CloudExamPro — Free AWS Certified AI Practitioner (AIF-C01) Study Guide
CloudExamPro Free Study Guide · 2026

AWS Certified AI Practitioner
(AIF-C01) Study Guide

Free Study Guide — Pattern recognition. Decision matrices. Clear exam-focused explanations.

Independently written. Reviewed against AWS AIF-C01 Exam Guide v1.2, published 29 October 2026.

Use this free AWS AIF-C01 study guide to prepare for the AWS Certified AI Practitioner exam with five-domain coverage, 17 chapters, AWS service comparisons, decision matrices, and practical revision plans.

5
Exam Domains
17
Chapters
13
Advanced Reference Modules
30+
Decision Matrices
25
Exam Traps

What This Free AWS AIF-C01 Study Guide Covers

This free AWS Certified AI Practitioner (AIF-C01) study guide is a structured learning resource for candidates preparing for the AWS AIF-C01 certification exam. It explains the exam concepts, compares relevant AWS AI services, and provides decision frameworks and revision plans across all five official exam domains.

  • Domain 1 — Fundamentals of AI and Machine Learning: 20% of scored content.
  • Domain 2 — Fundamentals of Generative AI: 24% of scored content.
  • Domain 3 — Applications of Foundation Models: 28% of scored content.
  • Domain 4 — Guidelines for Responsible AI: 14% of scored content.
  • Domain 5 — Security, Compliance, and Governance for AI Solutions: 14% of scored content.

The guide contains 17 learning chapters, 13 advanced reference modules, AWS service comparisons, decision matrices, a glossary, and 7-day and 14-day study plans. It was reviewed against the official AWS AIF-C01 exam guide, version 1.2, published on 29 October 2026.

What is not included: this study guide is not a full-length practice exam and does not reproduce the separate diagnostic question set. Use the free 25-question AIF-C01 diagnostic on its dedicated page to check your readiness after studying.

Recommended use: review the exam overview, study each domain, compare services using the decision tables, then follow the 7-day or 14-day revision plan that fits your schedule.

Editorial Scope, Sources, and Exam Alignment

Who this resource is for: learners preparing for the AWS Certified AI Practitioner (AIF-C01) exam who need a structured explanation of AI and machine learning fundamentals, generative AI, foundation model applications, responsible AI, and AI security and governance.

How the material is organized: the five domain names, task objectives, and scored-content weightings follow the AWS exam guide. The explanations, comparison tables, decision frameworks, examples, and revision recommendations are CloudExamPro learning material designed to help readers understand and apply those objectives; they are not official AWS exam questions or an AWS publication.

Source-checking approach: exam alignment is checked against the official AIF-C01 exam guide, its revision history, and relevant in-scope AWS services and AWS product documentation. AWS may revise its objectives and service scope, so candidates should verify the latest official materials before booking the exam.

Last content review: 8 November 2026, against Exam Guide v1.2 (published 29 October 2026). This review date describes the current editorial check; it does not imply that AWS endorsed or certified this guide.

Important distinction: domain percentages represent the share of scored exam content, not a guaranteed number of questions. The official exam guide remains the authority for exam format, policies, and objectives.

How to Use This Guide

This guide is built for the AIF-C01 exam, not for general AI education. Every chapter maps to official exam objectives. Every decision matrix reflects a distinction the exam tests. Every trap is a confusion that costs candidates points.

Coach's Note

Read the chapters in order if you are new to AI/ML. If you already work with AWS AI services, start with the Advanced Reference Modules (M1–M8), then read only the chapters where the matrices reveal gaps in your reasoning. The Final-Day Revision Sheet (M10) is designed for the last 24 hours before your exam.

Reading Paths

Table 0.1 — Choose Your Reading Path
If You Are…Start WithThenSkip Until Review
New to AI/MLTerminology Primer → Ch 1–5Ch 6–17 in orderAdvanced Reference Modules M6–M8
Experienced with AWS but new to AICh 6–9 (GenAI)Ch 10–13 (FM applications)Ch 1–5 (skim)
Experienced with AI/ML but new to AWSCh 5, Ch 10, Ch 11Ch 16–17 (security/governance)Ch 1–4 (skim)
Exam in 7 daysM10 (Final-Day Revision)M6 (Trap Library) → M7 (Trigger Phrases)Deep chapter reads

Free readiness check: After reviewing the concepts, use the AIF-C01 free 25-question diagnostic exam to check your current readiness. The diagnostic is kept on its dedicated exam page so this guide can stay focused on teaching and reference material.

Conventions Used in This Guide

  • Decision Matrix — a comparison table with a decisive factor column. The exam rewards the candidate who can name the deciding requirement, not the one who memorizes service names.
  • Exam Trap — a specific confusion between two or more concepts that the exam exploits in distractor options.
  • Memory Anchor — a short, accurate recall phrase. Not a mnemonic gimmick — a compressed distinction.
  • Coach's Takeaway — the one-sentence rule to carry into the exam.

AIF-C01 Exam Overview

Verified against the current official AWS Certified AI Practitioner exam guide. This guide follows the official blueprint, not the distribution of any practice question bank.

Table 0.2 — Official Exam Domains and Weights
DomainWeightFocus
Domain 1: Fundamentals of AI and ML20%AI/ML concepts, learning paradigms, problem types, data, evaluation metrics, AWS AI services
Domain 2: Fundamentals of Generative AI24%Foundation models, LLM mechanics, prompt engineering, hallucinations, RAG
Domain 3: Applications of Foundation Models28%Amazon Bedrock, SageMaker AI, customization strategy, agents, Guardrails, evaluation
Domain 4: Guidelines for Responsible AI14%Fairness, bias, explainability, transparency, human oversight, safety
Domain 5: Security, Compliance, and Governance14%IAM, encryption, PrivateLink, CloudTrail, Macie, Config, Inspector, Artifact, Trusted Advisor, data residency, governance
Important

The percentage of scored exam content is not a guaranteed number of questions on any individual exam. This guide teaches all domains at full depth. Do not skip a domain because its weight is lower.

Exam Logistics — Official Format

  • 65 questions: 50 scored and 15 unscored.
  • Duration: 90 minutes (about 83 seconds per question on average).
  • Question types: Multiple choice, multiple response, ordering, and matching.
  • Passing score: 700 on a scaled range of 100–1,000. Scoring is compensatory; only the overall result determines pass/fail.
  • Unscored questions: The 15 pilot questions are not identified. Treat every question as scored.
  • Answer strategy: Unanswered questions are incorrect; there is no penalty for guessing. Answer every question.

Verified against AWS's official AIF-C01 exam guide and certification overview. Recheck before booking.

AIF-C01 Exam Guide v1.2 — Alignment Update

Current source baseline

Reviewed against AWS AIF-C01 Exam Guide v1.2, published 29 October 2026. The five domain weights remain 20%, 24%, 28%, 14%, and 14%. This supplement strengthens the existing 17 chapters with focused revision of current objectives.

