I. Overview:

AI-102: Develop AI solutions in Azure is intended for software developers wanting to build AI infused applications that leverage Azure AI Foundry and other Azure AI services. Topics in this course include developing generative AI apps, building AI agents, and solutions that implement computer vision and information extraction.

II. Duration: 05 days (40 hours)

III. Objectives:

• Develop generative AI apps in Azure
• Develop computer vision solutions in Azure

IV. Intended Audience:

This course was designed for software engineers concerned with building, managing and deploying AI solutions that leverage Azure AI Foundry and other Azure AI services.

V. Prerequisites:

They are familiar with C# or Python and have knowledge on using REST-based APIs and SDKs to build generative AI, computer vision, language analysis, and information extraction solutions on Azure.

VI. Course outlines:

1. Develop generative AI apps in Azure:

Generative Artificial Intelligence (AI) is becoming more accessible through comprehensive development platforms like Microsoft Foundry. Learn how to build generative AI applications that use language models to chat with your users.

• Plan and prepare to develop AI solutions on Azure: Microsoft Azure offers multiple services that enable developers to build amazing AI-powered solutions. Proper planning and preparation involves identifying the services you'll use and creating an optimal working environment for your development team
• Choose and deploy models from the model catalog in Microsoft Foundry portal: Choose the various language models that are available through the Microsoft Foundry's model catalog. Understand how to select, deploy, and test a model, and to improve its performance.
• Develop an AI app with the Microsoft Foundry SDK: Use the Microsoft Foundry SDK to develop AI applications with Microsoft Foundry projects.
• Get started with prompt flow to develop language model apps in the Microsoft Foundry: Learn about how to use prompt flow to develop applications that leverage language models in the Microsoft Foundry.
• Develop a RAG-based solution with your own data using Microsoft Foundry: Retrieval Augmented Generation (RAG) is a common pattern used in generative AI solutions to ground prompts with your data. Microsoft Foundry provides support for adding data, creating indexes, and integrating them with generative AI models to help you build RAG-based solutions.
• Fine-tune a language model with Microsoft Foundry: Train a base language model on a chat-completion task. The model catalog in Microsoft Foundry offers many open-source models that can be fine-tuned for your specific model behavior needs.
• Implement a responsible generative AI solution in Microsoft Foundry: Generative AI enables amazing creative solutions, but must be implemented responsibly to minimize the risk of harmful content generation.
• Evaluate generative AI performance in Microsoft Foundry portal: Evaluating copilots is essential to ensure your generative AI applications meet user needs, provide accurate responses, and continuously improve over time. Discover how to assess and optimize the performance of your generative AI applications using the tools and features available in the Azure AI Studio.

2. Develop AI agents on Azure 

Generative Artificial Intelligence (AI) is becoming more functional and accessible, and AI agents are a key component of this evolution. This learning path will help you understand the AI agents, including when to use them and how to build them, using Microsoft Foundry Agent Service and Microsoft Agent Framework. By the end of this learning path, you will have the skills needed to develop AI agents on Azure.

• Get started with AI agent development on Azure: AI agents represent the next generation of intelligent applications. Learn how they can be developed and used on Microsoft Azure.
• Develop an AI agent with Microsoft Foundry Agent Service: This module provides engineers with the skills to begin building agents with Microsoft Foundry Agent Service.
• Develop AI agents with the Microsoft Foundry extension in Visual Studio Code: Learn how to build, test, and deploy AI agents using the Microsoft Foundry extension in Visual Studio Code.
• Integrate custom tools into your agent: Built-in tools are useful, but they may not meet all your needs. In this module, learn how to extend the capabilities of your agent by integrating custom tools for your agent to use.
• Develop a multi-agent solution with Microsoft Foundry Agent Service: Break down complex tasks with intelligent collaboration. Learn how to design multi-agent solutions using connected agents.
• Integrate MCP Tools with Azure AI Agents: Enable dynamic tool access for your Azure AI agents. Learn how to connect MCP-hosted tools and integrate them seamlessly into agent workflows.
• Develop an AI agent with Microsoft Agent Framework: This module provides engineers with the skills to begin building Microsoft Foundry Agent Service agents with Microsoft Agent Framework.
• Orchestrate a multi-agent solution using the Microsoft Agent Framework: Learn how to use the Microsoft Agent Framework SDK to develop your own AI agents that can collaborate for a multi-agent solution.
• Discover Azure AI Agents with A2A: Learn how to implement the A2A protocol to enable agent discovery, direct communication, and coordinated task execution across remote agents.

