Develop custom copilots with Azure AI Studio (AI-3016)

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.

Module1: Introduction to Azure AI Studio

• 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 when to use Azure AI Studio

Module 2: Explore and deploy models from the model catalog in Azure AI Studio

• Select a language model from the model catalog.
• Deploy a model to an endpoint.
• Test a model and improve the performance of the model.

Module 3 : Get started with prompt flow to develop language model apps in the Azure AI Studio

• 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.

Module 4 : Build a RAG-based copilot solution with your own data using Azure AI Studio

• 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

Module 5: Integrate a fine-tuned language model with your copilot in the Azure AI Studio

• Understand when to fine-tune a model.
• Prepare your data to fine-tune a chat completion model.
• Fine-tune a base model in the Azure AI Studio.

Module 6: Evaluate the performance of your custom copilot in the Azure AI Studio

• Understand model benchmarks.
• Perform manual evaluations.
• Assess your copilot with AI-assisted metrics.
• Configure evaluation flows in the Azure AI Studio.

Module 7: Responsible generative AI

• Describe an overall process for responsible generative AI solution development
• Identify and prioritize potential harms relevant to a generative AI solution
• Measure the presence of harms in a generative AI solution
• Mitigate harms in a generative AI solution
• Prepare to deploy and operate a generative AI solution responsibly

Before starting this module, you should be familiar with fundamental AI concepts and services in Azure. Consider completing the Get started with artificial intelligence learning path first.

AI Engineers, Data Scientists, students having knowledge in AI and willing to create custom copilots with Azure AI.