Official sources: Exam Guide · Revision history · Exam overview.

Domain 2 — Agentic AI and Context Engineering

  • Agentic AI: Goal-directed, multi-step behavior using reasoning, tools, and actions within permissions; distinguish it from one-shot text generation.
  • Multi-agent patterns and communication: Specialized agents delegate, collaborate, exchange results, and coordinate complex work.
  • MCP: Model Context Protocol standardizes connections between AI applications/agents and external tools or data systems.
  • Memory management: Retain relevant state across steps or interactions. Workflow orchestration: Coordinate sequence, handoffs, checkpoints, and completion.
  • Context engineering: Design the full context—instructions, retrieved knowledge, history, tools, and constraints—not just prompt wording.
  • Token-based pricing: Input/output tokens, model choice, and pricing mode affect cost. Long context and verbose outputs increase cost and may increase latency.
  • AWS technologies to recognize: Amazon Bedrock, SageMaker AI, SageMaker JumpStart, Amazon Quick, Kiro, Strands Agents, and Bedrock AgentCore.

Domain 3 — Foundation Model Application Decisions

Table V1.2-1 — Vector database recognition
ServiceScenario clue
Amazon OpenSearch ServiceSearch plus vector similarity retrieval.
Amazon AuroraRelational application data with vector retrieval.
Amazon NeptuneGraph data and relationships.
Amazon RDS for PostgreSQLPostgreSQL with vector extensions.
Table V1.2-2 — Customization trade-offs
ApproachBest fitTrade-off
In-context learningPrompt examples/instructions guide the model.Fast, but uses context tokens and window capacity.
RAGCurrent, private, or source-grounded knowledge.Depends on retrieval/index quality.
Fine-tuningConsistent task behavior or domain style.Needs curated data, evaluation, time, and cost.
Continued pre-trainingDeeper domain language/knowledge exposure.More compute- and data-intensive.
Model distillationSmaller student model approximates a larger teacher.Lower latency/cost may mean capability loss.

Model selection: Compare modality, language support, size/complexity, latency, input/output limits, customization, prompt caching, cost, compliance, and quality. Evaluation: Know ROUGE, BLEU, BERTScore, LLM-as-a-judge, human review, and benchmarks. Evaluate RAG, agents, and workflows using task completion, user satisfaction, and cost per interaction. Fine-tuning data: Know curation, governance, size, labeling, representativeness, and RLHF.

Domain 4 — Responsible AI

  • Include environmental impact and sustainability in model selection.
  • Assess dataset inclusivity, diversity, balance, and source quality.
  • Recognize IP claims, biased outputs, hallucinations, end-user harm, and loss of trust as legal or reputational risks.
  • Know subgroup analysis, human audits, label quality, SageMaker Clarify, SageMaker Model Monitor, and human-in-the-loop review workflows.
  • Understand Model Cards, open-source model information, licensing, data provenance, explainability, and human feedback.

Domain 5 — Security, Privacy, and Governance

Table V1.2-3 — Services and concepts to recognize
ItemExam association
Bedrock AgentCore Identity / PolicyAgent identity, authentication, and permissions.
Data lineage/catalogingDocumenting data origin, movement, ownership, and use.
Secure data engineeringData quality, privacy techniques, access control, and integrity.
AWS Config / Amazon InspectorConfiguration/compliance evaluation / vulnerability management.
AWS CloudTrail / Trusted AdvisorAPI audit trails / security, reliability, and cost recommendations.
Generative AI Security Scoping MatrixIdentify security concerns for different GenAI architectures.

AI security risks: Prompt injection, data leakage, unsafe tool invocation, toxicity, and poor output validation. Recognize least privilege, encryption at rest/in transit, input/output filtering, audit logs, and human approval for sensitive actions. Grounding: RAG ties answers to retrieved sources; validation checks outputs; confidence scoring can flag uncertainty. Citations improve traceability but do not guarantee correctness.

Version 1.2 revision note

AWS's v1.2 history records six services removed from the out-of-scope list: Amazon Elastic Transcoder, AWS Elemental MediaStore, AWS IoT 1-Click, AWS IoT Analytics, AWS IoT Events, and Amazon Nimble Studio. This does not mean they are newly emphasized exam topics. Use current task statements and the in-scope list as the primary boundary.

Study Plans

7-Day Aggressive Plan

Table 0.3 — 7-Day Study Plan
DayFocusDeliverable
1Ch 1–3 (AI/ML foundations, lifecycle)Complete Term Primer + Ch 1–3 Knowledge Checks
2Ch 4–5 (Evaluation, AWS services)Memorize evaluation metrics matrix
3Ch 6–7 (GenAI, LLM mechanics)Complete inference parameter matrix
4Ch 8–9 (Prompt engineering, RAG)Prompt technique comparison table
5Ch 10–13 (Bedrock, SageMaker, customization)Bedrock vs SageMaker matrix
6Ch 14–17 (Responsible AI, security)M6 Trap Library + M7 Trigger Phrases
7M9–M10 (Rapid review, final-day sheet)M11 Self-Assessment + M13 Exam-Day Checklist

14-Day Recommended Plan

Table 0.4 — 14-Day Study Plan
DaysFocusPriority
1–3Ch 1–5 (Domain 1)Foundations — do not rush
4–6Ch 6–9 (Domain 2)Highest combined weight with Domain 3
7–10Ch 10–13 (Domain 3)Largest single domain (28%)
11Ch 14–15 (Domain 4)Responsible AI
12Ch 16–17 (Domain 5)Security, compliance, governance
13M1–M8 (Advanced Reference Modules)Decision matrices + trap library
14M9–M13 (Review + Exam Day)Final-day revision + checklist

AI/ML Terminology Primer

If you are new to AI/ML, learn these 40 terms before Chapter 1. They appear throughout the guide and the exam.

