Force7 Training
FRCMIC-3Microsoft

Develop Generative AI Apps in Azure (AI-3016)

This course provides developers with the knowledge and hands-on experience needed to build, deploy, and enhance Generative AI applications using Azure AI services.

Duration · 1 dayVirtual + In-PersonInstructor-Led

Course Description

This course provides developers with the knowledge and hands-on experience needed to build, deploy, and enhance Generative AI applications using Azure AI services. Participants will learn how to leverage Azure OpenAI Service, implement prompt engineering techniques, integrate AI models into applications, and apply responsible AI practices throughout the development lifecycle.

— Be First in Line —

Register Your Interest

We're finalizing the schedule for Develop Generative AI Apps in Azure (AI-3016). Add your details below and we'll notify you the moment a session opens for registration — no payment or commitment required.

Audience Profile

This course is intended for:

  • Developers
  • Software Engineers
  • AI Engineers
  • Cloud Developers
  • Application Architects
  • Technical Consultants
  • IT Professionals

Prerequisites

Before enrolling, you should have:

  • Basic programming experience
  • Familiarity with cloud concepts
  • Understanding of REST APIs and JSON
  • Basic knowledge of Microsoft Azure

— What You'll Learn —

Learning Objectives

In this course, you will learn to:

  • 1Understand the fundamentals of Generative AI and Large Language Models (LLMs)
  • 2Deploy and manage Azure OpenAI resources
  • 3Design effective prompts for AI-powered applications
  • 4Integrate Azure OpenAI into applications and workflows
  • 5Implement Retrieval-Augmented Generation (RAG) solutions
  • 6Improve AI application performance and reliability
  • 7Apply responsible AI and security best practices
  • 8Plan and deploy production-ready Generative AI solutions

— Day-by-Day —

Course Outline

Module 1

Introduction to Generative AI and Azure OpenAI

  • Overview of Generative AI
  • Large Language Models (LLMs)
  • Foundation Models and Transformers
  • Common Generative AI Scenarios
  • Azure AI Services Overview
  • Azure OpenAI Service Architecture
  • Supported Models and Capabilities
  • Generative AI Use Cases Across Industries
  • Demonstration: Exploring Azure OpenAI Studio

Module 2

Provision and Manage Azure OpenAI Resources

  • Azure OpenAI Resource Deployment
  • Resource Groups and Azure Architecture
  • Authentication and Authorization
  • API Keys and Managed Identity
  • Security and Compliance Considerations
  • Monitoring and Usage Management
  • Cost Management Fundamentals
  • Hands-On Lab: Deploying an Azure OpenAI Resource

Module 3

Prompt Engineering Fundamentals

  • Prompt Engineering Concepts
  • Prompt Structure and Components
  • Zero-Shot Prompting
  • Few-Shot Prompting
  • Chain-of-Thought Techniques
  • Context Management
  • Output Formatting
  • Reducing Hallucinations
  • Hands-On Lab: Building and Testing Effective Prompts

Module 4

Integrating Azure OpenAI into Applications

  • Azure OpenAI APIs
  • Application Architecture Patterns
  • SDK Overview
  • Working with Chat Completions
  • Text Generation Scenarios
  • Summarization and Content Creation
  • Conversational AI Applications
  • Error Handling and Response Management
  • Hands-On Lab: Creating a Simple Generative AI Application

Module 5

Implement Retrieval-Augmented Generation (RAG)

  • Introduction to RAG Architecture
  • Why Grounding Matters
  • Azure AI Search Integration
  • Indexing Organizational Content
  • Semantic Search Concepts
  • Connecting Data Sources to LLMs
  • Improving Response Accuracy
  • Managing Knowledge Bases
  • Hands-On Lab: Building a RAG-Powered Chat Application

Module 6

Responsible AI, Security, and Governance

  • Responsible AI Principles
  • Content Filtering and Safety Systems
  • Prompt Injection Risks
  • Data Privacy and Protection
  • Security Best Practices
  • Compliance and Regulatory Considerations
  • Human Oversight Strategies
  • AI Governance Frameworks
  • Discussion: Real-World Responsible AI Scenarios

Module 7

Optimizing and Deploying Generative AI Solutions

  • Performance Optimization
  • Token Management
  • Cost Optimization Strategies
  • Monitoring and Logging
  • Application Scalability
  • Testing and Evaluation Methods
  • Deployment Considerations
  • Operational Best Practices
  • Hands-On Lab: Evaluating and Optimizing Model Responses
  • Capstone Exercise: Scenario-Based Project
  • Capstone Exercise: Participants will design and implement a Generative AI solution using Azure OpenAI and organizational data.
  • Activity: Define application requirements
  • Activity: Design prompts and workflows
  • Activity: Integrate Azure OpenAI services
  • Activity: Implement a RAG solution
  • Activity: Apply responsible AI controls
  • Activity: Present solution architecture and outcomes

The Big Picture

Key Takeaways

  • Azure OpenAI fundamentals
  • Prompt engineering best practices
  • Application integration techniques
  • Retrieval-Augmented Generation (RAG)
  • Responsible AI implementation
  • Production deployment considerations

What You'll Walk Away With

Skills Gained

  • Azure OpenAI deployment and management
  • Prompt engineering
  • Generative AI application development
  • RAG architecture implementation
  • AI governance and security
  • Production-ready AI solution design

Note: Course outlines are provided as a general guide. Content, pacing, labs, and instructional emphasis may vary based on instructor expertise, student experience levels, and customer-specific learning objectives.

— Keep Exploring —

Need a different angle?

Browse the full Microsoft catalog or chat with an advisor about a custom training plan for your team.