This repository is designed to help you pass the Microsoft Azure AI Fundamentals (AI-900) exam with a clear, structured learning path.
It teaches AI from the ground up, starting with fundamentals that stay true across tools and vendors. You will build a solid foundation in core concepts like data, features and labels, common ML tasks, evaluation, and Responsible AI.
After the fundamentals are clear, each concept is mapped to Azure services and tooling where relevant. This approach helps you study for the exam without relying on memorization, because you understand what each service is doing and why it fits the workload.
- Azure AI Fundamentals (AI-900) candidates who want a clear, structured path to pass exam confidently
- Junior/senior software engineers who have not worked with AI before
- Developers who want a practical mental model of common AI workloads and the ML lifecycle
- Readers who want to understand both the “why” and the “how” of foundational AI topics
- Deep-knowledge learners who want strong fundamentals first, then mapping to Azure services and tooling
- What AI is, what ML is, and how common AI workloads differ
- How AI solutions are typically built (data, model, evaluation, deployment)
- How data becomes model inputs (features) and outputs (labels)
- How to define the problem clearly before choosing a model (what is the input and what is the output)
- Why training, validation, and testing exist, and how splitting works
- Why overfitting happens and how validation helps catch it
- How to choose the right task type (Classification, Regression, Clustering, Anomaly Detection)
- How evaluation metrics work at a conceptual level (what they mean and when to use them)
- Responsible AI basics, including Transparency and Generative AI Safety Layers
- How language, vision, and document processing workloads fit into real solutions
- What “model monitoring” means and why models can degrade over time
- How these concepts map to Azure services (reference page)
This repo doesn’t replace official Microsoft documentation. It compresses it into high signal study material and practice tests that cover all important signals and key points.
If you feel overwhelmed by the high volume of knowledge and want distilled signal without losing what matters, this is built for you: concise summaries where every sentence earns its place. The goal is to shorten the path to exam ready, deep understanding by focusing on the injected key information without drowning you in detail.
Use official docs when you want the full depth in details and original context. Use this repo when you want to learn faster, stay accurate, and still understand the “why” without having to wade through everything.
- Start with the documents in order. Each document builds on the previous one.
- Read for understanding first, then revisit documents when you want a fast, high signal refresher (definitions, decision rules, etc).
- Use the practice tests as a diagnostic: they tell you what to revisit, not just what you got wrong.
- When you miss a question, use the Detailed version to repair the underlying concept—not to memorize the answer.
- Use the Compressed version for high impact revision especially on the night before the exam (maximum coverage, low volume).
- As you revise, prioritize clarity: aim to explain each concept in your own words before moving on.
- AI and ML Foundations
- ML Lifecycle: Data Prep and Splitting
- Choosing ML Problem Types and Metrics
- Responsible AI and Generative AI Safety
- Language and Conversational Workloads
- Vision and Document Workloads
- Azure Mapping: ML, Search, and Services Reference
This repo includes practice tests to validate understanding and catch common confusion points. The goal is not only to test recall, but to make sure the concepts are clear and usable in real scenarios.
These practice tests are designed as a connected set with three types:
- The Raw version is the source of truth for all questions.
- Every Raw question is mirrored one-to-one in the Detailed version. The Detailed version adds deep explanations, clarifications, and exam-focused guidance.
- The Compressed version covers the same key points with fewer questions, making it useful for faster revision and high-impact review.
Practice tests come in several formats:
- Markdown study files (study focused, includes answers, works well as a reference)
- Microsoft Forms quizzes (practice focused, exam-style, with explanations where available)
Caution
Practice test links are not working yet they’re still under development. Please star this repo and click Watch → Releases (or All activity) to get updates as soon as the practice tests become available.
Practice tests come in three types:
This includes all questions with no explanations, just the question and the correct answer.
It acts like the source material.
| Practice Test | Markdown Study File | Microsoft Form Quiz |
|---|---|---|
| Practice Test 01 | View Study File | Open Quiz |
| Practice Test 02 | View Study File | Open Quiz |
This version beside the question and the correct answer, it includes deep explanations, breakdowns, and additional clarifications.
It is designed to help repair weak understanding, not just tell you whether an answer is right or wrong.
| Practice Test | Markdown Study File | Microsoft Form Quiz |
|---|---|---|
| Practice Test 01 | View Study File | Open Quiz |
| Practice Test 02 | View Study File | Open Quiz |
This version reduces question volume while preserving the most important concepts and exam signals.
It is designed for faster revision when you want maximum coverage with less reading.
| Practice Test | Markdown Study File | Microsoft Form Quiz |
|---|---|---|
| Practice Test 01 | View Study File | Open Quiz |
| Practice Test 02 | View Study File | Open Quiz |