This Short Course was created to help Machine Learning and Artificial Intelligence professionals accomplish end-to-end integration of LLMs with digital twin environments using Azure Digital Twins as the reference implementation and a retrieval-augmented generation (RAG) pattern.

. By completing this course, you'll be able to convert plain-language prompts into ADTQL statements, wire up a live-data RAG pipeline, and confidently validate outputs against schema and permission rules on the job. By the end of this course, you will be able to: Apply the provided tool-calling prompt to convert a natural-language query into an Azure Digital Twins Query Language statement Configure a retrieval-augmented generation pipeline that enriches LLM responses with live twin state and metadata citations Evaluate the generated twin responses for schema compliance and permission adherence using the guardrail checklist This course is unique because it goes deep on one high-leverage integration pattern — Azure Digital Twins plus LLM tool-calling plus RAG — rather than surveying the full digital twin landscape, giving you a repeatable workflow that demonstrates how LLMs can query and retrieve information from digital twin environments using tool-calling and RAG techniques. To be successful in this course, you should have a background in Python programming, REST APIs, and foundational knowledge of LLMs and cloud platforms at a CB2 intermediate level.