Principles

The 10 fundamental principles of the Problem-Driven AI methodology.

"Those who stand for nothing fall for anything." — Alexander Hamilton

A methodology without principles is just a sequence of steps. These ten principles are the non-negotiable criteria that separate disciplined thinking from improvisation. They don't tell you what to build — they tell you when you're deceiving yourself.

1. The problem is sacred

Never assume you understand the problem. The real problem is rarely the one presented in the first conversation.

2. The client doesn't know what they want, but knows what they feel

Don't ask the client what solution they need. Ask them what hurts, what slows them down, what costs them.

3. Without organizational consensus there is no context

You can't write precise context for AI if there's disagreement within your organization about the problem or solution.

4. Context Engineering is design, not writing

Writing context for AI is not summarizing what you know. It's making deliberate decisions about what to include, exclude, and how to structure.

5. Building is a symptom, not a goal

Building is the natural consequence of having thought well. It's not an achievement in itself.

6. Speed is a reward, not a strategy

The speed AI offers is the result of having done the prior work well, not the goal of doing it.

7. The market always knows more than you

No discovery, however deep, replaces real contact with the market.

8. Iterating is not repeating

Each iteration must incorporate new information. If you return to the same point without learning something new, you're not iterating.

9. Context is a living asset

The context you build for AI is not a static document. It evolves with each iteration, market signal, and new learning.

10. Clarity is the only luxury you can't afford not to have

In every phase of this methodology, clarity is the scarcest and most valuable resource.