Operationalize generative AI applications

The following quickstart exercises are designed to provide you with a hands-on learning experience in which you’ll explore common tasks required to operationalize a generative AI workload on Microsoft Azure.

Note: To complete the exercises, you’ll need an Azure subscription in which you have sufficient permissions and quota to provision the necessary Azure resources and generative AI models. If you don’t already have one, you can sign up for an Azure account. There’s a free trial option for new users that includes credits for the first 30 days.

Quickstart exercises

Compare language models from the model catalog

Learn how to compare and select appropriate models for your generative AI project.

Explore prompt engineering with Prompty

Learn how to use Prompty to quickly test and improve on different prompts with your language model and ensure that they are constructed and orchestrated for best results.

Orchestrate a RAG system

Learn how to implement Retrieval-Augmented Generation (RAG) systems in your apps to enhance the accuracy and relevance of generated responses.

Optimize your model using a synthetic dataset

Learn how to create synthetic datasets and use them to enhance performance and reliability of your model.

Monitor your generative AI application

Learn how to monitor interactions with your deployed model and get insights on how to optimize its usage with your generative AI application.

Analyze and debug your generative AI app with tracing

Learn how to debug your generative AI application by tracing its workflow from user input to model response and post-processing.

Note: While you can complete these exercises on their own, they’re designed to complement modules on Microsoft Learn; in which you’ll find a deeper dive into some of the underlying concepts on which these exercises are based.