Introduction to the fundamentals of Artificial Intelligence: difference between AI, ML, and deep learning; basic data and metrics; stages of an ML project; risks and bias. Overview of Azure AI services and real-world use cases.

Creating ML experiments with Azure Machine Learning: workspace, datasets, and compute; training with notebooks or AutoML; model evaluation, registration, deployment, and monitoring within the MLOps lifecycle.

Image and document recognition with Azure Vision services: classification and object detection, OCR, and data extraction from documents; when to use prebuilt or custom models and how to interpret the results.

Text analysis with Azure Language: language detection, sentiment analysis, key-phrases, entity recognition, summarization; introduction to translation and conversational models, with a focus on quality and ambiguity.

Fundamentals of Generative AI on Azure: prompt design, system/message roles, temperature and top-p parameters, content safety. Introduction to embeddings, semantic search, and RAG for grounded responses with company data.