ExamFinch.com My Study

Cheat sheet

Azure AI-900 Cheat Sheet

Practice this exam

AI Workloads

  • 15-20% of exam
  • Responsible AI AI Workloads Document Processing Anomaly Detection Use Cases

Machine Learning

  • 15-20% of exam
  • Regression Classification Clustering Training Data Azure ML

Computer Vision

  • 15-20% of exam
  • Image Analysis OCR Face Custom Vision Document Intelligence

NLP Workloads

  • 15-20% of exam
  • Language Speech Translator Sentiment Key Phrases

Generative AI

  • 20-25% of exam
  • Azure OpenAI Prompts RAG Copilot Responsible GenAI

Quick Facts

  • Exam AI-900
  • Credential Azure AI Fundamentals
  • Time 45 min
  • Pass 700/1000
  • Level Fundamentals
  • Retired Jun 30 2026
  • Prereq None

Responsible Six WO

  • Fair safe private inclusive transparent accountable
  • Fairness Reliability Privacy Inclusiveness Transparency Accountability

Workload Picker WO

  • Images or video → Vision
  • Forms or invoices → Document Intelligence
  • Text sentiment → Language
  • Speech audio → Speech
  • Translate text → Translator
  • Generate content → Azure OpenAI

Responsible AI WO

  • Fairness Avoid bias
  • Reliability Work safely
  • Privacy Protect data
  • Inclusiveness Serve everyone
  • Transparency Explain behavior
  • Accountability Human responsibility

AI Workloads WO

  • Vision Images/video
  • NLP Human language
  • Speech Audio language
  • Document processing Forms/text extraction
  • Anomaly detection Unusual patterns
  • Generative AI Creates content
  • Recommendation Suggest items

ML Targets ML

  • Number, label, group
  • Regression Classification Clustering

Regression vs Classification ML

Regression

  • Numeric target
  • Price/quantity
  • Continuous output

Classification

  • Category target
  • Yes/no
  • Class label
  • Number vs label

ML Picker ML

  • Predict price → Regression
  • Predict category → Classification
  • Group customers → Clustering
  • Image recognition → Deep learning
  • Train without code → AutoML
  • Serve predictions → Endpoint

ML Concepts ML

  • Feature Input variable
  • Label Target value
  • Training set Learn patterns
  • Validation set Tune model
  • Test set Final check
  • Model Learned function
  • Inference Use model

Classification vs Clustering ML

Classification

  • Known labels
  • Supervised
  • Predict class

Clustering

  • No labels
  • Unsupervised
  • Find groups
  • Labels vs groups

ML Techniques ML

  • Regression Predict number
  • Classification Predict class
  • Clustering Find groups
  • Deep learning Neural networks
  • Transformer Attention architecture
  • AutoML Automate training
  • Metric Measure performance

Azure ML ML

  • Workspace ML container
  • Designer Visual pipelines
  • Automated ML Model search
  • Compute Training resources
  • Dataset Data asset
  • Endpoint Model serving

Vision vs Document VI

Vision

  • Images
  • Objects
  • Captions

Document

  • Forms
  • Tables
  • Fields
  • Scene vs form

Vision Picker VI

  • Read image text → OCR
  • Describe image → Image Analysis
  • Detect objects → Object detection
  • Classify custom images → Custom Vision
  • Extract form fields → Document Intelligence
  • Detect faces → Face

Vision Services VI

  • Image Analysis Tags/captions
  • OCR Read text
  • Face Detect faces
  • Custom Vision Custom classifier
  • Object detection Locate objects
  • People detection Locate people in images
  • Content safety Moderate content

Document Intelligence VI

  • Prebuilt model Common documents
  • Custom model Your forms
  • Layout Text/tables
  • Invoice Billing fields
  • Receipt Purchase fields
  • Confidence Extraction score

Language Stack NL

  • Text, speech, translate
  • Language Speech Translator

Speech vs Translator NL

Speech

  • Audio input
  • Transcription
  • Voice output

Translator

  • Text input
  • Language conversion
  • No audio
  • Audio vs text

Language Services NL

  • Sentiment Opinion score
  • Key phrases Important terms
  • Entity recognition Named things
  • PII detection Sensitive text
  • Summarization Shorten text
  • Question answering Knowledge answers
  • Conversational language Intent/entities

Speech + Translate NL

  • Speech-to-text Audio to words
  • Text-to-speech Words to audio
  • Speech translation Audio translated
  • Translator Text translation
  • Custom voice Brand voice
  • Pronunciation Speaking assessment

RAG Flow GE

  • Retrieve facts before generation
  • Search Ground Generate Cite

Prompt vs RAG GE

Prompt

  • Instruction
  • Context words
  • Model input

RAG

  • Retrieve facts
  • Ground output
  • External data
  • Ask vs ground

GenAI Picker GE

  • Need factual answers → RAG
  • Need search memory → Embeddings
  • Need task assistant → Copilot
  • Need custom app → Azure OpenAI
  • Need better output → Prompt engineering
  • Need safety controls → Content filters

Generative AI GE

  • LLM Text generation
  • Prompt Input instruction
  • Completion Generated output
  • Grounding Use facts
  • RAG Retrieve then generate
  • Embeddings Vector meaning
  • Copilot AI assistant
  • Azure OpenAI Hosted models

OpenAI vs Copilot GE

Azure OpenAI

  • Build apps
  • Model APIs
  • Custom prompts

Copilot

  • Ready assistant
  • Product embedded
  • Task help
  • Platform vs assistant

Common Traps

Regression vs classification

  • Regression predicts numbers ≠ Classification predicts labels

Vision vs OCR

  • Vision sees images ≠ OCR reads text

Translator vs Speech

  • Translator handles text ≠ Speech handles audio

Prompt vs grounding

  • Prompt instructs model ≠ Grounding supplies facts

Responsible AI

  • Fairness reduces bias ≠ Accountability stays human

AI-900 timing

  • Exam retired Jun 30 2026 ≠ AI-901 replaced it

Last Minute

  • 1. AI-900 retired Jun 30 2026
  • 2. GenAI is 20-25%
  • 3. Regression = number
  • 4. Classification = label
  • 5. Clustering = unlabeled groups
  • 6. OCR = read image text
  • 7. Language = text analytics
  • 8. Speech = audio
  • 9. RAG = retrieve then generate
  • 10. Responsible AI has six principles

Azure AI-900

  • Practice Questions 200 questions Study Guide 30 topics Cheat Sheet 67 facts Flashcards 50 cards Shorts 1 short Videos 4 videos Blogs 5 blogs Podcast