AZ-305 Learning Portal

AZ-305 Cheat Sheet

Workload-to-service mappings, decision flows, and exam traps — optimised for last-minute revision. Scan fast.

Section 1 — Workload-to-Service Mapping

WorkloadPrimary Azure ServiceKeyword Cues
Image classification / taggingAzure AI Vision (Tags) · Custom Visionlabel whole image, no boxes, categories
Object detectionAzure AI Vision (Objects) · Custom Visionbounding box, count items, locate
OCR — printed/handwritten textAzure AI Vision (Read API)extract text from image, receipts, signs
Forms with key/value + tablesAzure AI Document Intelligenceinvoice, claim form, structured fields
Face detection / attributesAzure AI Face (Detect)find faces, count, age/emotion attributes
Face identification / verificationAzure AI Face (Limited Access)who is this person, 1:1 / 1:N match
Sentiment / key phrase / NER / languageAzure AI Languagetone, named entities, key topics, language ID
Speech-to-text / text-to-speechAzure AI Speechtranscribe audio, voice synthesis, captions
Text translationAzure AI Translatortranslate text between languages
Speech translation (audio in)Azure AI Speech (translation)audio input → translated output
Generative chat / completionsAzure OpenAI in Azure AI FoundryGPT, summarisation, draft email, code-gen
RAG over enterprise docsAzure AI Search + Azure OpenAI (Prompt Flow)ground answers in company data
Train tabular regression/classificationAzure Machine Learning (AutoML / Designer)predict price, classify churn, no-code/SDK
Visual ML pipeline (drag-and-drop)Azure ML Designerno-code, components, canvas

KEY RULE: "OpenAI" in a scenario almost always means Azure OpenAI inside Azure AI Foundry — never the public OpenAI API.

Section 2 — The Six Responsible AI Principles

Fairness

Tested concern: Equal outcomes across demographic groups

Mitigation: Diverse data; fairness assessment in Responsible AI dashboard; demographic parity / equalised odds checks

Reliability and safety

Tested concern: Works on edge cases; human-in-the-loop on high-stakes calls

Mitigation: Red-teaming; monitoring; HITL approval gates; grounding for GenAI

Privacy and security

Tested concern: Personal data protected; resists data exfiltration / prompt injection

Mitigation: Data minimisation; encryption; RBAC; Content Safety; Prompt Shields

Inclusiveness

Tested concern: Everyone can USE the system (accents, abilities, languages)

Mitigation: Diverse data; alternative modalities (captions, voice, alt text); WCAG testing

Transparency

Tested concern: Users understand what the AI does, its limits, and that it IS AI

Mitigation: Transparency Notes; explainability dashboard; AI disclosure to users

Accountability

Tested concern: Humans (not AI) own the system's behaviour

Mitigation: Defined ownership; governance reviews; audit logs; escalation paths

TRAP: Fairness is about EQUAL OUTCOMES. Inclusiveness is about EQUAL ACCESS. If the scenario emphasises participation or accessibility → inclusiveness.

Section 3 — ML Technique Decision Flow

TechniqueOutputCanonical ScenarioEval Metrics
Regression (supervised)Continuous numberPredict house price, sales next month, temperatureMAE, RMSE, R²
Classification (supervised)Category / classSpam vs ham, fraud vs not fraud, cat/dog/rabbitAccuracy, Precision, Recall, F1, ROC-AUC
Clustering (unsupervised)Group assignments (no labels)Customer segmentation, anomaly groupingSilhouette, inertia
Deep learning (neural nets)Anything — usually images/audio/textImage classification, speech recognitionTask-specific (accuracy, BLEU, etc.)
Transformer (attention)Sequence (usually text)LLMs, translation, summarisationPerplexity, groundedness, BLEU, ROUGE

MEMORISE: "predict a number" → regression. "predict a category" → classification. "group similar with no labels" → clustering.

Section 4 — Computer Vision Cheat Card

CapabilityReturnsPick WhenService
Image classificationLabel(s) for whole image (no box)Need WHAT is in the picture, not whereAzure AI Vision Tags · Custom Vision
Object detectionLabels + bounding boxesNeed WHERE / count / locate itemsAzure AI Vision Objects · Custom Vision
OCR (Read API)Text + line/word coordinatesPlain printed/handwritten text from imagesAzure AI Vision (Read)
Document IntelligenceKey-value pairs, tables, fieldsForms, invoices, claims, structured docsAzure AI Document Intelligence
Face DetectionBounding box + attributesFind faces / count / age / emotionAzure AI Face (Detect)
Face Verification (1:1)Same person? Yes/No + scoreConfirm a specific person — Limited AccessAzure AI Face (Verify)
Face Identification (1:N)Person ID from PersonGroupWho is this? — Limited AccessAzure AI Face (Identify)

TRAP: Classification = WHOLE image label. Detection = label + bounding box. If the question mentions counting or locating → detection.