Table 0.5 — Essential AI/ML Terminology
TermPlain-English DefinitionExam Context
Artificial Intelligence (AI)Broad field of making machines perform tasks requiring human intelligenceThe outermost category
Machine Learning (ML)Subset of AI that learns patterns from dataMost exam scenarios sit here
Deep LearningML using multi-layer neural networksImages, audio, text at scale
Generative AICapability to generate new content, commonly using deep-learning foundation modelsText, image, audio, video, and code generation
Foundation Model (FM)Large pre-trained model adaptable to many tasksBedrock's core offering
Large Language Model (LLM)Foundation model specialized for textChatbots, summarization, translation
TokenUnit of text a model processes (word, subword, character)Context window, billing
EmbeddingNumeric vector representing meaningRAG, semantic search
Context WindowMaximum tokens a model can process at onceWhy long inputs fail
PromptInput instruction to a modelPrompt engineering
InferenceUsing a trained model to generate outputRuntime phase
TrainingLearning model weights from dataPre-training, fine-tuning
Fine-TuningFurther training a model on labeled task dataDomain adaptation
Continued Pre-TrainingFurther training on unlabeled domain dataDomain knowledge expansion
RAGRetrieval Augmented Generation — grounding responses in external dataReduces hallucinations
HallucinationModel generates plausible but false contentKey GenAI risk
TemperatureInference parameter that influences sampling variabilityLower = more focused; higher = more varied (not a factuality guarantee)
Top KLimits next-token candidates to K most probableDiversity control
Top PNucleus sampling — limits candidates by cumulative probabilityAlternative to Top K
GuardrailsSafety controls on model input and outputBedrock Guardrails
AgentAI system that reasons and calls external tools/APIsBedrock Agents
Vector DatabaseDatabase optimized for similarity search on embeddingsOpenSearch, Aurora pgvector
ChunkingSplitting documents into smaller units for embeddingRAG pipeline
OverfittingModel memorizes training data, fails on new dataTrain-good/test-bad
UnderfittingModel too simple to learn the patternTrain-bad/test-bad
RegularizationTechnique to reduce overfitting (L1, L2)SageMaker Linear Learner
PrecisionCorrect positive predictions / all positive predictionsMinimize false positives
RecallCorrect positive predictions / all actual positivesMinimize false negatives
F1 ScoreHarmonic mean of precision and recallImbalanced classes
ROUGESummarization evaluation metricCompare to references
BLEUTranslation evaluation metricCompare to references
BERTScoreSemantic similarity metric using embeddingsBedrock auto-eval for summarization
Data DriftInput distribution changes over timeModel Monitor detects
Concept DriftInput-output relationship changesModel Monitor detects
BiasSystematic error producing unfair outcomesSageMaker Clarify detects
ExplainabilityUnderstanding why a model made a decisionSageMaker Clarify SHAP values
Data ResidencyData must remain in a specific geographic regionCompliance requirement
PrivateLinkPrivate network connection to AWS servicesBedrock without public internet
Model CardStandardized model documentationGovernance and audit
Prompt InjectionMalicious input overriding system instructionsSecurity risk
Domain 1 · Chapter 1

Foundations of AI, Machine Learning, Deep Learning, and Generative AI

This chapter establishes the vocabulary you will use throughout the exam. It draws the boundaries between four related but distinct fields and shows where AWS services fit.

1.1 The AI Hierarchy

Think of these four terms as nested circles. Artificial intelligence (AI) is the broad goal of making machines perform tasks that normally require human intelligence. Machine learning (ML) is a subset of AI: instead of programming rules by hand, you let the system learn patterns from data. Deep learning is a subset of ML that uses multi-layer neural networks. Generative AI creates new content — text, images, audio, video, or code — rather than only classifying or predicting. Modern GenAI commonly uses deep-learning foundation models, but treat GenAI as a capability rather than a strict extra layer in every AI hierarchy. Agentic AI describes a system pattern in which an application can select actions, use tools, and coordinate steps; it is not simply another model type.

Memory Anchor

AI is the broadest field. ML learns patterns from data; deep learning is ML based on multi-layer neural networks. GenAI is a content-generation capability commonly powered by deep-learning foundation models. Agentic AI describes systems that use models, tools, memory, and workflows to pursue goals.

1.2 Neural Networks and Deep Learning Mechanics

A neural network consists of layers of interconnected nodes. Data enters through the input layer, passes through hidden layers, and exits through the output layer. Each connection has a weight that determines influence. During training, the network adjusts these weights to minimize error.

Input Data → Input Layer → Hidden Layer 1 → Hidden Layer 2 → Output Layer
                    ↓              ↓              ↓
              Weights        Weights        Weights
                    ↑              ↑              ↑
              Backpropagation ← Loss Function ← Prediction vs Actual
    

Figure 1.1 — Basic neural network training loop. Data flows forward; error gradients flow backward to update weights.

1.3 AWS AI Service Taxonomy

Table 1.1 — Managed AI Services vs. ML Platforms
DimensionManaged AI ServicesML Platforms
ExamplesRekognition, Comprehend, Transcribe, Polly, Translate, Personalize, Lex, TextractSageMaker AI, Bedrock, SageMaker JumpStart
ML expertise requiredNoneYes (SageMaker); moderate (Bedrock fine-tuning)
Time to valueMinutesDays to weeks
Best forStandard tasksDomain-specific tasks, proprietary data
Coach's Takeaway

Start with managed AI services. They solve standard problems with zero ML overhead. Move to platforms only when you need custom models or proprietary data.

Domain 1 · Chapter 2

Learning Paradigms and Problem Types

This chapter teaches the three learning paradigms and the problem types they solve. By the end, you will match a scenario to the right approach quickly.

2.1 Supervised Learning

Uses labeled training data — each input is paired with the correct output. The model learns the mapping and applies it to new data.

Memory Anchor

Labeled data + prediction target = supervised learning. Category = classification. Number = regression.

2.2 Unsupervised Learning

Works with unlabeled data. The algorithm discovers structure on its own — groupings, patterns, anomalies.

2.3 Reinforcement Learning

Trains an agent to make decisions by rewarding good actions and penalizing bad ones. The agent learns through trial and error.

2.4 Classification vs. Regression

Table 2.1 — Classification vs. Regression
DimensionClassificationRegression
Output typeCategoryContinuous number
ExampleWill customer churn? (yes/no)How much will customer spend? ($)
Loss functionCross-entropyMSE, MAE
Evaluation metricPrecision, recall, F1, accuracyRMSE, MAE, R²
Domain 1 · Chapter 3

The ML Development Lifecycle and Data

This chapter walks through the ML lifecycle from business goal identification to deployment and monitoring, then dives into data concepts.

3.1 The ML Lifecycle

flowchart LR
    A[Business Goal
Identification] --> B[ML Problem
Framing] B --> C[Data Processing] C --> D[Model Development] D --> E[Evaluation] E --> F[Deployment] F --> G[Monitoring] G --> A style A fill:#0b2545,color:#fff style B fill:#13315c,color:#fff style C fill:#1d4e89,color:#fff style D fill:#2d6a9f,color:#fff style E fill:#4a8db7,color:#fff style F fill:#4a8db7,color:#fff style G fill:#4a8db7,color:#fff

Figure 3.1 — ML lifecycle. Business goal identification comes first. Compliance and regulatory requirements are established before data collection.

Key Concept

Business goal first, always. Compliance, regulatory requirements, and success metrics are defined before any technical work begins.

