Skip to content

Field notes

Practitioner essays on building production software with AI agents.

Explore the engineering, economics, and organizational decisions behind software delivery. Start with a selected essay or browse the full collection.

Featured essay

The Agents Are Fine.
Your Codebase Is a Mess.

Your repository teaches agents how your team works. Clear boundaries, reliable tests, and a working build give them a better example to follow.

Read the essay

Start here

Five ways into the work.

  1. Economics

    Picking the Right Model Won’t Fix Your Product Roadmap

    Judge AI spending against customer value, labor costs, and delivery outcomes.

  2. Delivery

    Where delivery waits

    Map the work and waiting time to find what actually slows delivery.

  3. Quality

    Stop Reviewing Code. Start Proving It Works.

    Separate review rituals from evidence that software behaves correctly.

  4. Organizations

    Dear Developer: Why AI Adoption Is Slow

    Understand how trust, authority, and production risk affect adoption.

  5. Governance

    The AI Soft Ban Assessment

    Check whether everyday policies actually let engineers use approved AI tools.

Keep reading

Latest articles

Explore the archive

One useful note a week

Get one good email a week.

Short notes on AI-native software leadership. No launch sequence. No funnel theater.

Every article, narrated. Listen while you ship. →
From the Author

Corporate fiction

Three books. One operating problem. No clean hero.

Read 2028, Meridian, and AgentDrivenDevelopment.com’s Survive free online.

Read free online →