3. Develop natural language solutions in Azure

Natural language solutions use language models to interpret the semantic meaning of written or spoken language, and in some cases respond based on that meaning. You can use the Language service to build language models for your applications, and explore Microsoft Foundry to use generative models for speech.

• Analyze text with Azure Language: The Azure Language service enables you to create intelligent apps and services that extract semantic information from text.
• Create question answering solutions with Azure Language: The question answering capability of the Azure Language service makes it easy to build applications in which users ask questions using natural language and receive appropriate answers.
• Build a conversational language understanding model: The Azure Language conversational language understanding service (CLU) enables you to train a model that apps can use to extract meaning from natural language.
• Create custom text classification solutions: The Azure Language service enables processing of natural language to use in your own app. Learn how to build a custom text classification project.
• Custom named entity recognition: Build a custom entity recognition solution to extract entities from unstructured documents
• Translate text with Azure Translator service: The Translator service enables you to create intelligent apps and services that can translate text between languages.
• Create speech-enabled apps with Microsoft Foundry: The Azure Speech service enables you to build speech-enabled applications. This module focuses on using the speech-to-text and text to speech APIs, which enable you to create apps that are capable of speech recognition and speech synthesis.
• Translate speech with the Azure Speech service: Translation of speech builds on speech recognition by recognizing and transcribing spoken input in a specified language, and returning translations of the transcription in one or more other languages.
• Develop an audio-enabled generative AI application: A voice carries meaning beyond words, and audio-enabled generative AI models can interpret spoken input to understand tone, intent, and language. Learn how to build audio-enabled chat apps that listen and respond to audio.
• Develop an Azure AI Voice Live agent: Learn how to develop an Azure AI Voice Live agent using the Voice Live API and SDK. This module covers the fundamentals of the Voice Live platform, including API integration, SDK usage, and building conversational AI agents.

4. Develop computer vision solutions in Azure

Computer vision is an area of artificial intelligence that deals with visual perception. Azure AI includes multiple services that support common computer vision scenarios.

• Analyze images: With the Azure Vision service, you can use pre-trained models to analyze images and extract insights and information from them.
• Read text in images: The Azure Vision Image Analysis service uses algorithms to process images and return information. This module teaches you how to use the Image Analysis API for optical character recognition (OCR).
• Detect, analyze, and recognize faces: The ability for applications to detect human faces, analyze facial features and emotions, and identify individuals is a key artificial intelligence capability.
• Classify images: Image classification is used to determine the main subject of an image. You can use the Azure AI Custom Vision services to train a model that classifies images based on your own categorizations.
• Detect objects in images: Object detection is used to locate and identify objects in images. You can use Azure AI Custom Vision to train a model to detect specific classes of object in images.
• Analyze video: Azure Video Indexer is a service to extract insights from video, including face identification, text recognition, object labels, scene segmentations, and more.
• Develop a vision-enabled generative AI application: A picture says a thousand words, and multimodal generative AI models can interpret images to respond to visual prompts. Learn how to build vision-enabled chat apps.
• Generate images with AI: In Microsoft Foundry, you can use image generation models to create original images based on natural language prompts.

5. Develop AI information extraction solutions in Azure

Use Azure AI to extract information from content to support scenarios like:

- Data capture

- Business process automation

- Meeting summarization and analysis

- Digital asset management (DAM)

- Knowledge Mining

• Create a multimodal analysis solution with Azure Content Understanding: Use Azure Content Understanding for multimodal content analysis and information extraction.
• Create an Azure Content Understanding client application: Use the Azure Content Understanding REST API for multimodal content analysis and information extraction.
• Use prebuilt Document intelligence models: Learn what data you can analyze by choosing prebuilt Forms Analyzer models and how to deploy these models in a Document intelligence solution.
• Extract data from forms with Azure Document intelligence: Document intelligence uses machine learning technology to identify and extract key-value pairs and table data from form documents with accuracy, at scale. This module teaches you how to use the Azure Document intelligence cognitive service.
• Create a knowledge mining solution with Azure AI Search: Unlock the hidden insights in your data with Azure AI Search. In this module, you'll learn how to implement a knowledge mining solution that extracts and enriches data, making it searchable and ready for deeper analysis.