3.2 Data Types

Table 3.1 — Data Types and ML Approaches
Data TypeExampleML ApproachAWS Service
Structured (tabular)Customer records, sales transactionsClassical MLSageMaker AI, Personalize
Unstructured (text)Reviews, emails, documentsNLP, LLMsComprehend, Bedrock, Textract
Unstructured (image/video)Photos, surveillanceComputer visionRekognition, SageMaker AI
Unstructured (audio)Voice recordingsSpeech recognitionTranscribe
Time-seriesStock prices, sensor dataForecastingSageMaker AI (DeepAR)
Domain 1 · Chapter 4

Model Evaluation and Metrics

This chapter teaches the metrics used to evaluate classification, regression, and generative AI models, plus overfitting, underfitting, bias, and drift.

4.1 Classification Metrics

Table 4.1 — Classification Metrics
MetricFormulaMeasuresWhen to Use
Accuracy(TP+TN) / TotalOverall correctnessBalanced classes
PrecisionTP / (TP+FP)Correctness of positive predictionsMinimize false positives
RecallTP / (TP+FN)Coverage of actual positivesMinimize false negatives
F1 Score2 × (P × R) / (P + R)Balance of precision and recallImbalanced classes
Exam Trap

Accuracy is misleading on imbalanced data. If 95% of transactions are legitimate, a model predicting "legitimate" every time achieves 95% accuracy but catches zero fraud. Use F1 score instead.

4.2 Generative AI Evaluation Metrics

Table 4.2 — Text Generation Metrics
MetricPurposeWhen to Use
ROUGESummarization quality (recall-oriented)Comparing summaries to references
BLEUTranslation quality (precision-oriented)Comparing translations to references
BERTScoreSemantic similarity via embeddingsBedrock automatic evaluation for summarization
Important Nuance

Amazon Bedrock's automatic evaluation feature for text summarization reports BERTScore using the Gigaword dataset. The academic default for summarization is ROUGE. Both are correct in their contexts. If the question specifies Bedrock's automatic evaluation, choose BERTScore.

4.3 Overfitting and Underfitting

Table 4.3 — Overfitting vs. Underfitting
SignatureDiagnosisRemedy
Train-good, test-badOverfittingIncrease regularization, reduce complexity, more data
Train-bad, test-badUnderfittingIncrease complexity, add features, reduce regularization
Domain 1 · Chapter 5

AWS AI/ML Services Landscape

This chapter organizes AWS AI/ML services by the problem they solve — managed AI services, SageMaker AI, Bedrock, and generative AI developer tools.

5.1 Managed AI Services

Table 5.1 — Managed AI Services by Problem
ServiceProblem SolvedWhen to UseAlternative
Amazon RekognitionImage and video analysisObject detection, facial analysis, moderationSageMaker AI
Amazon ComprehendText analysisSentiment, entities, toxicitySageMaker AI, Bedrock
Amazon TranscribeSpeech to textSubtitles, call transcriptionNone
Amazon PollyText to speechVoice-overs, accessibilityNone
Amazon TranslateLanguage translationMultilingual contentNone
Amazon TextractDocument extractionOCR, forms, tablesBedrock Data Automation
Amazon LexConversational interfacesBuild chatbots and voice assistantsAmazon Bedrock
Amazon PersonalizeRecommendationsProduct/content recommendationsSageMaker AI
Amazon SageMaker AICustom fraud classificationBuild a model for organization-specific fraud patternsManaged AI services

5.2 Amazon SageMaker AI Feature Map

Table 5.2 — SageMaker AI Features by Task
FeaturePurpose
SageMaker StudioIntegrated development environment
SageMaker AutopilotAutomated model building and tuning
SageMaker JumpStartPre-trained models and solution templates
SageMaker Data WranglerVisual data preparation
SageMaker ClarifyBias detection and explainability
SageMaker Model MonitorProduction drift detection
SageMaker Model RegistryModel versioning and approval
SageMaker Model CardsStandardized model documentation
SageMaker Ground TruthData labeling with human review
SageMaker CanvasNo-code ML for business analysts
SageMaker Feature StoreCentralized feature repository
SageMaker PipelinesML workflow orchestration
SageMaker Serverless InferenceModel deployment without managing infrastructure
SageMaker Batch TransformOffline inference for large datasets

5.3 Amazon Bedrock Feature Map

Table 5.3 — Bedrock Features by Task
FeaturePurpose
Model accessBrowse and invoke FMs from multiple providers
Knowledge BasesManaged RAG — connect data and retrieve context
AgentsOrchestrate multi-step tasks with API calls
GuardrailsContent filters, denied topics, PII detection, grounding
Prompt ManagementStore, version, and reuse prompts
Model EvaluationAutomatic and human evaluation of outputs
Provisioned ThroughputDedicated capacity for steady traffic
Batch InferenceBulk generation at discounted rates
Prompt CachingReuse prompt prefixes to reduce latency and cost
Prompt RouterDynamically select the best model per request
Coach's Takeaway

Match the requirement to the service class: managed AI service for standard tasks, SageMaker AI for custom models, Bedrock for foundation models. When in doubt, start managed.

Domain 1 — v1.2 Focus: Inference, MLOps, and Business Outcomes

Choose the inference pattern from the workload. Batch inference processes collections of inputs together; real-time inference returns a response during a request; asynchronous inference accepts a request and returns its result later; serverless inference reduces the need to manage inference infrastructure.

Inference decision guide
RequirementBest fit
Score thousands of records overnightBatch inference
Return a prediction inside a live user requestReal-time inference
Accept a large job and retrieve its result laterAsynchronous inference
Run inference without managing serversServerless inference

MLOps covers repeatable experimentation, deployment, monitoring, and retraining practices. Connect technical metrics (accuracy, precision, recall, F1) to business measures such as cost per user, customer feedback, development cost, and ROI. A model with strong F1 can still fail the business case if operating cost is too high.

Exam distinction

Use a traditional ML model when a structured prediction, lower cost, or more explainable result is the better fit. Do not choose a foundation model simply because it is newer.

When AI/ML Is Not the Right Choice

AI is useful when prediction, classification, recommendation, perception, or language capabilities add measurable value. It is not automatically the best solution for every business problem.

Decision guide — AI/ML suitability
SituationBetter choiceWhy
A fixed, deterministic rule solves the taskOrdinary software or business rulesEasier to test, explain, and maintain
A guaranteed outcome is requiredDeterministic logic with validationML produces probabilistic predictions, not guarantees
Representative data is insufficientImprove data or use a simpler approachWeak or biased data makes predictions unreliable
Error cost exceeds expected benefitRetain human decisions or do not automateCompare model, infrastructure, monitoring, and review costs with measurable benefit
Structured historical data supports a clear predictionConsider traditional MLClassification or regression may be cheaper and more explainable than an FM
Exam Trap

Do not choose AI because it is fashionable. If a deterministic rule solves the problem reliably, or the cost-benefit case is weak, a non-AI solution may be the better answer.

Domain 2 · Chapter 6

Generative AI and Foundation Models

This chapter introduces generative AI fundamentals: foundation models, large language models, and the architecture that powers them.

