Microsoft Certified Azure AI Engineer Associate : AI-102

Explore an overview of artificial intelligence, machine learning, and deep learning. Examine the evolution and real-world applications of these technologies, learn gen ai fundamentals, and discuss artificial intelligence–assisted decision support.

Explore ai, ml, and dl, and learn how artificial intelligence learns from data, how ml infers patterns from examples, and how dl uses deep networks to detect features.

Trace the evolution of AI from early systems to modern applications and explore real-world uses across healthcare, finance, transportation, retail, education, and agriculture.

Explore the fundamentals of generative AI, including large language models and transformers, and how NLP and computer vision empower machines to understand and generate text, images, and code.

Explore how ai supports decision making with data analysis at scale, predictive modeling, and personalized recommendations, while highlighting risks and the need for human oversight.

Explore the Azure ecosystem UI and Azure Open AI services, including GPT and other models. Learn how to choose models and compare single versus multiple services.

Navigate the Azure portal to explore subscriptions, resources, and services; discover AI foundry, machine learning, computer vision, custom vision, face API, language, and how to create new resources.

Navigate the Azure portal to access the Azure OpenAI service, create an Azure OpenAI resource, and explore the model catalog, playground chat, and endpoints and keys for SDK usage.

Explore the Azure OpenAI service model catalog to browse GPT-5 and other models, filter by tasks like audio generation and chat completion, and review access requirements.

Explains the types of models in azure ai foundry and how to choose the right one using criteria like modality, performance, deployment options, licensing, and observability.

Compare single service and multiservice models in Azure AI, highlighting isolated endpoints and separate keys versus centralized authentication, unified billing, and cross-service integration for multi-feature apps.

Explore Azure AI foundry, understand large language models, and master prompt engineering fundamentals. See a demonstration of the Azure AI foundry playground.

Explore Azure AI Foundry, an enterprise grade PaaS that unifies models, tools, and agents to build, deploy, and manage AI applications with production ready infrastructure, unified SDKs, and compliance features.

Explore how large language models work from tokenization, vectorization, and embeddings to transformer architecture with self-attention, and decoding strategies that generate human-like text.

Craft clear prompts to guide AI outputs by setting tasks, constraints, and formats. Understand roles of system prompts, user prompts, and context history to shape precise completions.

Explore Azure AI Foundry Playground to prototype and validate generative AI models and agents with chat, video, and image tasks, configure deployment, and collaborate securely using enterprise-grade security.

Explore the Azure AI Foundry SDK in detail, build a Python chat client to converse with the Azure Foundry AI model, and connect it to an Azure Storage account.

Understand how the Azure AI foundry sdk simplifies building with Azure hosted resources, including foundation models, providing Python APIs, authentication, deployment, and monitoring; enables Rag workflows and vector search.

Learn to set up Azure OpenAI GPT-4 in VS Code, authenticate with a subscription key, and run a Python script that chats the model, using dot env for secure keys.

Demonstrates building a chat client with Azure CLI in Cloud Shell, configuring a venv and dot env, and using a GPT-4 deployment via Azure OpenAI with a DevOps prompt.

Explore what rag is, learn key terminologies, see a demonstration of implementing rag in Azure AI Foundry, and review best practices for rag applications in Azure.

Retrieval augmented generation merges external retrieval with a generator to deliver up-to-date, domain-specific responses, reducing hallucinations by citing sources and updating the knowledge base with real-time data.

Learn key terminologies in rag, including grounding to base answers on retrieved data, chunking documents into fixed-size or semantic chunks, embeddings to capture meaning, and vector stores for fast retrieval.

Learn to implement retrieval augmented generation by uploading data to Azure AI Foundry, creating a vector index with AI search, and querying GPT-4 against the Bitcoin white paper.

Explore best practices for RAG applications in Azure, including document preparation, chunking with Azure Cognitive Search, embeddings, vector search, grounding, prompt engineering, secure access with RBAC, and Azure Blob Storage.

Explore the fundamentals of AI agents, their usefulness, and how to deploy them on Azure, with a focus on AI agent components and an introduction to Semantic Kernel.

Ai agents understand goals, break them into steps, select tools, and execute actions. They interact with apis and manage workflows to automate multi-step tasks, from planning trips to writing code.

Discover how AI agents automate tasks, plan workflows, and integrate with tools to act on live data, from summarizing PDFs to automating meetings and stock insights.

Explore Azure services for agent deployment in the Foundry portal, configure agents with settings, data sources, and actions like code interpreter and OpenAPI tools, then train and test with triggers.

Explore AI agents’ components—perception and input handling, planning, memory, reasoning, action, communication, and learning—driven by NLP, tool calls, and adaptation.

Deploy an AI agent in Azure using Azure AI Foundry, select a GPT-4 model, and add a code interpreter with a Python file; review outputs and charts, noting deployment delays.

Discover semantic kernel as a model-agnostic orchestration layer for enterprise AI, enabling plugins, prompt workflows, and a chatbot demo that uses Azure OpenAI to fetch weather via Open Mateo API.

Explore natural language processing in Azure as we cover intents, utterances, and entities, then demonstrate building a conversational agent with Azure AI service.

Explore Azure AI language and Azure OpenAI for core natural language processing. Use cognitive search for semantic search, sentiment analysis, named entity recognition, and summarization.

Explore intents, utterances, and entities in Azure AI language understanding, showing how intents define goals, utterances train the model, and entities extract location or date to fulfill a request.

Build a conversational agent with Azure Language Service by creating a resource, defining intents, utterances, and entities, training a model, deploying it, and testing with utterances.

Explore computer vision concepts in Azure, deploy CV models in Azure AI Foundry, master face detection, detect faces with Vision Studio, and perform OCR with text recognition in images.

Explore computer vision concepts, from image processing and edge detection to classification and segmentation, and learn to automate visual tasks and decision making with Azure AI Vision.

Deploy an Azure computer vision resource and analyze images with the vision software development kit, generating captions, dense captions, and object and people detections with bounding boxes.

Demonstrates detecting a face in an image using Vision Studio, creating and using a computer vision resource, uploading images, and exploring SDK samples for face analysis.

Explore how OCR converts text in images into editable, searchable data by covering image acquisition, preprocessing, text detection, feature extraction, and character recognition with CNNs, RNNs, and transformers.

Demonstrate using Vision Studio to extract handwritten text from images, upload photos, and view how extraction maps to image areas, with options to view supported languages and try the SDK.

Design and deploy AI solutions on Azure using the Azure OpenAI service, Azure AI Foundry, and end-to-end pipelines, preparing for the AI 102 certification.