AZ-2005 : Developing AI agents using Azure OpenAI and the SDK
- Developeur
Training Overview
This course covers kernel generation, explaining the purpose of an SDK and the basic concepts of prompts, as well as techniques for optimising them. Participants will learn how to create and use plug-ins for the SDK, as well as how to equip their AI agent with skills via native functions and function plug-ins. The course also includes exercises for combining prompts and functions, using the Semantic Kernel SDK for automatic function calls, and creating an AI travel agent capable of generating relevant responses, manipulating results, and executing tasks via plug-ins.
Learning objectives
At the end of this course, participants will be able to :
- Build your kernel
- Running queries with Semantic Kernel
- Create Semantic Kernel Plugins
- Apply filters to features
- Create a DevOps Assistant with the Semantic Kernel SDK.
To follow this course, you must have programming experience in C#. You must also be familiar with and use Azure and the Azure portal.
You must also have access to Azure OpenAI Services and have the Visual Studio Code IDR installed.
Build your kernel
- Understand the purpose of a semantic core.
- Understand the basic concepts of prompts.
- Learn techniques to improve prompt efficiency.
Running queries with Semantic Kernel
- Understand the purpose of semantic kernel plugins.
- Use predefined plug-ins.
- How to create your own plug-ins.
Create Semantic Kernel Plugins
- Understand the native functions in the semantic kernel SDK.
- Create native function plug-ins.
- Combine queries with native functions.
Apply filters to features
- Create plug-ins with the Semantic Core SDK.
- Combine queries with native functions.
Create a DevOps Assistant with the Semantic Kernel SDK
- Create plug-ins for the semantic kernel.
- Create prompts to get the best responses from the Large Language Model (LLM).
- Embed expressions in prompts to manually invoke functions.
- Automatically call the appropriate plug-ins to perform tasks.
- Apply filters to the plugin’s functions.
Updated on 08/26/2025
In this training, we mix theory with technical workshops to quickly make you operational. Additionally, each participant receives course materials at the end of the training.
One of our consultant trainers conducts the training. With solid field experience, they make the learning process both interactive and enriching.
For assessment, the trainer regularly asks questions and uses various methods to continuously measure your progress. This approach promotes a dynamic and engaging learning experience.
After the training, we ask you to complete a satisfaction questionnaire. Your feedback helps us to maintain and constantly improve the quality of our training.
Finally, we offer the flexibility to deliver this training both in-person and remotely, and it can be customized to meet your company’s specific needs upon request.
You can register for one of our training courses up to two business days before it starts, if there are still available places and you signed quote.
If you have specific needs related to a disability, please do not hesitate to make a request; we are happy to adjust our services according to the type of disability.
Nos formations sur la même thématique
AZ-2007: Accelerate application development using GitHub Copilot
Exploring Generative AI
C# Development Fundamentals
AI-3002 : Developing Solutions with Azure AI Document Intelligence
AI-3003 : Developing natural language processing solutions with Azure AI Services
AI-3004 : Creating a solution with Azure AI Vision
AI-901 : Introduction to AI in Azure