6.1 What Makes Generative AI Different

Traditional ML predicts a label or value. Generative AI creates new content — text, images, audio, video, code. The distinction matters because the exam tests whether you recognize when a scenario calls for generation versus prediction.

Memory Anchor

Predict a category → classification. Predict a number → regression. Create new content → generative AI.

6.2 Foundation Models and LLMs

A foundation model is a large pre-trained model adaptable to many downstream tasks. A large language model is a foundation model specialized for text. Transformers — the architecture behind modern LLMs — use self-attention to capture contextual relationships across all tokens simultaneously.

flowchart TD
    A[Foundation Model] --> B[Text: LLM]
    A --> C[Image: Diffusion]
    A --> D[Multimodal]
    B --> E[Chatbot]
    B --> F[Summarization]
    B --> G[Code Generation]
    C --> H[Image Generation]
    C --> I[Image Editing]
    D --> J[Text + Image Understanding]
    D --> K[Video Generation]
    style A fill:#0b2545,color:#fff
    style B fill:#1d4e89,color:#fff
    style C fill:#1d4e89,color:#fff
    style D fill:#1d4e89,color:#fff
    

Figure 6.1 — Foundation model taxonomy. Foundation models specialize by modality (text, image, multimodal) and application (chat, summarize, generate).

6.3 Model Selection Considerations

Table 6.1 — Model Selection Factors
FactorWhat It MeansExam Trigger
ModalityInput/output types supported"Text and image inputs" → multimodal
LatencyResponse time"Real-time" → prioritize low latency
Context windowMaximum input size in tokens"Long documents fail" → context limit
CostPer-token pricing"Minimize cost" → smaller model
CustomizationFine-tuning support"Domain-specific" → fine-tuning
Coach's Takeaway

Select the smallest model that satisfies the performance requirement. Larger models cost more without adding value when a smaller model already meets the task.

Domain 2 · Chapter 7

LLM Mechanics: Tokens, Embeddings, Context Windows, and Inference Controls

This chapter explains how LLMs process text and how inference parameters control output.

7.1 Tokens and Tokenization

Tokenization splits text into smaller units — words, subwords, or characters — that the model processes numerically. These tokens are the building blocks for all NLP tasks.

7.2 Embeddings

Embeddings map text into a high-dimensional vector space where proximity reflects semantic similarity. That enables mathematical comparison — cosine similarity, nearest-neighbor search — for semantic search, clustering, and retrieval.

Exam Trap

Embeddings are not generated text. Embeddings are numeric vectors for comparison. Generated text is the model's output. A text embeddings model converts text to vectors; a text generation model produces new text.

7.3 Context Windows

Language models have a maximum context window measured in tokens. If input exceeds that limit, the model cannot process the full input — leading to errors, truncation, or failure.

7.4 Inference Parameters

Table 7.1 — Inference Parameters
ParameterEffectUse When
TemperatureControls sampling variability; lower values make outputs more focused, higher values allow more variationLower for consistency, higher for creative diversity
Top KLimits next-token candidates to K most probableBalance diversity and focus
Top PNucleus sampling — cumulative probability cutoffAlternative to Top K
Max tokensMaximum output lengthControl response size
Stop sequencesTokens that end generationPrevent runaway output
Key Distinction

Lower temperature generally makes sampling more focused; higher temperature generally increases variation. A temperature of 0 does not guarantee identical outputs in every system or context, and low temperature does not guarantee factual accuracy. Use grounding, evaluation, and validation to address hallucinations.

Domain 2 · Chapter 8

Prompt Engineering Techniques

This chapter teaches the prompting techniques the exam tests: zero-shot, few-shot, chain-of-thought, and their applications.

8.1 Prompt Engineering Fundamentals

A prompt is the input instruction you give the model. Prompt engineering is the practice of designing prompts that produce accurate, relevant, and well-formatted responses.

8.2 Prompting Techniques

Table 8.1 — Prompt Engineering Techniques
TechniqueWhat It DoesWhen to UseExample Trigger
Zero-shotNo examples; task onlySimple, well-defined tasks"Classify the following text…"
Few-shotA few labeled examples before taskFormat or style must be matchedThree examples, then "Now classify this"
Single-shotOne worked example before the taskOne example clarifies the expected patternShow one input/output pair, then ask for the next
Negative promptStates content, style, or elements to avoidGeneration needs explicit exclusions"Do not include text, logos, or extra objects"
Iterative refinementUses follow-up feedback or comments to improve an earlier responseThe first output needs correction or more detailReview, give targeted feedback, and regenerate
Chain-of-thoughtInstructs step-by-step reasoningComplex multi-step problems"Think step by step"
ReActReasoning + external tool/API callsNeed live data or actions"Check inventory and respond"
Prompt chainingOutput of one prompt feeds nextMulti-stage complex tasksSequential subtask execution
Memory Anchor

No examples → zero-shot. Few examples → few-shot. Step-by-step → chain-of-thought. Reason + act → ReAct. Chained prompts → prompt chaining.

8.3 Prompt Injection and Security

Prompt injection is an attempt to make a model ignore its intended instructions or misuse the context and tools available to it. It can arrive directly from a user or indirectly through retrieved documents, web pages, and other untrusted content. Retrieved text should be treated as data, not as trusted instructions.

Table 8.2 — Prompt Engineering Risks
RiskMeaningExample / Response
ExposureSensitive prompts, system instructions, or confidential context are revealedMinimize secrets in model context; restrict access and redact sensitive data
Prompt poisoningMalicious or misleading content is inserted into prompt inputs or retrieved sourcesValidate and curate data sources; treat retrieved content as untrusted
Prompt hijacking / injectionAttacker-supplied instructions attempt to override the intended task or system rulesSeparate trusted instructions from data; apply input screening and tool authorization
JailbreakingPrompts attempt to bypass safety restrictions or policy controlsUse safety testing, guardrails, monitoring, and human escalation for sensitive actions
Security Design Rule

Guardrails are one layer, not a complete security boundary. Combine them with least-privilege IAM, restricted tool permissions, validation of external content, output checks, logging, and human approval for consequential actions.

8.4 Prompt Management and Versioning

Prompts are application assets. When teams change an instruction, template, example, or model setting, they should be able to identify exactly which version produced a response and compare the effect of the change.

  1. Use a reusable template: separate stable instructions from variables such as customer question, retrieved context, or product details.
  2. Store versions: label meaningful prompt revisions and preserve the previous working version.
  3. Record the configuration: track the model, prompt version, inference parameters, and relevant evaluation dataset together.
  4. Test before promotion: run representative examples, adversarial inputs, and regression tests against the same evaluation criteria.
  5. Promote and monitor: release the approved version, monitor quality and cost, and roll back if results deteriorate.
AWS Service Association

Amazon Bedrock Prompt Management helps create, store, version, and manage reusable prompts. For exam scenarios that mention centralized prompt templates, prompt versions, or controlled prompt iteration on AWS, recognize Prompt Management.

