AI-901 — Microsoft Azure AI Fundamentals Quick Review

Quick Review for Microsoft Azure AI Fundamentals (AI-901): high-yield AI workloads, Azure AI services, machine learning basics, responsible AI, and practice focus.

Quick Review Purpose

This Quick Review is for candidates preparing for the real Microsoft Azure AI Fundamentals (AI-901) exam from Microsoft. It focuses on the high-yield ideas you should be able to recognize quickly before moving into topic drills, mock exams, and detailed explanations.

AI-901 is a fundamentals exam. Expect conceptual and scenario-based questions more than deep implementation tasks. You should be able to:

  • Match common AI workloads to the right Azure AI service.
  • Distinguish machine learning, computer vision, natural language processing, speech, search, and generative AI scenarios.
  • Recognize responsible AI considerations.
  • Understand basic model training, evaluation, deployment, and inferencing language.
  • Avoid confusing similar Azure services and similar AI concepts.

This page is IT Mastery review support and is not affiliated with Microsoft.

High-Yield Exam Map

AreaWhat to know quicklyCommon exam angle
AI workloadsPrediction, classification, anomaly detection, vision, NLP, speech, search, generative AI“Which workload is this scenario?”
Responsible AIFairness, reliability and safety, privacy and security, inclusiveness, transparency, accountability“Which principle is being addressed?”
Machine learningFeatures, labels, training, validation, regression, classification, clustering, metrics“Which ML type or metric applies?”
Azure Machine LearningWorkspaces, compute, data assets, automated ML, designer, pipelines, endpoints“Which Azure ML capability helps?”
Computer visionImage analysis, object detection, OCR, document extraction, custom vision models“Which visual task or service?”
Natural languageSentiment, key phrases, language detection, entity recognition, translation, Q&A, summarization“Which text feature?”
SpeechSpeech-to-text, text-to-speech, speech translation, speaker-related capabilities“Which speech service task?”
Generative AIPrompts, tokens, completions, embeddings, grounding, RAG, content safety“How do you reduce hallucination or ground an answer?”
Search and knowledge miningIndexing, enrichment, semantic/vector search, retrieval“How do users search across documents?”

Azure AI Service Selection Rules

Use this table to answer service-selection questions quickly.

ScenarioBest fit to considerWhy
Build, train, evaluate, deploy ML modelsAzure Machine LearningEnd-to-end ML lifecycle platform
Non-experts want to try models from dataAutomated ML in Azure Machine LearningAutomates model and algorithm selection
Drag-and-drop ML workflowAzure Machine Learning designerVisual pipeline construction
Predict a numeric valueRegression modelOutput is continuous numeric
Predict a categoryClassification modelOutput is a class or label
Group similar records without labelsClustering modelNo known target label
Analyze images for tags/captions/objectsAzure AI VisionGeneral computer vision tasks
Extract printed/handwritten text from imagesOCR / Read capability in Azure AI VisionConverts image text to machine-readable text
Extract fields from invoices, receipts, formsAzure AI Document IntelligenceStructured document extraction
Analyze sentiment or key phrases in textAzure AI LanguageText analytics capabilities
Translate text between languagesAzure AI TranslatorText translation
Convert audio speech to textAzure AI SpeechSpeech recognition
Convert text to spoken audioAzure AI SpeechSpeech synthesis
Create a chatbot or conversational appAzure Bot Service, Copilot-related tools, or language servicesConversation orchestration and language understanding
Add enterprise document searchAzure AI SearchIndexing and retrieval over content
Use large language models for chat or generationAzure OpenAI Service / Azure AI model catalog capabilitiesGenerative AI model access
Ground generated answers in your documentsAzure AI Search plus generative AIRetrieval-augmented generation pattern

Service names and portal experiences can evolve. For exam readiness, focus on the capability being tested: vision, language, speech, search, machine learning, or generative AI.