Section 5 — NLP Cheat Card

CapabilityWhat It DoesService
Key phrase extractionSurface main topics in textAzure AI Language
Named Entity Recognition (NER)Tag people, places, orgs, dates, moneyAzure AI Language
Sentiment analysisPositive / neutral / negative + opinion miningAzure AI Language
Language detectionIdentify which language a text is inAzure AI Language
Summarisation / Q&A / CLUSummarise docs; answer over KB; intent + entitiesAzure AI Language
Speech-to-text / TTS / Speech translationTranscribe audio; synthesise voice; speech in → translated text outAzure AI Speech
Text translationTranslate text between 100+ languagesAzure AI Translator

TRAP: Audio in → Azure AI Speech (even if output is translated text). Translator is text-in, text-out only.

Section 6 — Generative AI Stack

Azure AI Foundry

Unified portal for projects, model catalogue, deployments, Prompt Flow, evaluations, Content Safety. Supersedes the old Azure OpenAI Studio.

Azure OpenAI Service

OpenAI's models (GPT-4o, gpt-4.1, o-series, embeddings, DALL·E, Sora) inside Azure with privacy + regional residency. Runs INSIDE Foundry.

Foundry Model Catalog

1,800+ models — Azure OpenAI, Microsoft Phi, Meta Llama, Mistral, Cohere, Hugging Face, Nvidia NIM, DeepSeek, Stability AI.

Serverless API vs Managed Compute

Serverless API = pay per token, Microsoft hosts. Managed compute = your dedicated GPU VMs, more control, you pay for the VM regardless of traffic.

Prompt Flow

Visual / code authoring for chaining LLM calls, Python steps, prompts, and connections (e.g. Azure AI Search) into a runnable evaluatable pipeline. Standard way to build RAG.

Azure AI Content Safety

Four harm categories: Hate · Sexual · Violence · Self-harm (severity 0–6). Plus Prompt Shields, Protected Material detection, Groundedness detection. Default-on for Azure OpenAI deployments.

Content Safety extras to memorise

  • Prompt Shields — blocks direct & indirect prompt injection / jailbreak (User Prompt Attacks).
  • Groundedness detection — flags hallucinated / ungrounded responses in RAG.
  • Protected Material detection — flags copyrighted text / code in completions; required for Customer Copyright Commitment.

Section 7 — Top Exam Traps

Read each one carefully — these are the most commonly missed question patterns on AZ-305.

1.

RAG vs fine-tuning

RAG injects fresh, citable context at runtime — pick it for changing enterprise docs (HR handbook, policies). Fine-tuning bakes style/format into model weights — pick it for a tone or output schema, not for facts.

2.

Image classification vs object detection

Classification labels the WHOLE image (no boxes). Detection adds bounding boxes and counts. If the question mentions WHERE, COUNT, or LOCATE → detection.

3.

Hallucination ≠ prompt injection ≠ bias

Hallucination = confidently wrong (Reliability/Safety, mitigate with grounding). Prompt injection = adversarial override (Privacy/Security, mitigate with Prompt Shields). Bias = unequal outcomes (Fairness).

4.

Fairness vs Inclusiveness

Fairness = equal OUTCOMES across groups. Inclusiveness = equal ACCESS / participation (accents, abilities, modalities). Speech-to-text struggling with non-native accents → inclusiveness, NOT fairness.

5.

Sentiment ≠ language detection

Sentiment returns positive/neutral/negative tone. Language detection returns the language code (en, fr, ja). If the scenario says 'we don't know what language' — that is language detection.

6.

Translator vs Speech Translation

Translator = text-in, text-out. If the input is AUDIO, the answer is Azure AI Speech (speech translation), even if the output is text in another language.

7.

Azure OpenAI vs public OpenAI API

If a scenario mentions Azure data residency, enterprise SLA, or RBAC + Microsoft privacy commitments — the answer is Azure OpenAI in Azure AI Foundry, never 'call OpenAI's public API.'

8.

Limited Access features

Face Identify, Face Verify, the face ID property, Custom Neural Voice Pro, Speaker Recognition, and Celebrity Recognition are gated behind Microsoft's Limited Access policy. Detection and attribute analysis are NOT.

9.

OCR vs Document Intelligence

Plain text from photos / signs / handwriting → OCR (Read). Forms with fields, tables, key-value pairs (invoices, claims, tax forms) → Azure AI Document Intelligence.

10.

AutoML vs Designer

AutoML = wizard that auto-tries algorithms on tabular data (pick a target column and go). Designer = drag-and-drop pipeline canvas where you wire components yourself. Both are no-code; AutoML is auto, Designer is visual.

Cheat sheet last reviewed 2026-04-27. Based on AZ-305 exam objectives current as of May 2, 2025.