Exam Trap

Prompt versioning is not model fine-tuning. Versioning changes and tracks instructions or templates; fine-tuning changes model weights using training data. If a team only needs to improve instructions and compare revisions, start with prompt engineering and management.

Domain 2 · Chapter 9

Hallucinations, Grounding, and RAG Fundamentals

This chapter teaches why LLMs hallucinate, how RAG grounds responses in external data, and how to evaluate RAG systems.

9.1 Hallucinations

A hallucination is plausible-sounding but factually incorrect content. It is the primary production risk for generative AI in customer-facing and regulated contexts.

9.2 Retrieval Augmented Generation (RAG)

RAG retrieves relevant information from an external knowledge base at inference time and feeds it to the model as context. The model stays fixed; retrieved context changes. That grounds responses in verifiable sources and reduces hallucinations.

flowchart LR
    A[User Query] --> B[Query Embedding]
    B --> C[Vector Search]
    C --> D[Retrieve Relevant Chunks]
    D --> E[Augment Prompt with Context]
    E --> F[LLM Generates Grounded Response]
    F --> G[Response with Source Citations]
    style A fill:#0b2545,color:#fff
    style F fill:#1d4e89,color:#fff
    style G fill:#2d6a9f,color:#fff
    

Figure 9.1 — RAG workflow. The query is embedded, relevant chunks are retrieved, and the LLM generates a response grounded in those chunks.

9.3 RAG Pipeline: Online vs. Offline

Table 9.1 — RAG Pipeline Stages
StageWhen It RunsLatency Requirement
Parse documentsOffline (batch)None
Chunk documentsOffline (batch)None
Generate content embeddingsOffline (batch)None
Build search indexOffline (batch)None
Generate query embeddingsOnline (query time)Low
Retrieve relevant contentOnline (query time)Low
Generate responseOnline (query time)Low
Coach's Takeaway

RAG's core value is reducing hallucinations through grounding. It does not speed up training or inference. Update the knowledge base, not the model.

Domain 2 — v1.2 Focus: Context Engineering, Agents, and Cost

Context engineering designs all information supplied to a foundation model at inference time: instructions, user input, retrieved documents, conversation history, tool descriptions, and constraints. Prompt engineering focuses on wording; context engineering manages the wider information environment.

Agentic AI concepts to recognize
ConceptExam clue
Tool useAgent invokes an external function, API, or service
MemoryRelevant state is retained across steps or interactions
Multi-agent patternSpecialist agents delegate, collaborate, and exchange results
Workflow orchestrationCoordinates sequence, handoffs, and completion
Model Context Protocol (MCP)Standardized connection to external tools and data

Token economics: input and output tokens contribute to inference cost. Longer context, larger prompts, and verbose responses can increase cost and may add latency. Compare model capability, token price, throughput, and response-time requirements together.

AWS infrastructure and tool selection: use Amazon Bedrock for managed access to foundation models and application features; use SageMaker AI when broader control is needed to build, train, customize, or host models. SageMaker JumpStart helps discover and deploy pretrained models. Amazon Quick is an in-scope analytics/work-assistance offering, while Kiro and Strands Agents are developer and agent-building technologies; do not confuse them with model-training platforms. Bedrock AgentCore supports building and operating agents. Architecture choices should weigh managed API access against self-hosting, on-demand against provisioned capacity, token cost against throughput, and latency against redundancy and regional availability. Custom models can improve fit but add training, hosting, governance, and operational costs.

Exam distinction

An agent is not simply a chatbot that writes a longer answer. Agentic behavior includes selecting tools or actions and coordinating steps within permission boundaries.

Domain 3 · Chapter 10

Amazon Bedrock: The Managed FM Platform

This chapter covers Amazon Bedrock's capabilities: model access, Knowledge Bases, Agents, Guardrails, and pricing models.

10.1 Bedrock Overview

Amazon Bedrock is a fully managed service that provides access to high-performing foundation models from multiple providers through a single API. You do not manage infrastructure, and you pay for what you use.

10.2 Bedrock Capabilities

Table 10.1 — Bedrock Capabilities
CapabilityPurposeWhen to Use
Knowledge BasesManaged RAGGround responses in company data
AgentsMulti-step task orchestrationAPI calls, tool use, transactions
GuardrailsSafety controlsBlock harmful content, PII, denied topics
Prompt ManagementStore and reuse promptsStandardize prompt templates
Model EvaluationAssess model qualityCompare models, measure accuracy
Prompt CachingReuse prompt prefixesReduce latency and cost
Prompt RouterDynamic model selectionSingle endpoint, best model per request

10.3 Pricing Models

Table 10.2 — Bedrock Pricing Models
ModelBest ForWhen to Choose
On-DemandUnpredictable or low usagePilot phase, variable traffic
Provisioned ThroughputSteady, high-volume trafficPredictable usage, custom models
BatchPeriodic bulk generationWeekly reports, catalog updates
Coach's Takeaway

Steady, predictable traffic → Provisioned Throughput. Unpredictable or low usage → On-Demand. Periodic bulk → Batch.

Domain 3 · Chapter 11

Amazon SageMaker AI and Custom Model Development

This chapter covers SageMaker AI's platform capabilities: Autopilot, JumpStart, Clarify, Model Monitor, Ground Truth, and deployment options.

11.1 SageMaker AI Overview

SageMaker AI is AWS's end-to-end platform for building, training, and deploying custom ML models. It provides infrastructure, tools, and workflows for every stage of the ML lifecycle.

11.2 Key SageMaker Features

Table 11.1 — SageMaker AI Features by Lifecycle Stage
Lifecycle StageFeaturePurpose
Data preparationData WranglerVisual, low-code data preparation
Data labelingGround TruthHuman review and labeling
Model buildingAutopilotAutomated model building and tuning
Model buildingCanvasNo-code ML for business analysts
Model buildingJumpStartPre-trained models and templates
TrainingSageMaker TrainingManaged training jobs
Bias/explainabilityClarifyBias detection and SHAP explanations
GovernanceModel CardsStandardized model documentation
GovernanceModel RegistryVersioning and approval workflows
DeploymentEndpointsReal-time inference
DeploymentServerless InferenceNo infrastructure management
DeploymentBatch TransformOffline inference for large datasets
MonitoringModel MonitorDrift detection
Exam Trap

Model Monitor vs. Clarify. Model Monitor detects production drift. Clarify detects bias and explains predictions. Both are governance features, but they solve different problems.

Domain 3 · Chapter 12

Customization Strategy: Prompt Engineering vs. RAG vs. Fine-Tuning vs. Continued Pre-Training

This chapter teaches the decision framework for customizing foundation models.