Fast Decision Path

    flowchart TD
	    A[What is the scenario asking?] --> B{Train custom predictive model?}
	    B -->|Yes| C[Azure Machine Learning]
	    B -->|No| D{Image, video, or document?}
	    D -->|Image analysis / objects / OCR| E[Azure AI Vision]
	    D -->|Forms, invoices, receipts| F[Azure AI Document Intelligence]
	    D -->|No| G{Text or language?}
	    G -->|Sentiment, entities, key phrases| H[Azure AI Language]
	    G -->|Translation| I[Azure AI Translator]
	    G -->|No| J{Speech audio?}
	    J -->|Speech-to-text or text-to-speech| K[Azure AI Speech]
	    J -->|No| L{Search across content?}
	    L -->|Yes| M[Azure AI Search]
	    L -->|No| N{Generate or summarize with an LLM?}
	    N -->|Yes| O[Generative AI / Azure OpenAI Service]
	    N -->|No| P[Re-read scenario for workload clues]

Responsible AI: Principles and Traps

Microsoft commonly describes responsible AI using principles such as fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability. AI-901 questions often describe a business risk and ask which principle applies.

PrincipleWhat it meansExam clue
FairnessAI should avoid unfair bias or disparate impact“Model performs worse for one demographic group”
Reliability and safetyAI should behave consistently and safely under expected conditions“System must work reliably in critical scenarios”
Privacy and securityData and models should be protected; personal data handled appropriately“Sensitive data, access control, encryption, privacy”
InclusivenessAI should work for people with diverse needs and abilities“Accessible to users with disabilities or different languages”
TransparencyPeople should understand system behavior, limitations, and use of AI“Explain how the model makes decisions”
AccountabilityHumans and organizations remain responsible for AI outcomes“Who is responsible for monitoring and governance?”

Common Responsible AI Mistakes

  • Fairness vs inclusiveness: Fairness is about avoiding unjust bias in outcomes. Inclusiveness is about designing so more people can use the system.

  • Transparency vs accountability: Transparency explains what the system does and its limitations. Accountability assigns responsibility for decisions, oversight, and remediation.

  • Privacy vs security: Privacy concerns appropriate use and protection of personal information. Security concerns protecting systems, data, credentials, and access.

  • Safety is not just cybersecurity: Reliability and safety also include predictable behavior, testing, monitoring, and harm reduction.

Machine Learning Fundamentals

Core Vocabulary

TermMeaning
DatasetCollection of records used for training, validation, testing, or inference
FeatureInput variable used by the model
LabelKnown target value the model learns to predict
TrainingProcess of fitting a model to data
ValidationUsed during model development and tuning
Test dataUsed to estimate final model performance on unseen data
InferenceUsing a trained model to make predictions
ModelLearned function or algorithm that maps inputs to outputs
ExperimentA tracked ML run or set of runs
EndpointDeployed access point for model inferencing

Supervised vs Unsupervised Learning

TypeUses labels?OutputExample
Supervised learningYesPrediction based on known examplesPredict loan approval from past decisions
Unsupervised learningNoPatterns, clusters, associationsGroup customers by behavior
Reinforcement learningUses rewardsAction policyOptimize decisions through trial and feedback

AI-901 usually emphasizes supervised and unsupervised learning more than advanced reinforcement learning.

Regression, Classification, and Clustering

TaskPredictsExampleTrap
RegressionNumeric valuePredict sales revenue, temperature, delivery timeNot every “prediction” is regression
Binary classificationOne of two classesFraud/not fraud, approve/denyOutput is category, not number
Multiclass classificationOne of many classesIdentify product categoryStill classification
Multi-label classificationMultiple possible labelsTag image with several attributesMore than one label can apply
ClusteringGroups similar itemsSegment customersNo predefined label

Evaluation Metrics to Recognize

MetricUsed forMeaning
AccuracyClassificationOverall proportion of correct predictions
PrecisionClassificationOf predicted positives, how many were truly positive
RecallClassificationOf actual positives, how many were found
F1 scoreClassificationBalance between precision and recall
AUC / ROCClassificationAbility to separate classes across thresholds
MAERegressionAverage absolute prediction error
RMSERegressionPenalizes larger regression errors more strongly
R-squaredRegressionProportion of variance explained by the model

Precision vs Recall Decision Rule

  • Choose precision when false positives are costly. Example: incorrectly flagging legitimate transactions as fraud.
  • Choose recall when false negatives are costly. Example: failing to detect a serious disease or safety issue.
  • Use F1 score when you need a balance between precision and recall.

