Skip to content

Working with Agents

From writing code to orchestrating AI agents — exploring the new role, real workflows, what breaks, judgment, context, and team adoption.

8 chapters
Chapter 1

From Programmer to Orchestrator: The Silent Revolution Almost Nobody Sees

How I went from writing every line of code to orchestrating AI agents — and why the biggest tech revolution is happening so quietly that almost nobody sees.

Chapter 2

The Hidden Job of the AI Era: The Art of Directing Agents

AI agents aren't productivity multipliers — they're judgment multipliers. Why direction matters more than the model, and what that means for engineering.

Chapter 3

The Permanent Hackathon: Why We Can't Stop Building

AI was supposed to give us more free time. Instead, it created an addictive building loop — backed by neuroscience, economics, and a meetup confession.

Chapter 4

The Agent Economy: When AI Gets Its Own Money

AI agents now have payment cards, wallets, email, and social networks. A new economy is forming — and it's not what I predicted in 2018.

Chapter 5

The Skill Layer: When Agents Stop Reinventing the Wheel

An agent that can install a skill from a URL stops reinventing the wheel. A field report on the standard agents are quietly building beneath the surface.

Chapter 6

The Harness Layer: The System Around the Model

Harness engineering is the new way to steer AI agents — the system around the model that checks its work and stops it repeating the same mistake.

Chapter 7

Deep Work Plan: Give Your Agent a Plan and a Harness

An agent nailed the first hour and drifted by the third. The fix wasn't a smarter model — it was a durable plan the repository itself could hold the work to.

Chapter 8

Loop Engineering: Automation in the Age of AI

Everyone's saying we should write loops, not prompts. Strip away the novelty and it's automation — with one new thing sitting inside the loop's body.

Series complete

8 chapters

Working with Agents

Working with Agents