12.1 The Customization Decision

Table 12.1 — Customization Approaches
ApproachData RequiredEffortWhen to Use
Prompt engineeringNoneLowestStyle, format, simple task adaptation
RAGDocuments (unlabeled)ModerateFrequently changing data, grounded answers
Fine-tuningLabeled input-output pairsHighTask-specific behavior, style adaptation
Continued pre-trainingUnlabeled domain textHighestDomain knowledge expansion
Memory Anchor

Least to most effort: prompt → RAG → fine-tune → continued pre-training. Prompt engineering first. RAG for changing data. Fine-tuning for task behavior. Pre-training for domain knowledge.

12.2 Training and Fine-Tuning: What Happens to the Data?

For the exam, distinguish the purpose of each training stage and the kind of data it uses. You are expected to recognize the approach—not implement a training pipeline.

Table 12.2 — Training Stages and Fine-Tuning Methods
MethodWhat Changes?Typical DataExam Clue
Pre-trainingBuilds broad language or multimodal capabilities from large datasetsLarge-scale, often unlabeled dataCreating a foundation model from the beginning
Continued pre-trainingExtends a pretrained model's knowledge in a domainAdditional domain-specific, usually unlabeled dataSpecialized vocabulary or domain knowledge
Instruction fine-tuningImproves following instructions and producing desired responsesInstruction-and-response examplesConsistent task behavior or response format
Transfer learningAdapts knowledge learned on one task or dataset to anotherTask- or domain-specific examplesReuse a pretrained model rather than start from zero
Model distillationTransfers useful behavior from a larger teacher model to a smaller student modelTeacher outputs and/or curated training examplesLower inference cost or latency with a smaller model
RLHFUses human preferences to guide model behaviorHuman rankings or preference comparisonsPeople compare responses and indicate which is better

Fine-Tuning Data Preparation

  1. Define target behavior: specify the task, audience, expected output, and success criteria.
  2. Curate representative examples: cover normal cases, edge cases, and the real distribution of expected inputs.
  3. Check quality and labels: remove duplicates, correct errors, standardize formats, and verify labels.
  4. Apply governance: confirm rights to use the data, minimize sensitive information, and apply access controls.
  5. Separate evaluation data: keep a held-out set not used for training, so evaluation measures generalization.
Exam Trap

More training is not always the answer. If facts change frequently, RAG is often more practical than fine-tuning. If the goal is consistent output behavior, instruction fine-tuning may fit. If the goal is lower serving cost, consider distillation. Choose by the stated business need.

Scenario Check

A company needs an assistant to use a frequently updated internal policy library but does not need to change the model's writing style. Best fit: RAG, because the knowledge changes independently of model weights.

Domain 3 · Chapter 13

Agents, Guardrails, and Model Evaluation on Bedrock

This chapter covers Bedrock Agents, Guardrails, and model evaluation capabilities.

13.1 Bedrock Agents

Amazon Bedrock Agents orchestrate multi-step tasks: interpreting user input, calling external APIs, and producing outputs. They are the right choice when the application needs to reason and act.

RAG and AI Agents — Different Jobs, Often Used Together
PatternMain jobExampleWhat it does not do by itself
RAGFind relevant information and provide it as evidence for a generated answerAnswer a policy question using the latest approved policy documentsIt does not normally approve requests, update records, or execute a business process
AI agentCoordinate steps, select tools, and take permitted actions toward a goalCheck an order, verify eligibility, create a support ticket, and report the resultIt does not automatically have reliable, current knowledge unless connected to trusted data sources
RAG + agentGround decisions in retrieved information, then orchestrate authorized actionsRetrieve the current refund policy, check the order, and submit an eligible refund request for approvalRequires access controls, action validation, monitoring, and human approval where appropriate
Decision Anchor

Need to answer from changing documents? Use RAG. Need to perform a multi-step task with tools? Use an agent. Need both grounded information and actions? Combine RAG with an agent, while enforcing permissions outside the model.

13.2 Bedrock Guardrails

Table 13.1 — Bedrock Guardrails Policies
PolicyWhat It DoesWhen to Use
Content filtersBlock harmful categories (hate, violence, sexual, insults)General safety
Denied topicsBlock custom subject areasPolitics, competitor products, legal advice
Word filtersBlock specific words or phrasesProfanity, brand names
Sensitive information filtersBlock or mask PIICustomer data protection
Contextual grounding checkVerify responses are supported by source contextReduce hallucinations
Prompt attacksDetect jailbreak attemptsPublic-facing chatbots
Exam Trap

Content filters vs. denied topics. Content filters handle predefined harmful categories (hate, violence). Denied topics handle custom subject areas you define (politics, competitor products).

13.3 Bedrock Model Evaluation

Table 13.2 — Bedrock Evaluation Metrics
MetricWhat It MeasuresTask Type
BERTScoreSemantic similarity to referenceSummarization (automatic)
ROUGEN-gram overlap with referenceSummarization (academic)
BLEUTranslation qualityTranslation
FaithfulnessResponse grounded in retrieved contextRAG
CompletenessAll parts of prompt addressedAgent responses
CorrectnessFactual accuracyGeneral
HarmfulnessToxic content detectionSafety
RefusalModel declines to answerGuardrail testing

13.4 Choosing the Right Evaluation Method

No single metric proves that a foundation model is good. Match the evaluation method to the task, compare outputs against a suitable reference or rubric, and use human review when quality requires judgment.

Table 13.3 — Evaluation Methods and Metrics
Method / MetricWhat It Helps AssessUseful WhenImportant Limitation
Benchmark datasetPerformance on repeatable representative tasksComparing models or versionsMay not represent real users or production data
Human evaluationUsefulness, correctness, tone, relevance, nuanced qualitySubjective or high-impact tasksNeeds a clear rubric and reviewer consistency
ROUGEWord or sequence overlap with reference textSummarization comparisonsOverlap does not prove factual correctness
BLEUn-gram precision against reference translationsMachine translation evaluationMay miss meaning and valid alternative wording
BERTScoreSemantic similarity using contextual token representationsText generation where meaning matters beyond exact wordingSimilarity is not proof that claims are true
LLM-as-a-judgeScores or compares responses against a rubricScaling structured evaluationJudge bias requires calibration and human spot checks

13.5 Evaluate the Application, Not Only the Model

A model can produce fluent text while the complete application still fails. Evaluate the end-to-end system using measures that match its architecture.

Table 13.4 — Application-Level Evaluation
ApplicationWhat to TestUseful Measures
RAG applicationWhether retrieval finds the right passages and the answer is supported by themRetrieval relevance/recall, faithfulness, answer relevance, citation correctness
AI agentWhether it chooses the right tool, follows required steps, and completes the task safelyTask success, tool-call accuracy, completion rate, policy violations
WorkflowWhether handoffs, steps, and final outputs work reliably end to endEnd-to-end success rate, error rate, latency, escalation rate
Coach's Note — RAG Evaluation

Check two stages. Retrieval: did the system find the right evidence? Generation: did the model answer accurately using that evidence? Relevant retrieval does not guarantee a faithful answer.

