AI Engineering is fundamentally about system building. It is the transition from demos to production-grade Python systems that must be scalable, reliable, and testable. In my experience, one way to achieve this consistently with AI-generated code is to stop coding first —and start specifying first. Spec-Driven Development (SDD) is a practical methodology for AI-assisted development. It is not about heavy bureaucracy; it’s about creating a "Single Source of Truth" that both humans and AI agents can rely on.

In this talk, I will show how I use existing tools like OpenSpec and SpecKit to develop my own AI-assisted workflows that actually fit my way of thinking. I will present an explicitly opinionated comparison of these tools—not to choose a winner, but to understand the trade-offs:

• SpecKit: My choice for larger features with many dependencies.
• OpenSpec: My choice for smaller features, rapid prototyping, or bug fixes.

The talk is grounded in real-world features I have developed in my daily work as an AI Engineer, particularly in building RAG systems.

What You Will Learn:

• What is Spec-Driven Development? A clear breakdown of the spec-first workflow.
• The Paradigm Shift: Why "specifying" may be the new "coding" in a world of Large Language Models.
• The Subjective Tool Guide: A practical comparison of SpecKit vs. OpenSpec regarding their technical benefits and trade-offs.
• Customization: How to adapt existing tools to fit your personal engineering workflow.