Overfitting and Underfitting

ProblemWhat happensTypical causePossible response
OverfittingPerforms well on training data but poorly on new dataModel learned noise or is too complexMore data, regularization, simpler model, better validation
UnderfittingPerforms poorly even on training dataModel too simple or features insufficientBetter features, more suitable algorithm, more training

Data Leakage

Data leakage occurs when training data includes information that would not be available at prediction time. It can make model performance look unrealistically good.

Common leakage examples:

  • Using a future outcome as a feature.
  • Training and testing on duplicate or near-duplicate records.
  • Preprocessing the full dataset before splitting into train/test sets.
  • Including fields that directly reveal the label.

Azure Machine Learning Review

Azure Machine Learning is the main Azure platform for building, training, managing, and deploying machine learning models.

CapabilityWhat it does
WorkspaceTop-level resource for Azure ML assets and collaboration
ComputeTraining or inference compute resources
Data assetsRegistered references to datasets
Jobs / experimentsRun and track training work
Automated MLTries algorithms and settings to find a strong model
DesignerVisual drag-and-drop ML workflow tool
PipelinesRepeatable workflows for data prep, training, and deployment
Model registryManage trained model versions
Managed endpointsDeploy models for online or batch inference
Responsible AI toolsHelp assess model behavior, explainability, and fairness

Azure ML Scenario Traps

If the scenario says…Think…
“No-code or low-code model creation”Automated ML or designer
“Data scientist needs full control with code”Notebooks, SDK/CLI, custom training jobs
“Repeatable ML workflow”Pipeline
“Track model runs and metrics”Experiments/jobs in Azure ML
“Deploy model for real-time predictions”Online endpoint
“Run predictions over many records asynchronously”Batch endpoint
“Choose the best algorithm automatically”Automated ML

Computer Vision Review

Computer vision workloads process images, video, or visual documents.

WorkloadDescriptionExample
Image classificationAssigns a label to an entire image“This image is a dog”
Object detectionFinds and locates objects in an imageDraw boxes around cars
OCRReads text from imagesExtract text from a scanned page
Image analysisTags, captions, categories, objects, metadataDescribe image content
Face detectionDetects presence/location of human facesCount faces in an image
Document extractionExtracts structured fields from formsInvoice total, vendor, date

Vision Service Matching

ScenarioLikely service/capability
Read text from a sign or scanned imageAzure AI Vision OCR / Read
Identify objects in photosAzure AI Vision
Create a custom model to classify specific product imagesCustom vision capability / custom model approach
Extract fields from receipts, invoices, tax forms, IDs, or business formsAzure AI Document Intelligence
Analyze images with tags and captionsAzure AI Vision image analysis
Detect unsafe or restricted visual contentContent safety or moderation-related capability

Common Vision Mistakes

  • Image classification vs object detection: Classification labels the whole image. Object detection identifies and locates objects within the image.

  • OCR vs document intelligence: OCR extracts text. Document intelligence extracts structured fields and layout from forms and documents.

  • Face detection vs face recognition: Detection finds faces. Recognition or identification compares identity. Be careful with wording and responsible AI implications.

  • Computer vision vs machine learning platform: Use Azure AI Vision for prebuilt vision tasks. Use Azure Machine Learning when the question is about building and managing custom ML models more generally.

Natural Language Processing Review

Natural language processing, or NLP, helps applications understand, analyze, translate, and generate human language.

