Azure AI Foundry & AI Studio Training

Build and deploy production AI solutions with Azure AI Foundry (formerly Azure AI Studio) in this hands-on 3-day training. Learn to navigate the model catalog, engineer effective prompts, implement retrieval-augmented generation (RAG) patterns, fine-tune foundation models, and deploy AI solutions with built-in content safety and responsible AI practices.

Training Details


Duration	3 days (24 hours)
Level	Intermediate
Delivery	In-person, Live online, Hybrid

Who Is This For?

AI engineers building solutions on Azure AI Foundry
Developers integrating foundation models into applications
Data scientists exploring model deployment and fine-tuning on Azure
Solution architects designing AI-powered applications
Technical leads evaluating Azure AI Foundry for their teams

Learning Outcomes

After completing this training, you’ll be able to:

Set up and configure Azure AI Foundry workspaces and projects
Deploy and manage models from the Azure AI model catalog
Design effective prompts and build prompt flow pipelines
Implement retrieval-augmented generation with Azure AI Search
Fine-tune foundation models for domain-specific tasks
Evaluate, benchmark, and deploy AI solutions to production

Detailed Agenda

Day 1: Azure AI Foundry Platform and Prompt Engineering

Module 1: Azure AI Foundry Platform Overview

Azure AI Foundry architecture and workspace setup
Projects, connections, and resource management
Model catalog exploration and model comparison
Azure AI Foundry SDK and CLI overview
Hands-on: Set up an AI Foundry workspace and project

Module 2: Model Deployment and Management

Deploying models from the model catalog
Managed compute and serverless deployment options
Model versioning and endpoint configuration
Monitoring model performance and usage
Hands-on: Deploy and test foundation models

Module 3: Prompt Engineering and Prompt Flow

Prompt engineering principles and best practices
System prompts, few-shot learning, and chain-of-thought
Prompt flow for orchestrating AI workflows
Testing and iterating on prompt designs
Hands-on: Build a prompt flow pipeline

Day 2: RAG Patterns and Fine-Tuning

Module 4: Retrieval-Augmented Generation (RAG)

RAG architecture and design patterns
Azure AI Search for knowledge retrieval
Vector search and hybrid search strategies
Indexing, chunking, and embedding strategies
Hands-on: Build a RAG solution with Azure AI Search

Module 5: Fine-Tuning Foundation Models

When to fine-tune vs. prompt engineer
Preparing training data for fine-tuning
Fine-tuning workflows in Azure AI Foundry
Evaluating fine-tuned model performance
Hands-on: Fine-tune a model for a domain-specific task

Module 6: Evaluation and Benchmarking

Model evaluation metrics and methodologies
Built-in evaluation flows in Azure AI Foundry
Comparing model performance across tasks
A/B testing and iterative improvement
Hands-on: Evaluate and compare model outputs

Day 3: Content Safety, Responsible AI, and Production Deployment

Module 7: Content Safety and Responsible AI

Azure AI Content Safety service
Content filtering and moderation policies
Jailbreak detection and prompt shields
Responsible AI principles in practice
Hands-on: Configure content safety for AI deployments

Module 8: Deploying AI Solutions to Production

Managed online endpoints for real-time inference
Batch endpoints for large-scale processing
Blue-green deployment strategies
API gateway integration and scaling
Hands-on: Deploy an AI solution to a managed endpoint

Module 9: Monitoring and Managing AI Endpoints

Endpoint monitoring and logging
Cost management and token usage tracking
Performance optimization and autoscaling
Troubleshooting and operational best practices
Hands-on: Set up monitoring and alerts for AI endpoints

Prerequisites

Basic familiarity with Azure portal and services
Understanding of AI and machine learning concepts
Programming experience in Python
Experience with REST APIs

Delivery Formats

Format	Description
In-Person	On-site at your company’s location, hands-on with direct interaction
Live Online	Interactive virtual sessions with screen sharing and real-time labs
Hybrid	Combination of on-site and remote sessions, flexible scheduling

All formats include hands-on labs, course materials, reference architectures, and post-training support.