AZ-2005 | Develop AI agents using Azure OpenAI and the Semantic Kernel SDK
 
Learn how to use the Semantic Kernel SDK to build intelligent applications that automate tasks and perform natural language processing.
 
Prerequisites
Experience programming in C#.
Visual Studio Code IDE installed.
Familiarity with Azure and the Azure portal.
Access to Azure OpenAI Services.
 
Course Outline
Module 1: Build your kernel
This module introduces the Semantic Kernel SDK. Learn how the kernel connects code to large language models to extend functionality with generative artificial intelligence.
Introduction
What is semantic kernel
Why use semantic kernel
How to build your kernel
Exercise - Create your endpoint
Exercise - Build a kernel object
Knowledge check
Summary
Learning objectives
Understand the purpose of Semantic Kernel.
Understand prompting basics.
Learn techniques for more effective prompts.
Module 2: Create plugins for semantic kernel
This module explores Semantic Kernel SDK plugins. Learn how plugins to the SDK are used to accomplish customized tasks and create intelligent applications.
Introduction
Explore built-in plugins
Exercise - Use built-in plugins
Optimize language model prompts
Exercise - Write your own prompt
Exercise - Use personas in prompts
Save prompts to files
Exercise - Saving prompts to files
Knowledge check
Summary
Learning objectives
Understand the purpose of Semantic Kernel plugins
Learn how to use premade plugins
Learn how to create your own plugins
Module 3: Give your AI agent skills
This module explores native functions in the Semantic Kernel SDK. Learn how native functions can accomplish customized tasks, effectively giving your AI agent a "skill."
Introduction
Understand native functions
Exercise - Create native functions
Knowledge check
Summary
Learning objectives
Understand native functions in the Semantic Kernel SDK.
Learn how to create native function plugins.
Learn how to combine prompts with native functions.
Module 4: Combine Prompts and Functions
This module demonstrates how to combine functions and prompts with the Semantic Kernel SDK. Nesting functions within prompts can allow your code to complete tasks large language models can't typically complete on their own.
Introduction
Use functions in prompts
Exercise - Use nested functions for song suggestions
Knowledge check
Summary
Learning objectives
Practice creating plugins with the Semantic Kernel SDK.
Learn how to combine prompts with native functions.
Module 5: Use intelligent planners
This module introduces different ways to automatically invoke functions using the Semantic Kernel SDK. Learn how planners can generate plans to accomplish tasks and how to fine-tune planners to optimize performance.
Introduction
Learn about AI planners
How to use a planner
Exercise - Create a planner
Exercise - Use a plan template
Optimize your planners
Automatically invoke functions
Exercise - Automatically invoke functions
Knowledge check
Summary
Learning objectives
Understand planners in the Semantic Kernel SDK.
Learn how to use planners to automate function calls.
Learn how to optimize planners.
Learn how to use Semantic Kernel SDK to automatically invoke functions.
Module 6: Guided project - Create an AI travel agent
This module guides you through the steps required to develop a proof-of-concept AI Travel assistant with the Semantic Kernel SDK. By the end of this module, you complete a small chatbot application.
Introduction
Prepare for guided project
Exercise - Create a currency converter
Exercise - Route user intent
Exercise - Provide context cues
Knowledge check
Summary
Learning objectives
Create plugins for the Semantic Kernel.
Create prompts to elicit the best responses from the large language model (LLM).
Manipulate LLM responses to guide the execution of code.
Automatically invoke the correct plugins to complete tasks.
 
Descargue el temario para conocer el detalle completo de los contenidos.
 
Debido a las constantes actualizaciones de los contenidos de los cursos por parte del fabricante, el contenido de este temario puede variar con respecto al publicado en el sitio oficial, sin embargo, Netec siempre entregará la versión actualizada de éste.