NLP taskWhat it doesExample
Language detectionIdentifies language of textDetect English, French, Spanish
Sentiment analysisDetermines positive, negative, neutral sentimentAnalyze customer reviews
Opinion miningFinds sentiment about specific aspects“Food was great, service was slow”
Key phrase extractionFinds important phrasesExtract topics from feedback
Named entity recognitionIdentifies people, places, organizations, dates, etc.Extract company names
PII detectionFinds personally identifiable informationDetect names, emails, phone numbers
SummarizationCondenses long textSummarize support tickets
Question answeringAnswers user questions from contentFAQ bot
Conversational language understandingInterprets intents and entities“Book a flight tomorrow”

NLP Service Matching

ScenarioLikely service
Detect sentiment in customer commentsAzure AI Language
Extract key phrases from survey responsesAzure AI Language
Detect names, locations, organizations, or PIIAzure AI Language
Build an FAQ-style question answering experienceAzure AI Language question answering capability
Translate documents or messagesAzure AI Translator
Interpret user intent in a conversational appAzure AI Language conversational understanding
Generate free-form text or chat responsesGenerative AI model, such as through Azure OpenAI Service

NLP Traps

  • Translation is not the same as language detection. Translation converts text; detection identifies the language.
  • Entity recognition is not sentiment analysis. Entity recognition extracts things; sentiment measures attitude.
  • Question answering is not general search. Q&A returns targeted answers from a knowledge source; search retrieves ranked documents or passages.
  • NLP and generative AI overlap but are not identical. Traditional NLP can classify or extract. Generative AI can create new text, summarize, or answer conversationally.

Speech Review

Speech workloads process spoken audio or generate speech.

CapabilityDirectionExample
Speech recognitionSpeech to textTranscribe a meeting
Speech synthesisText to speechRead a response aloud
Speech translationSpeech in one language to text/audio in anotherLive multilingual captions
Speaker-related featuresAnalyze speaker characteristics depending on capabilityDistinguish speakers or voices in supported scenarios

Common Speech Mistakes

  • Speech-to-text transcribes audio into text.
  • Text-to-speech creates spoken audio from text.
  • Translation changes language; transcription alone does not.
  • NLP begins after text exists. If the source is audio, speech recognition may be needed before text analytics.

Generative AI Review

Generative AI creates new content such as text, code, images, summaries, or answers. Large language models, or LLMs, are a major generative AI category.

Key Concepts

ConceptMeaning
PromptInput instruction or question given to the model
Completion / responseModel-generated output
TokenUnit of text processed by the model
Context windowAmount of text the model can consider at once
System messageHigh-priority instruction that shapes assistant behavior
TemperatureControls randomness or creativity of responses
GroundingConnecting responses to trusted data sources
RAGRetrieval-augmented generation: retrieve relevant data, then generate answer
EmbeddingNumeric representation of text or data for similarity search
Vector searchFinds semantically similar content using embeddings
Fine-tuningFurther training a model for a specific style or task
Content filteringDetects or blocks harmful or policy-violating content

Prompting Patterns

PatternUse when…Example
Direct instructionThe task is simple“Summarize this paragraph in three bullets.”
Role promptingYou want style or perspective“Act as a support agent.”
Few-shot promptingYou want a format or patternProvide examples, then ask for another
Grounded promptingAccuracy depends on source material“Answer only from the provided policy.”
Structured outputApp needs parseable output“Return JSON with these fields.”

RAG vs Fine-Tuning vs Prompt Engineering

ApproachBest forNot best for
Prompt engineeringBetter instructions, formatting, constraintsAdding large amounts of private knowledge
RAGGrounding answers in current enterprise contentTeaching a model a new writing style by examples alone
Fine-tuningConsistent style, domain-specific patterns, specialized behaviorFrequently changing facts or documents
Content filteringReducing harmful outputsGuaranteeing factual correctness by itself

Generative AI Traps

  • Hallucination means the model may produce plausible but incorrect output.
  • Grounding reduces hallucination risk by providing trusted context, but does not eliminate all risk.
  • Embeddings do not generate answers. They represent content for similarity comparison.
  • Vector search is not the final answer generator. It retrieves relevant content; an LLM may then generate a response from that content.
  • Fine-tuning is not the default answer for adding current company documents. RAG is often the better pattern when facts change.
  • Temperature affects variation, not truthfulness by itself.
  • Content filters support safety, but human review and governance may still be required.

