In this module, we will explore the foundations of generative AI, large language models, and Semantic Kernel while comparing key AI frameworks and understanding how AI agents enable intelligent business applications through scalable and maintainable architectures.

In this module, we will set up the complete development environment by installing .NET, configuring Azure OpenAI resources, creating a starter solution, and securely managing application settings to establish a strong foundation for building Semantic Kernel applications.

In this module, we will build a functional AI chat application using Semantic Kernel by configuring Azure OpenAI services, implementing conversational workflows, managing chat history, and organizing the application into reusable components following best development practices.

In this module, we will explore prompt engineering, Semantic Kernel plugins, reusable prompt templates, personas, and prompt-backed functions to build intelligent AI applications that deliver dynamic, customizable, and business-focused interactions.

In this module, we will develop native Semantic Kernel plugins that integrate real business functionality, improve AI tool discoverability, support automatic function invocation, and follow best practices for creating scalable and maintainable AI solutions.

In this module, we will integrate Semantic Kernel into an ASP.NET Core application, build supporting business features, and develop a context-aware chat assistant that leverages application data to deliver more relevant and intelligent user interactions.

In this module, we will enhance the AI assistant by implementing persistent storage, user authentication, conversation history management, and contextual memory, enabling personalized and continuous AI experiences across user sessions.

In this module, we will implement intelligent document processing capabilities by building upload workflows, extracting text from PDFs, processing scanned documents with OCR, and creating preprocessing pipelines that prepare content for AI-powered search and analysis.

In this module, we will implement Retrieval-Augmented Generation (RAG) by preparing document embeddings, building semantic search capabilities, retrieving relevant knowledge, grounding AI responses with trusted sources, and creating a document-aware chat assistant that delivers accurate, transparent, and context-rich answers.