Complete AI-900 study guide — AI workloads, machine learning, computer vision, NLP, and generative AI on Azure.
This guide works best as a loop: read a chapter, test yourself with practice questions, look up unfamiliar terms in the glossary, then move to the next chapter.
100 chapters covering every exam objective. Each chapter includes key concepts, exam tips, common traps, comparison tables, and a 5-question quiz at the end.
Start Chapter 1Free timed and untimed practice with instant feedback and full explanations. Pick 10–120 questions per session. Filter by domain to drill your weak areas.
Go to practice testEvery AI-900term defined and searchable. Use it when a chapter mentions a concept you haven't seen before or want a quick refresher on.
Browse glossaryExam blueprint, domain weights, passing score, duration, cost, and registration links. Start here if you're new to this certification.
View exam guide14 chapters
What is Artificial Intelligence?
Objective 1.1 · AI Workloads
Types of AI Workloads
Objective 1.1 · AI Workloads
Responsible AI Principles
Objective 1.2 · AI Workloads
AI vs Machine Learning vs Deep Learning
Objective 1.1 · AI Workloads
Narrow AI vs General AI
Objective 1.1 · AI Workloads
AI Use Cases: Prediction, Classification, Generation
Objective 1.1 · AI Workloads
AI Reliability, Safety, and Privacy
Objective 1.2 · AI Workloads
AI Transparency and Explainability
Objective 1.2 · AI Workloads
AI Accountability and Human Oversight
Objective 1.2 · AI Workloads
Azure AI Services Overview
Objective 1.1 · AI Workloads
Cognitive Services Pricing and Tiers
Objective 1.1 · AI Workloads
AI Infrastructure Costs and GPU Compute
Objective 1.1 · AI Workloads
AI-900 Exam Strategy and Scenario Questions
Objective 1.1 · AI Workloads
ML Ethics, Fairness, and Inclusiveness
Objective 1.2 · AI Workloads
28 chapters
Machine Learning Core Concepts
Objective 2.1 · Machine Learning
Supervised vs Unsupervised Learning
Objective 2.1 · Machine Learning
Regression and Classification
Objective 2.2 · Machine Learning
Deep Learning and Neural Networks
Objective 2.3 · Machine Learning
Azure Machine Learning Studio
Objective 2.4 · Machine Learning
Automated ML (AutoML)
Objective 2.4 · Machine Learning
Clustering
Objective 2.2 · Machine Learning
Features, Labels, and Training Data
Objective 2.1 · Machine Learning
Training, Validation, and Test Data Splits
Objective 2.1 · Machine Learning
Overfitting, Underfitting, and Model Complexity
Objective 2.1 · Machine Learning
ML Evaluation Metrics: Accuracy, Precision, Recall
Objective 2.2 · Machine Learning
Confusion Matrix and ROC Curve
Objective 2.2 · Machine Learning
Decision Trees and Random Forests
Objective 2.2 · Machine Learning
Linear vs Logistic Regression
Objective 2.2 · Machine Learning
Anomaly Detection
Objective 2.2 · Machine Learning
Recommendation Systems
Objective 2.2 · Machine Learning
Time Series Forecasting
Objective 2.2 · Machine Learning
Convolutional Neural Networks (CNN)
Objective 2.3 · Machine Learning
RNNs and Transformer Architecture
Objective 2.3 · Machine Learning
Transfer Learning and Pre-Trained Models
Objective 2.3 · Machine Learning
Azure Machine Learning Workspace
Objective 2.4 · Machine Learning
Azure ML Designer: Drag-and-Drop ML
Objective 2.4 · Machine Learning
Azure ML Notebooks and Compute Clusters
Objective 2.4 · Machine Learning
Azure ML Endpoints: Real-Time and Batch
Objective 2.4 · Machine Learning
Responsible AI Dashboard in Azure ML
Objective 2.4 · Machine Learning
No-Code AI Tools: Lobe, Teachable Machine
Objective 2.4 · Machine Learning
MLOps Concepts: Model Registry and Monitoring
Objective 2.4 · Machine Learning
Azure ML Pipelines for Batch Inference
Objective 2.4 · Machine Learning
17 chapters
What is Computer Vision?
