Practical use of AI/LLM

Spec-Driven Development Live

Sakari Nahi

Sakari Nahi

Sakari is the other founder and CEO of Zure, an Azure-focused company. He has been coding on .NET professionally since 2002. He's a dad of two, husband of one and likes roguelikes & text-based games. He's passionate about emerging technologies, distributed computing, and synergies thereof. Sakari is also a Microsoft Regional Director, and AI+Azure MVP. He organizes Finland Azure User Group and casts a pod Ikkunastudio in Finnish.

Zure designs, develops, and manages solutions on Azure, with offices in Finland, Belgium, Denmark, United Kingdom and Netherlands.

1 / 2

What happens when you build software with AI in front of an audience?

In this live session, we’ll ideate with the room and turn the idea into a working solution using Spec-Driven Development (SDD) and other AI development practices.

AI-assisted development is evolving quickly. Spec-Driven Development is one approach, but not the only one. Context engineering, harness engineering, AI Test-Driven Development, and agentic development are all concepts in their own right. In practice, you often end up combining many of them.

Today, we will explore these approaches with SDD at the center while trying to build something live.

This is not a polished demo. It is a real-time look at how software development is changing. We will move from an initial idea toward a more reliable implementation, and see what changes when you go from solo vibecoding to something a team could build on.

You will leave with practical patterns for guiding AI, structuring specs, and building in a way that’s repeatable, testable, and usable in real projects.