Generative AI Fundamentals With Microsoft Azure AI Foundry

In this video, you'll learn what Generative AI is, how it differs from traditional AI, and how it creates text, images, and more from natural language prompts. We'll explore real-world examples that showcase its powerful capabilities across industries.

In this video, we introduce the fundamentals of Generative AI—what it is, how it works, and why it’s a game changer. You’ll learn how generative models like large language models (LLMs) are trained to understand and produce human-like content from simple prompts.

We’ll also explore key use cases across industries and set the stage for hands-on learning with Microsoft Azure AI Foundry in upcoming lessons.

In this video, you’ll learn why crafting clear and specific prompts is essential for getting accurate, relevant, and high-quality outputs from language models. We’ll explore examples of good vs. poor prompts, common mistakes to avoid, and tips for guiding Generative AI effectively.

Mastering prompt clarity is a key skill in getting the most out of any AI model.

In this video, you’ll explore practical techniques to enhance the quality of responses from Generative AI models. Learn how to use structured prompts, provide context, apply few-shot examples, and guide tone and style. We’ll walk through real examples to show how small prompt changes can produce much better results.

These techniques will help you get more accurate, useful, and consistent outputs from language models.

In this video, you'll learn what Artificial Intelligence (AI) is, how it works, and the different types of AI, including narrow, general, and generative AI. We’ll explore how AI mimics human intelligence to solve problems, make decisions, and power modern applications—from chatbots to self-driving cars.

This foundational overview sets the stage for deeper learning in AI and its real-world impact.

In this video, you’ll explore practical techniques to enhance the quality of responses from Generative AI models. Learn how to use structured prompts, provide context, apply few-shot examples, and guide tone and style. We’ll walk through real examples to show how small prompt changes can produce much better results.

These techniques will help you get more accurate, useful, and consistent outputs from language models.

In this video, you'll learn about the key tools and environments available for developing Generative AI solutions on Azure. We'll explore Azure AI Studio, notebooks, SDKs, REST APIs, and integration with tools like Visual Studio Code.

You'll understand how these environments support building, testing, and deploying AI models efficiently and securely.

In this video, you’ll learn what Responsible AI means and why it’s essential in today’s AI-driven world. We’ll explore the core principles—fairness, reliability, privacy, safety, transparency, and accountability—that guide ethical AI development.

You’ll also get an overview of Microsoft’s approach to Responsible AI and how these principles are embedded into tools and workflows to ensure trustworthy and safe AI solutions.

In this video, you’ll explore the four-stage framework for implementing Responsible AI: Map, Measure, Mitigate, and Manage. Learn how to identify potential harms, evaluate model outputs for risk, reduce the impact of those harms, and establish governance to ensure ethical and accountable AI deployment.

This structured approach helps integrate responsibility into every phase of your AI solution.

In this video, you'll discover why Generative AI is one of the most transformative technologies of our time. Learn how it can generate text, images, code, and more from simple prompts—enabling innovation across industries like healthcare, education, entertainment, and business.

We’ll explore its capabilities, real-world impact, and why it's reshaping how we interact with technology.

In this video, you'll learn how to proactively plan for responsible use of Generative AI. We’ll cover best practices for identifying potential risks, setting ethical guidelines, and aligning AI development with fairness, privacy, and transparency principles.

You'll also explore how to embed responsibility from the start—ensuring safe, trustworthy, and accountable AI solutions.

In this video, you’ll learn how to assess and measure potential harms in Generative AI outputs. We’ll walk through methods for detecting bias, misinformation, and safety risks in generated content.

Understanding this process is key to ensuring your AI systems are fair, transparent, and aligned with responsible AI practices.

In this video, you’ll explore how to reduce risks in Generative AI using a layered mitigation approach. Learn how combining techniques—like prompt filtering, output moderation, and human review—helps minimize harmful or biased content.

This strategy ensures safer, more reliable AI outputs across different use cases and industries.

In this video, you’ll learn how to prepare Generative AI solutions for safe deployment through robust pre-release checks and post-release monitoring. We’ll cover steps for ensuring model compliance, documentation, risk mitigation, and ongoing oversight to align with responsible AI standards.

This process helps maintain accountability, trust, and compliance throughout the AI lifecycle.

In this video, you’ll learn what AI agents are and how they differ from traditional AI models. Discover how agents use reasoning, memory, and tools to autonomously achieve specific goals.

This introduction sets the foundation for building intelligent, task-oriented agents using platforms like Azure AI Agents Service.

In this video, you’ll explore the different ways to develop AI agents using Microsoft Azure. Learn about no-code, low-code, and code-first approaches available through Azure AI Agents Service.

We’ll also compare flexibility, customization, and use cases for each option—helping you choose the best development path for your AI solution.

In this video, you’ll get an overview of the Azure AI Agent Service—a powerful platform for building autonomous, goal-oriented AI agents using large language models. Learn how it enables agents to reason, plan, and take action by integrating tools, memory, and APIs.

This video sets the foundation for creating intelligent agents that can automate complex tasks across various enterprise scenarios.

In this hands-on lab, you’ll learn how to deploy an AI agent using Azure AI Foundry. We’ll walk through the step-by-step process of setting up the environment, configuring agent capabilities, connecting tools and APIs, and deploying the agent to run real-world tasks.

By the end of this lab, you’ll have a working AI agent deployed on Azure and ready to act autonomously based on goals and prompts.