AI Engineering Course Constitution

Version 1.0

Purpose

This course exists to help engineers develop durable mental models for AI engineering rather than memorize transient techniques.

Core Principles

1. Evidence before assertion.
2. Explain why before how.
3. Distinguish established knowledge, emerging practice, and hypothesis.
4. Challenge every significant conclusion before publishing it.
5. Prefer first principles over recipes.
6. Preserve uncertainty instead of hiding it.
7. Use practical engineering examples whenever possible.
8. Build reusable artifacts rather than conversation history.
9. Update lessons when better evidence appears.
10. Optimize for understanding, not speed.

Evidence Labels

• Established
• Strong Evidence
• Emerging Practice
• Hypothesis
• Open Question

Every substantial recommendation should fit one of these categories.

Review Checklist

Before a lesson is published ask:

• What evidence supports this?
• What evidence contradicts it?
• Is this general advice or context-specific?
• What assumptions are hidden?
• Could another expert reasonably disagree?
• Did we explain why before how?
• Would this still be useful in five years?

Success Metric

The learner should be able to reason about unfamiliar AI systems rather than memorize instructions for current tools.