AI-900

AI-900 Cheat Sheet 2026: Key AI & ML Concepts for the Exam

Every AI-900 topic condensed into quick-reference tables — AI workloads, machine learning, computer vision, NLP, and generative AI on Azure. Bookmark this for your final review.

Updated June 202613 min read

This cheat sheet is a fast, exam-focused review of everything on AI-900 (Microsoft Azure AI Fundamentals). It is built for your final days of prep — skim it, test yourself, and drill anything that feels unfamiliar. It is a memory aid, not a replacement for understanding: AI-900 questions describe a use case and ask which Azure AI service or ML approach fits, so know when to use each one.

Exam Snapshot

Passing Score

700 / 1000

Cost

$99 USD

Questions

40–60

Time

45 minutes

AI Workloads & ML

30–40%

Computer Vision & NLP

30–40%

Generative AI

20–25%

1. AI Workloads & Responsible AI

Common AI workload types

WorkloadWhat it does
Machine LearningPredict values or categories from data (foundation for the others).
Computer VisionInterpret images and video (objects, faces, text).
Natural Language ProcessingUnderstand and generate written and spoken language.
Document IntelligenceExtract fields and data from forms and documents.
Knowledge MiningIndex large content stores to make them searchable (Azure AI Search).
Generative AICreate new content — text, images, code — from prompts.

The 6 Responsible AI principles — memorize these

FairnessTreat all groups equitably; avoid bias.
Reliability & SafetyPerform consistently and handle unexpected conditions safely.
Privacy & SecurityProtect data and respect user privacy.
InclusivenessEmpower everyone, including people with disabilities.
TransparencyMake systems understandable; explain decisions.
AccountabilityPeople remain responsible for AI systems they build/operate.

Exam tip: Match the scenario to the principle. "The model denies loans to one demographic more often" = Fairness. "Users should know they're talking to a bot" = Transparency. "A human must approve the AI's decision" = Accountability.

2. Machine Learning Fundamentals

ML approaches — pick by the scenario

TypePredictsExample
RegressionA continuous numberHouse price, temperature
ClassificationA category / labelSpam vs not spam
ClusteringGroups in unlabeled dataCustomer segments

Labeled data → supervised (regression + classification). Unlabeled data → unsupervised (clustering).

Key ML terms

  • Features: Input variables (columns) used to make a prediction.
  • Label: The value the model predicts.
  • Training vs validation data: Train on one split, evaluate on a held-out split.
  • Model: The trained output that makes predictions on new data.

Classification evaluation metrics

AccuracyOverall correct predictions / total.
PrecisionOf predicted positives, how many were right.
RecallOf actual positives, how many were found.
F1 scoreBalance of precision and recall.

Azure Machine Learning tools

  • Automated ML (AutoML): Tries many algorithms automatically to find the best model.
  • Designer: Drag-and-drop, no-code pipeline builder.
  • Data labeling: Create labeled datasets for training.
  • Compute: Managed resources to train and deploy models.

Test the concepts you just reviewed

Try 40 Free AI-900 Practice Questions

Scenario-based questions with detailed explanations. No credit card required.

Start Free Practice →

3. Computer Vision

CapabilityWhat it does
Image classificationAssign a label to a whole image.
Object detectionLocate and label multiple objects with bounding boxes.
OCRRead printed and handwritten text from images.
Facial detection / recognitionDetect and identify faces (Azure AI Face).
Document IntelligenceExtract key/value pairs and tables from forms and invoices.

Service to know: Azure AI Vision covers analysis, OCR, and tagging. Custom Vision lets you train your own image classification / object detection models.

4. Natural Language Processing

CapabilityWhat it does
Key phrase extractionPull the main talking points from text.
Sentiment analysisScore text as positive, negative, or neutral.
Entity recognition (NER)Identify people, places, dates, organizations.
Language detectionIdentify the language of text.
TranslationTranslate text/speech between languages (Azure AI Translator).
Speech to text / text to speechTranscribe and synthesize spoken language (Azure AI Speech).
Conversational language understandingMap utterances to intents and entities for bots.

Service to know: Azure AI Language handles text analytics, NER, sentiment, and conversational understanding. Azure AI Speech handles speech-to-text, text-to-speech, and translation.

5. Generative AI & Azure OpenAI

Core concepts

Large Language Model (LLM)Model trained on huge text corpora that generates language.
PromptThe input/instruction you give the model.
CompletionThe model's generated response.
TokenChunk of text the model processes; billing/limits are token-based.
EmbeddingNumeric vector representing meaning; powers search and RAG.
Grounding / RAGSupply your own data so answers are based on it, reducing hallucination.
CopilotAn AI assistant embedded in an app to help users complete tasks.

Where it runs: Azure OpenAI Service provides GPT models for text/code, plus image and embedding models — with Azure security, regional control, and Responsible AI content filters. Azure AI Foundry is the portal/platform for building and deploying generative AI solutions.

Exam tip: Generative AI is the newest and most heavily weighted domain. Know prompts, tokens, grounding/RAG, Copilots, and that content filters enforce Responsible AI.

6. Azure AI Services Quick Map

Need…Use…
Analyze / tag images, OCRAzure AI Vision
Train your own image modelCustom Vision
Sentiment, NER, key phrasesAzure AI Language
Speech-to-text, TTS, translationAzure AI Speech
Extract data from forms/invoicesAzure AI Document Intelligence
Search large content storesAzure AI Search
Generate text/code/imagesAzure OpenAI Service
Build and deploy AI solutionsAzure AI Foundry
Train/deploy custom ML modelsAzure Machine Learning

7. Acronym Quick List

AI — Artificial Intelligence

ML — Machine Learning

NLP — Natural Language Processing

NER — Named Entity Recognition

OCR — Optical Character Recognition

LLM — Large Language Model

RAG — Retrieval-Augmented Generation

AutoML — Automated Machine Learning

CLU — Conversational Language Understanding

TTS / STT — Text-to-Speech / Speech-to-Text

F1 — Balance of precision & recall

RAI — Responsible AI

Reviewed the cheat sheet? Now prove you're ready.

Take the free 5-minute AI-900 readiness quiz — no signup required — or jump into 40 free practice questions calibrated harder than the real exam.

Common Questions

Is a cheat sheet enough to pass AI-900?

A cheat sheet is a fast review and memory aid, not a substitute for understanding. Use it to consolidate concepts after working through Microsoft Learn and practice questions. AI-900 questions describe a use case and ask which Azure AI service or ML approach fits, so you need to know when to use each one — not just recognize its name.

What is the difference between supervised and unsupervised learning?

Supervised learning trains on labeled data where the correct answer is known — that covers regression (predict a number) and classification (predict a category). Unsupervised learning finds patterns in unlabeled data, such as clustering customers into segments. If the scenario gives historical outcomes to learn from, it's supervised.

What is the passing score for AI-900?

700 out of 1000 on a scaled scoring system (roughly 70%). The exam has 40–60 questions, a 45-minute time limit, and costs $99 USD.

What is the difference between Azure AI Vision and Custom Vision?

Azure AI Vision is a prebuilt service that analyzes, tags, and reads text from images out of the box. Custom Vision lets you train your own image classification or object detection model on your own labeled images when the prebuilt models don't recognize what you need.

About MSCertQuiz

MSCertQuiz provides 500 practice questions per certification, calibrated harder than the real exam so test day feels easier. Questions are built by certified professionals and updated for 2026 exam objectives. Start with 40 free questions — no credit card required.