. The failure at VT taught me the most important lesson: the mind is the ultimate puzzle, and learning how to learn is the meta-skill that unlocks everything else.
The Mentor Archive
129 mentors organized by pillars and questions.