AI-103 Cheat Sheet

Cheat sheet AI-103 Cheat Sheet Practice Questions Study Guide Print / Save PDF

Plan + Manage 25-30% of exam Foundry Model Choice Deployments Security Monitoring

Generative + Agents 30-35% of exam RAG Function Calling Agent Tools Evaluation Tracing

Computer Vision 10-15% of exam Multimodal Captioning VQA Image Generation Visual Safety

Text Analysis 10-15% of exam Entities Sentiment Translation Speech Structured JSON

Information Extraction 10-15% of exam Azure AI Search Vector Search Hybrid Search OCR Content Understanding

Quick Facts Exam AI-103 Credential AI Apps Associate Platform Microsoft Foundry Pass 700/1000 Time 120 min Questions 40-60 typical Price $165 US Blueprint Apr 16 2026

Observability PL Trace tokens latency safety Traces Tokens Latency Safety

Identity vs Key PL

Managed identity Keyless RBAC Rotates automatically

API key Secret value Must protect Manual rotation Identity beats secrets

Solution Picker PL Need keyless auth → Managed identity ( Security ) Need private traffic → Private endpoint ( Network ) Need grounded answers → RAG ( Sources ) Need retrieval index → AI Search ( Grounding ) Need visual reasoning → Multimodal model ( Vision ) Need document fields → Document Intelligence ( Extraction ) Need unsafe blocking → Content filters ( Safety ) Need tool actions → Agent Service ( Agents )

Foundry Planning PL Foundry AI app platform Hub Shared governance Project App workspace Model catalog Model selection Deployment Callable model endpoint Quota Capacity limit TPM Token throughput PTU Provisioned throughput

Filter vs Shield PL

Content filter Classifies content Blocks categories Input/output

Prompt shield Injection defense Jailbreak detection Indirect attacks Content vs attack

Security + Ops PL Managed identity Keyless auth Private endpoint Private network path Key Vault Secret storage RBAC Role authorization Content filter Moderates content Prompt shield Injection defense Monitor Production signals Trace Step evidence Safety event Risk signal

RAG GE Retrieve before generate Retrieve Ground Cite Answer

RAG vs Fine-tuning GE

RAG Adds facts Uses sources Easier updates

Fine-tuning Changes behavior Domain style Training data Facts vs behavior

Generation Picker GE Need exact schema → Structured outputs ( JSON ) Need API action → Function calling ( Tools ) Need low latency → Streaming ( UX ) Need bulk runs → Batch API ( Offline ) Need domain tone → Fine-tuning ( Behavior ) Need current facts → Grounded RAG ( Retrieval ) Need quality score → Evaluators ( Metrics ) Need debug path → Tracing ( Evidence )

Generative Patterns GE RAG Retrieve then generate Grounding Source-backed answer Embeddings Vector representation Function calling Tool invocation Structured outputs Schema-constrained JSON Streaming Token-by-token response Agent Framework workflows Multi-step orchestration Fine-tuning Model adaptation Batch API Offline bulk jobs Evaluation Quality scoring

Agent Core GE Agents need role tools memory Role Tools Memory Guardrails

Function vs Structured GE

Function Calls tool Takes action Uses schema

Structured Returns JSON No tool call Schema output Act vs format

Agent Building GE Agent role Behavior definition Goal Task objective Tool schema Callable contract Memory Conversation state Thread Conversation container File search Knowledge tool Code interpreter Analysis tool OpenAPI tool External API Multi-agent Orchestrated agents Approval flow Human checkpoint

Agent vs Flow GE

Agent Chooses tools Uses memory Goal-driven

Flow Fixed steps Deterministic path Orchestrated workflow Adaptive vs fixed

Quality Observability GE Groundedness Uses provided sources Relevance Answers request Fabrication Unsupported claim Latency Response time Token analytics Usage breakdown Drift Behavior change Feedback User quality signal Canary Controlled rollout

Vision Workloads VI Multimodal Text plus media Captioning Image description VQA Visual question answering Alt text Accessible description Image generation Text to image Inpainting Masked image edit Video analysis Segment understanding Object detection Locate items Visual policy Image safeguards

Text + Speech TE Entities Named facts Topics Theme extraction Summaries Condensed text Sentiment Tone detection PII Sensitive data Translator Language conversion STT Speech to text TTS Text to speech SSML Speech markup Custom speech Domain adaptation

Search Stack EX Vector plus keyword wins Vector BM25 Semantic Citations

Vector vs Hybrid EX

Vector Semantic similarity Embeddings Concept match

Hybrid Vector + keyword Better recall BM25 included Similarity vs combined

Extraction Picker EX Need similarity search → Vector search ( Embeddings ) Need keyword plus semantic → Hybrid search ( Recall ) Need result rerank → Semantic ranker ( Relevance ) Need image text → OCR ( Read ) Need form fields → Document Intelligence ( Forms ) Need multimodal parse → Content Understanding ( Media ) Need permissions → Security trimming ( Access ) Need source proof → Citations ( Trust )

