Microsoft AI-3016 - Develop Generative AI Apps in Azure

What you’ll learn

After completing this course, students will be able to:

• Identify common AI capabilities that you can implement in applications

• Describe Microsoft Foundry and considerations for using it

• Describe Foundry Tools and considerations for using them

• Identify appropriate developer tools and SDKs for an AI project

• Describe considerations for responsible AI

• Explore and filter models in the model catalog

• Compare models using benchmark metrics for quality, safety, cost, and performance

• Deploy a model to an endpoint and test it in the playground

• Evaluate model performance using manual and automated approaches

• Understand different evaluation metrics and when to use them

• Describe the process for creating a generative AI chat application with Microsoft Foundry

• Use the Chat playground to explore models and generate code samples

• Choose an endpoint, authentication method, and client SDK for your app development

• Use the Responses API to generate AI responses in applications

• Use the ChatCompletions API to generate AI responses in applications

• Describe the capabilities of generative AI tools

• Use the code_interpreter tool to run code and analyse data

• Use the web_search tool to retrieve real-time information from the internet

• Use the file_search tool to access and analyse files

• Use the function tool to run custom code

• Apply prompt engineering techniques including system messages, few-shot learning, and model parameters to optimise model output

• Understand when and how to ground a language model using Retrieval Augmented Generation (RAG)

• Identify when fine-tuning a model improves behavioral consistency

• Compare optimisation strategies and determine when to combine them

• Describe an overall process for responsible generative AI solution development

• Identify and prioritise 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

Microsoft Azure at Lumify Work

As part of Lumify Group, Lumify Work has skilled more people in Microsoft technologies than any other organisation in Australia and New Zealand. We have a campus in the Philippines, too. We offer the broadest range of instructor-led training courses, from end user to architect level.  We are proud to be the winner of the Microsoft MCT Superstars Award for FY24, which formally recognises us as having the highest quality Microsoft Certified Trainers in ANZ. 

View all Microsoft Azure at Lumify Work courses

Who is the course for?

This course is designed for data scientists and AI engineers with existing knowledge of generative AI models and Python who want to create, customise, and deploy their own Copilots.

Prerequisites

• You should be familiar with fundamental AI concepts and services in Azure. Consider completing the Introduction to AI in Azure course first.

• You should also be proficient in programming with Python or Microsoft C#.

Terms & Conditions

The supply of this course by Lumify Work is governed by the booking terms and conditions. Please read the terms and conditions carefully before enrolling in this course, as enrolment in the course is conditional on acceptance of these terms and conditions.