AI-102T00 Develop AI solutions in Azure
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.
By the end of this course, participants will be able to:
-
Plan and Manage AI Solutions – Design, deploy, and secure AI solutions on Azure with Responsible AI practices.
-
Implement Generative AI – Build applications and agents using Azure OpenAI, Semantic Kernel, RAG patterns, and prompt flows.
-
Develop Computer Vision Solutions – Apply Cognitive Services for image analysis, object detection, OCR, and face recognition.
-
Build Natural Language and Speech Solutions – Create text analytics, speech-enabled apps, conversational bots, and NLU solutions.
-
Implement Knowledge Mining – Design intelligent search with Azure AI Search, semantic and vector search, and data extraction using Cognitive Services.
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. 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.
Before attending this course, students must have:
- Knowledge of Microsoft Azure and ability to navigate the Azure portal
- Knowledge of either C# or Python
- Familiarity with JSON and REST programming semantics Recommended course prerequisites
- AI-900T00: Microsoft Azure AI Fundamentals course
- What is AI?
- Azure AI services and Azure AI Foundry
- Developer tools, SDKs, and Responsible AI
- Explore and deploy models from the catalog
- Azure AI Foundry SDK basics and project connections
- Prompt flows: lifecycle, components, monitoring, and variants
- Build applications and agents using Azure OpenAI and Semantic Kernel
- Implement Retrieval-Augmented Generation (RAG) with custom data
- Fine-tuning language models and prompt optimization
- Responsible generative AI (planning, mapping, mitigating harms)
- Evaluating generative AI performance
- Introduction to AI agents and Azure AI Foundry Agent Service
- Develop agents and integrate custom tools
- Build Semantic Kernel agents with plugins
- Orchestrate multi-agent solutions (group chats, selection strategies, termination)
- Integrate MCP tools into Azure AI agents
- Text analytics: sentiment, PII detection, entity extraction, classification
- Conversational AI: intents, utterances, entities, and conversational models
- Question answering and knowledge bases
- Speech solutions: speech-to-text, text-to-speech, and speech translation
- Develop audio-enabled generative AI applications
- Provision and configure speech services
- Deploy multimodal models for text, audio, and vision-based chat apps
- Image analysis and OCR
- Face detection, analysis, and recognition with Responsible AI considerations
- Custom Vision: image classification and object detection
- Video analysis with Azure Video Indexer
- Generate images using AI models
- Develop vision-enabled generative AI apps
- Azure AI Content Understanding: analyzers, REST APIs, and client applications
- Prebuilt models (General, Read, Layout, Financial, ID, Tax)
- Extract data from forms and train custom models
- Azure Document Intelligence Studio for development and testing
- Introduction to AI-powered search
- Extract and enrich data using indexers and AI skills
- Semantic and vector search capabilities
- Persist information in a knowledge store
- Apply Responsible AI principles across solutions
- Evaluate risks and mitigation strategies
- Ensure compliance and governance in AI projects
- Hands-on practice with Azure AI services (NLP, Vision, Agents, Generative AI, Search)
- Module assessments to validate learning