Retrieval Search EX AI Search Retrieval index Vector search Similarity retrieval Hybrid search Keyword plus vector Semantic ranker Reranks results Indexer Data ingestion Chunking Document splitting Skillset Enrichment pipeline Citations Source evidence Security trimming Permission-filtered results

DocIntel vs Content EX

Doc Intelligence Forms/docs Layout fields OCR pipeline

Content Understanding Multimodal Analyzers Agent-ready output Documents vs multimodal

Document Extraction EX OCR Text from images Layout Document structure Fields Extracted values Tables Grid extraction Document Intelligence Form extraction Content Understanding Multimodal extraction Analyzer Extraction configuration Markdown output Reasoning-friendly text Grounded representation Trusted downstream data

Common Traps

Agent vs chatbot Agent uses tools ≠ Chatbot answers only

RAG vs memory RAG fetches sources ≠ Memory tracks conversation

Filter vs shield Filters classify content ≠ Shields block injection

Key vs identity Keys are secrets ≠ Identity is keyless

Vector vs semantic Vector finds similarity ≠ Semantic reranks text

Evaluation vs monitoring Evaluation scores quality ≠ Monitoring watches production

Vision text risk Image text can inject ≠ Treat media as input

Last Minute 1 . Use April 2026 weights 2 . Gen+agents largest 30-35% 3 . Plan domain 25-30% 4 . RAG needs search index 5 . Agents need tool controls 6 . Use managed identity 7 . Trace tokens and latency 8 . Evaluate groundedness and safety 9 . Vision includes prompt injection 10 . Extraction includes OCR

Microsoft Azure AI App and Agent Developer (AI-103) Practice Questions 200 questions Study Guide 10 topics Cheat Sheet 82 facts Flashcards 50 cards Shorts 1 short Videos 3 videos Blogs 3 blogs Free CE Podcast

Third-party resources · We may earn a commission from purchases.

AI-103 EXAM PREP AND PRACTICE 2026-2027: Comprehensive Study Guide with 1,000+ Practice Questions and 10 Full-Length Tests for the Microsoft Azure Engineer Associate Certification By PRESS, THINKFORGE $37.24 · Buy on Amazon Take courses on Udemy

Same family resources Explore More Microsoft Azure Certifications Continue into nearby exams from the same family. Each card keeps practice questions, study guides, flashcards, videos, and articles in one place.

Azure AI-900 Cheat Sheet 67 facts Practice Questions 200 questions Study Guide 30 topics Flashcards 50 cards Shorts 1 short Videos 4 videos Blogs 5 blogs

Azure AZ-104 Cheat Sheet 104 facts Practice Questions 200 questions Study Guide 75 topics Flashcards 50 cards Videos 4 videos Blogs 5 blogs Free CE

Azure AZ-900 Cheat Sheet 73 facts Practice Questions 200 questions Study Guide 40 topics Flashcards 50 cards Shorts 3 short s Videos 4 videos Blogs 5 blogs Free CE

Azure DP-700 Cheat Sheet 114 facts Practice Questions 200 questions Study Guide 24 topics Flashcards 50 cards Videos 3 videos Blogs 4 blogs Free CE

Microsoft Certified: Azure AI Fundamentals (AI-901) Cheat Sheet 102 facts Practice Questions 100 questions Study Guide 15 topics Flashcards 50 cards Shorts 1 short Videos 2 videos Blogs 3 blogs Free CE

Azure AI-102 Cheat Sheet 84 facts Practice Questions 200 questions Study Guide 37 topics Flashcards 50 cards Videos 2 videos Blogs 2 blogs

More From This Family Videos and articles for deeper review. Video FREE Microsoft AI-103 Practice Questions by Domain (2026) This exam Video Microsoft AI-103 Exam Guide 2026: Azure AI Apps and Agents This exam Video AI-102 vs AI-103 in 2026: Which Azure AI Exam, Foundry Shift, and Study Migration Video AI-200 Study Guide 2026: Build One Project Across All 4 Domains Article Microsoft AI-103 Exam Guide 2026: Azure AI Apps and Agents 17 min read Article FREE Microsoft AI-103 Practice Questions by Domain (2026) 11 min read Article AZ-104 Study Guide 2026: Pass the Azure Administrator Exam 19 min read Article Azure vs AWS Certification 2026: Which Cloud Cert Should You Get First? 18 min read

Independent exam preparation notice OpenExamPrep is an independent education provider, not affiliated with or endorsed by the exam sponsors named on this site. Exam and certification names identify what our resources help you study for; they do not imply sponsorship, approval, or review of our materials. Unless a resource expressly identifies authorized public material, our practice questions are independently developed simulations, not actual, recalled, or sponsor-provided exam items. We aim to reflect publicly available exam outlines and topic information in our study resources. Coverage, format, and difficulty may differ from the actual exam, and we cannot guarantee that every detail is accurate or current. Confirm exam requirements, fees, and policies with the official exam sponsor. Updated 2026-10-28 . Official exam sources checked April 16, 2026 . This is a study aid only and is not for use during the exam. Microsoft Learn AI-103 Study Guide Exam AI-103 Details Course AI-103T00-A Azure AI Search Azure AI Document Intelligence