Generative Artificial Intelligence (AI) is becoming more accessible through easy-to-use platforms like Azure AI Studio. Learn how to build generative AI applications like custom copilots that use language models and prompt flow to provide value to your users.

This course is for Data Scientists and AI Engineers.

Before starting this module, you should be familiar with fundamental AI concepts and services in Azure.

After completing this course, students will be able to:

• Describe core features and capabilities of Azure AI Studio
• Use Azure AI Studio to provision and manage an Azure AI resource
• Use Azure AI Studio to create and manage an AI project
• Understand the development lifecycle when creating language model applications
• Understand what a flow is in prompt flow
• Explore the core components when working with prompt flow
• Identify the need to ground your language model with Retrieval Augmented Generation (RAG)
• Index your data with Azure AI Search to make it searchable for language models
• Build a copilot using RAG on your own data in the Azure AI Studio
• Describe an overall process for responsible generative AI solution development
• Identify and prioritise potential harms relevant to a generative AI solution
• Mitigate harms in a generative AI solution
• Prepare to deploy and operate a generative AI solution responsibly

Introduction to Azure AI Studio

• What, how, and when to use Azure AI Studio

Explore and deploy models from the model catalog in Azure AI Studio

• Explore the language models in the model catalog
• Deploy a model to an endpoint
• Improve the performance of a language model

Get started with prompt flow to develop language model apps in the Azure AI Studio

• Understand the development lifecycle of a large language model (LLM) app
• Understand core components and explore flow types
• Explore connections and runtimes
• Explore variants and monitoring options

Build a RAG-based copilot solution with your own data using Azure AI Studio

• Understand how to ground your language model
• Make your data searchable
• Build a copilot with prompt flow

Integrate a fine-tuned language model with your copilot in the Azure AI Studio

• Understand when to fine-tune a language model
• Prepare your data to fine-tune a chat completion model
• Explore fine-tuning language models in Azure AI Studio

Evaluate the performance of your custom copilot in the Azure AI Studio

• Assess the model performance
• Manually evaluate the performance of a model
• Assess the performance of your custom copilot

Responsible generative AI

• Plan a responsible generative AI solution
• Identify potential harms
• Measure potential harms
• Mitigate potential harms
• Operate a responsible generative AI solution