Azure AI Search and Knowledge Retrieval

Azure AI Search helps create searchable indexes over content. It can support traditional keyword search, semantic ranking, and vector-based retrieval patterns used in generative AI solutions.

ConceptMeaning
IndexSearchable structure containing fields from source content
IndexerPulls data from a source into an index
SkillsetEnrichment steps such as OCR, entity extraction, or language processing
AnalyzerProcesses text for search, such as tokenization
Semantic searchImproves relevance using language understanding
Vector searchSearches by similarity using embeddings
RAGUses retrieval results as grounding context for generation

Search Traps

  • Search is retrieval, not training. Indexing documents does not train a model in the same way ML training does.
  • Keyword search and vector search solve different retrieval problems. Keyword search matches terms; vector search matches semantic similarity.
  • OCR may be needed before search if source documents are scanned images.
  • Azure AI Search can be part of a generative AI architecture but is not itself the LLM.

Conversational AI Review

Conversational AI allows users to interact through natural language, often in chat or voice interfaces.

ComponentRole
Bot channelWhere users interact, such as web chat or messaging
Conversation logicControls flow, prompts, and responses
Language understandingDetects user intent and entities
Knowledge sourceProvides FAQ or document-based answers
Backend integrationConnects to business systems
Generative modelMay generate natural responses or summaries

Conversational AI Traps

  • Intent is what the user wants to do. Example: “BookFlight.”
  • Entity is a detail needed to complete the task. Example: destination, date, passenger count.
  • A bot is not automatically intelligent. It may use rules, language understanding, retrieval, generative AI, or a combination.
  • Generative chat still needs grounding and safety controls for enterprise use.

Security, Privacy, and Governance Basics

AI-901 is not a deep security exam, but you should recognize basic cloud and AI governance concerns.

ConcernWhat to look for
AuthenticationWho or what can access the service
AuthorizationWhat actions are allowed
Data privacyHandling personal or sensitive information properly
EncryptionProtecting data at rest and in transit
MonitoringTracking behavior, performance, and errors
Human oversightReviewing high-impact or uncertain decisions
Model driftModel performance changes as real-world data changes
AuditabilityAbility to review decisions, data, and system activity

Common Governance Mistakes

  • Treating a model score as a final decision without human oversight in sensitive contexts.
  • Ignoring monitoring after deployment.
  • Assuming training performance will remain stable forever.
  • Sending sensitive data to a model without considering privacy, access, retention, and compliance requirements.
  • Failing to document known limitations.

Exam-Style Scenario Clues

Use these clues to move quickly in practice questions.

Wording in questionLikely answer direction
“Predict next month’s revenue”Regression
“Approve or reject an application”Binary classification
“Classify support tickets by category”Multiclass classification
“Find unusual transactions”Anomaly detection
“Group customers by similar behavior”Clustering
“Extract text from scanned images”OCR
“Extract invoice total and vendor name”Document intelligence
“Identify sentiment in customer reviews”Language sentiment analysis
“Translate a web page”Translator
“Transcribe phone calls”Speech-to-text
“Read a response aloud”Text-to-speech
“Search across product manuals”Azure AI Search
“Answer questions using company documents”RAG with search plus generative AI
“Generate draft email replies”Generative AI
“Explain model decisions”Transparency / explainability
“Ensure system works for users with disabilities”Inclusiveness
“Reduce biased outcomes between groups”Fairness
“Protect personal data”Privacy and security

Common Candidate Mistakes

Mistake 1: Choosing Azure Machine Learning for Every AI Scenario

Azure Machine Learning is for building and managing ML models. Many AI-901 scenarios are better answered by prebuilt Azure AI services.

