Industry-Relevant GenAI Course

Outcome: This week will help you understand the current business landscape of Generative and Agentic AI, while equipping you to identify key industry trends, opportunities, and challenges in their adoption. 

Topics Covered: 

• Overview of Generative AI: Definition, evolution, and impact on various industries. 
• Overview of Agentic AI: Definition, characteristics, and potential applications. 
• Market trends and business opportunities in GenAI and Agentic AI. 
• Case studies of successful GenAI and Agentic AI implementations across different sectors 
• Sample Case Study: Understand the architecture of Real time grammar/spelling correction tool and how Generative AI enhance performance of tool,

Topics Covered: 

• Prompt Engineering Basics: Principles and best practices 
• Text Prompts: Techniques for generation, summarization, and conversation 
• Speech Prompts: Using Azure AI for speech-to-text and text-to-speech 
• Image Prompts: Guiding image generation and manipulation 
• Advanced Techniques: Zero-shot, Few-shot, Chain/Tree-of-thought, self-consistency, Rephrase & Respond 

Sample Case Study: Use Prompt engineering for customer support, personalize marketing, and create interactive product visuals

Outcome: This week, you will learn to develop Python scripts for interacting with Azure OpenAI and handling text data (Coding Track), as well as use Azure PromptFlow to design, test prompt-based applications without extensive coding (No-Code Track) 

Topics Covered: 

Coding Track: 

• Text in Python: Strings, common string methods 
• File Handling: Reading/writing files, working with .txt, .csv, .json 
• Text Manipulation & Cleaning: Advanced string operations (find/replace, extract, split/join), removing unwanted characters, handling dates and numbers in text 

No-Code Track: 

• Promptflow Basics: Introduction, key features, setup, and integration 
• Navigation & Workflows: Exploring the interface and building basic workflows 

Sample Case Study: Cleaning and Analyzing Survey Responses at HealthTrack

Topics Covered: 

• Explore business use cases for text classification and implement LLM-based classification workflows. 
• Evaluate sentiment and aspect-based classification using accuracy metrics. 
• Understand business applications of text generation and implement LLM-driven text-to-text workflows. 
• Assess text generation outputs using ROUGE, BERTScore, and LLM-based evaluation. 

Sample Case Study: Generate automated summary reports and personalized product recommendations for customers

Outcome: This week, you will learn to enhance AI solutions using embeddings, vector databases, and LLMs to build efficient Retrieval-Augmented Generation (RAG) systems for effective question answering. 

Topics Covered: 

• Explore business use-cases for RAG 
• Build RAG workflows using LLMs 
• Learn embeddings and how to choose embedding models 
• Overview of vector databases 
• Manage vector databases (CRUD operations) 
• Implement RAG for question answering 

Sample Case Study: Automating Financial Report Generation at FinInsight using RAG

Outcome: This week, you will learn to implement Retrieval-Augmented Generation (RAG) for multimodal inputs, evaluate RAG model outputs, and mastering advanced techniques to improve the quality and performance of RAG systems in business applications. 

Topics Covered: 

• RAG with multimodal data sources (data with text, images and tables) 
• Evaluating RAG outputs (Ragas and RAG Triad) 
• Advanced Retrieval Mechanisms ( Hypothetical Questions, Query Expansion) 
• Advanced Generation Mechanisms (Reranking, Information Compression) 

Sample Case Study: Enhancing Patient Data Insights at MedCare using Advanced RAG

Outcome: In this week, you'll learn to deploy and serve Large Language Models, optimizing them for real-world use. You'll also gain a thorough understanding of the end-to-end AI application workflow, covering prompt engineering, building interfaces with Streamlit, containerizing with Docker, and hosting models. 

Topics Covered:

• Master the deployment, management, and serving of Large Language Models (LLMs) 
• Gain expertise in configuring and optimizing models for high-volume, high-performance tasks 
• Use Streamlit to design user-friendly interfaces for AI applications 
• Learn to Dockerize applications for seamless containerization and deployment 

Sample Case Study: RAG Model Deployment for E-commerce Product Description Generation

Outcome: This week covers the key differences between AI agents and LLM assistants, the evolution and use cases of generative AI agents, and the core functional modules of AI agent architecture. You will learn agentic design patterns, explore single-agent systems, and gain hands-on experience in designing and building simple autonomous AI agents. 

Topics Covered: 

• Generative AI Agents: Definition, use cases, and LLM vs. agent workflows. 
  
  
• LLM Workflows with LangGraph/CrewAI: Sequential, parallel, and conditional workflows. 
• AI Agent Architecture: Key components - planning, reasoning, execution, and memory. 
• Types of Agents: Reflex, model-based reflex, goal-based agents. 
• Agent Building: Python (LangChain with Azure) and no-code (Azure AI Agent Service). 

Sample Case Study: Generative AI Agent for Automated Lead Generation and Customer Engagement

This project involves deploying a Generative AI Agent to automate customer support for an e-commerce platform. The AI will handle common queries, process return requests, and provide personalized recommendations. It covers the deployment, optimization, containerization, and UI design of a high-performance support agent capable of managing high volumes of customer interactions

Topics Covered: 

• Introduction to MLOps and LLMOps: Differences and similarities. 
• LLM lifecycle: Experimentation, training, deployment, monitoring. 
• Model versioning and registry in Azure Machine Learning. 
• Deployment of LLMs as endpoints (Coding Track) and through PromptFlow (No-Code Track). 

Sample Case Study: Automating Healthcare Documentation with LLMOps at HealthDocs

Topics Covered: 

• Monitor LLM performance: Latency, throughput, accuracy. 
• Logging and observability for LLMs in Azure. 
• CI/CD pipelines for LLMs (Coding Track) and automated deployments with PromptFlow (No-Code Track). 
• Security best practices for LLM deployments on Azure. 

Sample Case Study: Optimizing LLM Deployment and Monitoring at FinTech AI