Overview

This Nanodegree program equips you with the skills to design, build, and deploy autonomous AI agents. Unlike standard LLM courses that focus on text generation, this program focuses on Agentic AI—enabling AI to perceive, reason, plan, and act. Leveraging the Microsoft Azure AI ecosystem, you will learn to implement robust prompting strategies, design agentic workflows, integrate external tools using Microsoft Semantic Kernel, and orchestrate multi-agent systems that collaborate to achieve complex goals within Microsoft Foundry.

Syllabus

Prompting for Effective LLM Reasoning and Planning with Microsoft Foundry

Go beyond simple prompts and learn to design robust, Azure-native AI agents. In this course, you’ll use Microsoft Foundry and the Agent Service to build role-based agents that reason, plan, and act with real-world tools and data.

You’ll master advanced prompting techniques—including Chain-of-Thought, ReAct, and systematic prompt refinement—to turn raw model capabilities into reliable, controllable behavior.

You'll chain agents into multi-step workflows, adding validation gates and feedback loops so agents can inspect, correct, and improve their outputs.

Through focused, hands-on labs, you’ll apply these patterns to a realistic supply chain scenario, culminating in a multi-tool agent that can analyze data, call utilities, and support complex operational decisions end to end.

Agentic AI Workflows with Microsoft Azure

This course offers a comprehensive exploration of advanced workflow implementations using Azure's capabilities. Beginning with foundational concepts, you will learn about practical applications such as implementing agentic workflows using the Semantic Kernel, utilizing prompt chaining for enhanced interactions, and applying routing workflows for efficient task management. Additional focus will be on parallelization techniques with Python, as well as developing evaluator-optimizer workflows to refine results. Finally, you will learn about the orchestrator-workers pattern for seamless workflow coordination and leverage AgentQuant for insightful data analysis.

Building AI Agents with Microsoft Azure

This course explores the intricacies of constructing AI agents utilizing Microsoft Azure. You will embark on a journey through the fundamentals of agent design before mastering tools that extend agent capabilities. Key focus areas include the implementation of structured outputs with Pydantic, state management, and memory systems, both short- and long-term. The curriculum emphasizes integration with external tools and databases, particularly through Cosmos DB and Bing Search to enhance functionality. Additionally, you will explore evaluation techniques for agents. By the end of the course, you will build a sophisticated AI travel concierge agent, contextualizing their learning in a hands-on project.

Multi-Agent AI Systems with Microsoft Azure

This course offers a comprehensive exploration of designing and implementing multi-agent architectures. Starting with an introduction to course concepts, students will learn to leverage the Semantic Kernel for effective agent architecture creation. Key lessons focus on agent orchestration, optimizing routing and data flow, and managing state within multi-agent environments. Advanced topics include orchestrating agents collaboratively and employing Retrieval Augmented Generation (RAG) to enhance data retrieval in agentic systems. The course culminates with a practical application of these concepts in the VectraBank project, showcasing agentic RAG tailored for banking applications.