Objective 3.1 · Computer Vision
Azure AI Vision Service
Objective 3.2 · Computer Vision
Azure Document Intelligence
Objective 3.4 · Computer Vision
Azure Custom Vision
Objective 3.5 · Computer Vision
Azure Face Service
Objective 3.3 · Computer Vision
Image Classification Tasks
Objective 3.1 · Computer Vision
Object Detection and Bounding Boxes
Objective 3.1 · Computer Vision
Semantic Segmentation
Objective 3.1 · Computer Vision
Optical Character Recognition (OCR)
Objective 3.2 · Computer Vision
Image Analysis: Tags, Captions, Objects
Objective 3.2 · Computer Vision
Spatial Analysis and Video Insights
Objective 3.2 · Computer Vision
Face Detection vs Face Recognition
Objective 3.3 · Computer Vision
Face Attributes and Emotion Detection
Objective 3.3 · Computer Vision
Document Layout Analysis
Objective 3.4 · Computer Vision
Pre-Built Models: Invoices, Receipts, IDs
Objective 3.4 · Computer Vision
Custom Vision Models: Training and Evaluation
Objective 3.5 · Computer Vision
Custom Image Classification vs Object Detection
Objective 3.5 · Computer Vision
21 chapters
What is NLP?
Objective 4.1 · NLP
Azure AI Language Service
Objective 4.2 · NLP
Sentiment Analysis and Key Phrase Extraction
Objective 4.3 · NLP
Azure AI Speech Service
Objective 4.4 · NLP
Azure AI Translator
Objective 4.5 · NLP
Azure Bot Service and QnA Maker
Objective 4.6 · NLP
Tokenization and Text Normalization
Objective 4.1 · NLP
Named Entity Recognition (NER)
Objective 4.2 · NLP
Entity Linking and Knowledge Base
Objective 4.2 · NLP
Question Answering with Language Service
Objective 4.3 · NLP
Conversational Language Understanding (CLU)
Objective 4.6 · NLP
Speech to Text and Custom Speech
Objective 4.4 · NLP
Text to Speech and Neural Voices
Objective 4.4 · NLP
Speech Translation
Objective 4.5 · NLP
Document Translation
Objective 4.5 · NLP
Custom Translator
Objective 4.5 · NLP
LUIS vs Conversational Language Understanding
Objective 4.6 · NLP
Power Virtual Agents and Azure Bot Framework
Objective 4.6 · NLP
Language Detection
Objective 4.2 · NLP
PII Detection and Extraction
Objective 4.3 · NLP
Extractive vs Abstractive Text Summarisation
Objective 4.3 · NLP
20 chapters
What is Generative AI?
Objective 5.1 · Generative AI
Large Language Models (LLMs)
Objective 5.1 · Generative AI
Azure OpenAI Service
Objective 5.2 · Generative AI
Prompt Engineering Fundamentals
Objective 5.3 · Generative AI
Microsoft Copilot and AI-900
Objective 5.4 · Generative AI
Types of Generative AI: Text, Image, Code, Audio
Objective 5.1 · Generative AI
Foundation Models and Fine-Tuning
Objective 5.1 · Generative AI
GPT Models: GPT-3.5, GPT-4, o-Series
Objective 5.2 · Generative AI
DALL-E for Image Generation
Objective 5.2 · Generative AI
Azure OpenAI Deployments and API Access
Objective 5.2 · Generative AI
Zero-Shot, Few-Shot, and Chain-of-Thought Prompts
Objective 5.3 · Generative AI
System Messages and Grounding Prompts
Objective 5.3 · Generative AI
Retrieval Augmented Generation (RAG)
Objective 5.3 · Generative AI
Embeddings and Vector Search
Objective 5.3 · Generative AI
Azure AI Content Safety
Objective 5.4 · Generative AI
Microsoft Copilot Ecosystem
Objective 5.4 · Generative AI
Microsoft Copilot Studio
Objective 5.4 · Generative AI
Azure AI Foundry (Azure AI Hub)
Objective 5.2 · Generative AI
Azure AI Search for RAG Applications
Objective 5.3 · Generative AI
Azure OpenAI Fine-Tuning
Objective 5.2 · Generative AI
Free AI-900 practice questions with full explanations. Test what you learn chapter by chapter.
AI-900 Practice Questions