miyagi

Why we included this project

Miyagi is a demonstration, not a product, and it's upfront about that: the point is to see how Microsoft's Copilot stack fits together in working code. It walks through a retail-style scenario where generative and traditional ML use cases coexist, combining Semantic Kernel, Promptflow, LlamaIndex, and LangChain with vector stores and fine-tuned models like Llama2 and Phi-2. The workshop material that ships with it covers prompt-engineering patterns such as chain-of-thought and retrieval-augmentation, so engineers new to AI-infused experiences can learn the ideas from code rather than slides. If you're sizing up the Azure AI ecosystem and want a concrete tour of the moving parts before you commit to an architecture, this is a good read even though it's explicitly a demo, not something to run in production.