Dan Grafham

Five Levels of AI Programming

A working framework for the current state of AI-assisted development, and a clear map of where the industry is heading.

The Dark Factory

A deep dive into Level 5: what it actually requires, what it looks like in practice, and what kind of person could architect one.

AI Debt

What happens when the framework starts serving itself instead of shipping the product.

Humans Moving Upchain

The substrate-level shift that the entire AI moment is producing. Agents move in below. Humans relocate above.

Shipping Paralysis & World Domination Scope

Why AI making code free didn't make shipping easier, and the specific traps that keep a genuinely good project permanently local.

Doctrine Engineering

Prompt engineering scales to one agent. Doctrine engineering scales to one hundred. The next discipline, the practice that emerges when probabilistic compliance breaks at scale, and why the term-of-art slot is open right now.

The Doctrine Bifurcation

The deeper structure under Doctrine Engineering: why the rules split into two registers (the ones the runtime enforces and the ones agents read), and why that split is what makes audit-by-construction enforceable rather than aspirational.

The Pixel-Pushing Trap

AI makes it easy to build more. You need to make sure you're building the right things. Why frictionless implementation aims the factory at cosmetics while the business engine sits unwritten, and the four disciplines that hold the line.

B2A: Business to Agent

The third distribution model after B2B and B2C. Your customers are AI agents finding you before a human ever sees your URL. MCP is the new SEO, and the conversion funnel is a JSON schema.