If the task is…Prefer…
Sentiment analysisAzure AI Language
Speech transcriptionAzure AI Speech
Image taggingAzure AI Vision
Invoice extractionAzure AI Document Intelligence
Text translationAzure AI Translator
Custom predictive modelingAzure Machine Learning

Mistake 2: Confusing Model Training with Inferencing

ActivityMeaning
TrainingModel learns from historical data
EvaluationModel performance is measured
DeploymentModel is made available for use
InferencingModel makes predictions on new data
MonitoringPerformance and behavior are tracked after deployment

Mistake 3: Ignoring Labels

If the scenario has known historical outcomes, it is likely supervised learning. If the scenario asks to discover natural groupings without known target values, it is clustering.

Mistake 4: Treating Accuracy as Always Best

Accuracy can be misleading with imbalanced classes. If only 1% of transactions are fraudulent, a model that always predicts “not fraud” can appear highly accurate but be useless for fraud detection.

Mistake 5: Using Generative AI Without Grounding

For enterprise answers based on policy, manuals, or internal documents, think about grounding and retrieval. A model’s general knowledge may be incomplete or outdated.

Mini Review Tables

Workload to Data Type

Data typeLikely workload
Tabular rows and columnsMachine learning
Images or video framesComputer vision
Scanned forms or invoicesDocument intelligence
Written textNLP or generative AI
Spoken audioSpeech
Large document collectionsSearch / knowledge mining
Prompts and generated responsesGenerative AI

Output Type to Model Type

OutputModel type
NumberRegression
Yes/noBinary classification
One category from manyMulticlass classification
Multiple labelsMulti-label classification
Group assignment without known labelsClustering
Unusual/not unusualAnomaly detection

Risk to Responsible AI Principle

RiskPrinciple
Discriminatory outcomesFairness
Unpredictable behavior in productionReliability and safety
Exposure of sensitive dataPrivacy and security
Inaccessible designInclusiveness
Users do not know AI is involvedTransparency
No owner for system decisionsAccountability

How to Use This Quick Review with Practice

A good AI-901 study loop is:

  1. Review the decision tables above.
  2. Complete topic drills by domain: ML, vision, language, speech, search, responsible AI, and generative AI.
  3. For every missed question, write down the clue you overlooked.
  4. Re-answer similar original practice questions until the service-selection pattern is automatic.
  5. Use mock exams to check timing and mixed-topic recognition.
  6. Read detailed explanations even for correct answers when you guessed.

When reviewing practice questions, focus less on memorizing wording and more on identifying the workload, data type, output type, and responsible AI concern.

Final Rapid Checklist

Before sitting for Microsoft Azure AI Fundamentals (AI-901), make sure you can answer these without hesitation:

  • Can I distinguish regression, classification, clustering, and anomaly detection?
  • Can I explain features, labels, training, testing, deployment, and inferencing?
  • Can I match vision, language, speech, search, and generative AI scenarios to Azure services?
  • Can I identify responsible AI principles from scenario wording?
  • Can I explain why RAG helps ground generative AI responses?
  • Can I distinguish OCR from document intelligence?
  • Can I distinguish sentiment analysis, entity recognition, key phrase extraction, and translation?
  • Can I choose between real-time and batch inference?
  • Can I spot overfitting, underfitting, data leakage, and metric traps?
  • Can I read a scenario and identify the main data type and desired output?

Practical Next Step

Use this Quick Review as your final concept pass, then move into IT Mastery practice: start with targeted topic drills, answer original practice questions by workload area, and use detailed explanations to close any gaps before attempting full mock exams.

Continue in IT Mastery

Use this Quick Review as a final concept map, then move into IT Mastery for focused topic drills, mixed practice sets, timed mock exams, and detailed explanations. The practice questions are original IT Mastery practice items; they are not official Microsoft questions, copied live-exam content, or exam dumps.

Browse Certification Practice Tests by Exam Family