Thinking Through AI

Every Department's Agent Map Looks the Same

I mapped agents onto twelve company functions. The maps converged on one design, and the real work turned out to be the refusal list.

Jul 12 • Thinking Through AI

What I Set Up to Run Parts of My Life With Agents

I wired agents to my money, time, health, and learning. The surprise wasn't saved time. It was a lighter head.

Jul 5 • Thinking Through AI

June 2026

An Agent That Opens Its Own Gate Has No Gate

The hard part of an autonomous coding loop isn't the agent — it's making the human checkpoint impossible for the agent to skip. Notes from a first…

Jun 28 • Thinking Through AI

How I Built a Harness to Run a Company of Agents

A goal in, a shipped feature out. The agents, what each one produced, the runtime we built to run them, and where it broke. A small, honest experiment…

Jun 21 • Thinking Through AI

1

On Prompting Well

William Zinsser wrote one of the best books on context engineering in 1976. He just didn't know it was about machines.

Jun 14 • Thinking Through AI

Organizational memory is the first agent system I would build

Every agent answers from something. Make it the company.

Jun 7 • Thinking Through AI

May 2026

I Wrote a Plan. The Work Steered It.

What steering through one project taught me about how engineering work actually happens once AI is in the loop.

May 31 • Thinking Through AI

Engineering Orgs Aren't Adopting AI. They're Rebuilding Around It.

Generation is cheap. Judgment is scarce.

May 17 • Thinking Through AI

2

April 2026

Skills to Survive the AI Wave

A collection of thoughts on what actually matters

Apr 18 • Thinking Through AI

The Agentic Mindset

How to make yourself 10x with AI.

Apr 11 • Thinking Through AI

The Agent Cost Stack

What it actually costs to run an AI agent in production.

Apr 5 • Thinking Through AI

March 2026

Multi-Agent AI Is Slower, Costlier, and Sometimes Finds Better Answers

I built three AI agents to plan a trip and raced them against one.

Mar 29 • Thinking Through AI