13.6 Connect AI Performance to Business Objectives

Technical quality matters when it improves the intended user or business outcome. Choose the metric that measures the outcome named in the scenario.

Table 13.5 — Business Alignment Metrics
MetricMeaningExample
Task completion ratePercentage of user tasks completed successfullySupport requests resolved without handoff
User satisfactionUser-reported experience or satisfactionPost-interaction survey score
Cost per interactionAverage cost to serve one interactionModel, retrieval, and infrastructure cost per request
ProductivityTime or effort saved on a processAverage handling time before and after deployment
EngagementWhether users meaningfully use the applicationRepeat usage or successful feature adoption
Exam Trap

Do not confuse model quality with business success. BLEU or ROUGE may compare generated text, but neither tells a business whether users completed tasks or whether interactions were cost-effective.

13.7 Applied Decision Examples

Practical patterns for selecting evaluation and customization approaches
Application situationAppropriate approachReasoning and limitation
Comparing summaries against human-written reference summariesROUGEMeasures overlap with reference text; it does not independently establish factual accuracy
Knowledge assistant produces fluent but unsupported answersEvaluate retrieval relevance and answer faithfulnessCheck both the evidence retrieved and whether generated claims are supported by that evidence
Customer-service agent must resolve requests successfullyTask completion rateMeasure completed user goals; pair with cost per interaction and user satisfaction
Large model is too expensive for a narrower, repeatable taskModel distillationA smaller student model can approximate useful behavior from a larger teacher; validate quality and safety after distillation

Domain 3 — v1.2 Focus: Application Design and Evaluation

For vector storage questions, identify the data model and surrounding application requirement. The exam expects recognition of common AWS options, not database administration.

Vector storage selection cues
ServiceScenario clue
Amazon OpenSearch ServiceSearch workloads combined with vector similarity retrieval
Amazon AuroraRelational application data with vector retrieval
Amazon NeptuneKnowledge graphs and relationship-rich data
Amazon RDS for PostgreSQLPostgreSQL application with vector extensions

Evaluate the whole application, not only the foundation model. For RAG, check retrieval relevance, answer faithfulness to retrieved evidence, and citation correctness. For agents, check tool-call accuracy, task completion, policy violations, and safe escalation. For workflows, check end-to-end completion, latency, and failure rates.

Business alignment metrics include task completion rate, user satisfaction, and cost per interaction. ROUGE, BLEU, and BERTScore assess aspects of generated text; human evaluation and benchmark datasets provide complementary evidence. No single metric proves business success.

Domain 4 · Chapter 14

Responsible AI: Fairness, Bias, and Inclusivity

This chapter covers the responsible AI dimensions the exam tests: fairness, bias, inclusivity, and mitigation strategies.

14.1 Responsible AI Dimensions

Table 14.1 — Responsible AI Dimensions
DimensionDefinitionExam Trigger
FairnessEquitable outcomes across demographic groupsDiverse data, protected groups
ExplainabilityUnderstanding why a model made a decisionRationale, SHAP, feature importance
TransparencyVisibility into how AI systems make decisionsModel Cards, documentation
Privacy and SecurityData protection and access controlEncryption, IAM, PII
SafetyPreventing harmful output and misuseGuardrails, content filters
RobustnessResilience to unexpected inputsAdversarial testing
ControllabilityHuman oversight and interventionHuman-in-the-loop review workflows

14.2 Bias Detection and Mitigation

Bias enters through unrepresentative training data, historical bias in labels, proxy features, or sample selection. SageMaker Clarify computes pre-training and post-training bias metrics and generates reports on feature importance.

Coach's Takeaway

Bias from training data → fix the data. Bias from model design → use fairness-aware techniques. Diverse, balanced data is the foundation of fair AI.

14.3 Dataset Quality, Robustness, and Veracity

Responsible AI begins before model training. Review whether the dataset represents the people and situations affected by the system, whether labels are reliable, and whether important groups are missing or underrepresented.

Table 14.2 — Data and Responsible AI Checks
CheckWhat to ExamineWhy It Matters
Diversity and inclusivityCoverage across relevant demographic groups, languages, locations, and use casesReduces the risk that some groups are poorly represented
BalanceWhether classes or outcomes are disproportionately representedSkewed data can distort model behavior and evaluation
Label qualityAccuracy, consistency, and agreement of labelsIncorrect labels can teach the model incorrect patterns
Curated sourcesOrigin, permission, relevance, and quality of collected dataSupports reliability, traceability, and responsible use
RobustnessPerformance on unusual, noisy, shifted, or adversarial inputsHelps the system behave reliably outside ideal test cases
VeracityWhether generated statements are accurate and supported by evidenceReduces misleading or fabricated outputs

Bias and Variance: Recognize the Symptoms

  • High bias / underfitting: the model is too simple or constrained to learn important patterns; it performs poorly on both training and unseen data.
  • High variance / overfitting: the model fits training examples too closely and performs worse on new data.
  • Demographic performance gaps: overall accuracy can hide poor results for a subgroup. Compare relevant metrics across groups rather than relying only on an aggregate score.
Monitoring Pattern

Use label-quality reviews, human audits, subgroup analysis, and ongoing monitoring. Amazon SageMaker Clarify can help examine bias and explainability; SageMaker Model Monitor can help detect data and model-quality changes over time. Select the tool based on the issue being investigated.

14.4 Legal, Trust, and Sustainability Risks

  • Intellectual property: generated content may create infringement or licensing concerns; review data rights and intended use.
  • Biased outputs: unfair recommendations can harm affected users and damage trust.
  • Hallucinations: unsupported statements can create user, financial, legal, or safety risks.
  • Loss of customer trust: opaque or harmful behavior can damage confidence in the organization.
  • Environmental impact: consider energy use, model size, compute demand, and whether a smaller or more efficient model can meet the requirement.
Exam Trap

A model with the highest benchmark score is not automatically the most responsible choice. Consider fairness, robustness, safety, licensing, user impact, and environmental cost alongside performance.

Domain 4 · Chapter 15

Explainability, Transparency, and Human Oversight

This chapter covers explainability techniques, transparency documentation, and human-in-the-loop workflows.

15.1 Explainability Techniques

SHAP values show how much each feature contributed to a prediction. Feature importance ranks inputs by influence. Counterfactuals show what would need to change for a different outcome. SageMaker Clarify provides these capabilities.

15.2 Transparency Documentation

Table 15.1 — Transparency Documentation Tools
ToolWhat It DocumentsWhen to Use
SageMaker Model CardsPurpose, performance, limitations, risksCustom model governance
AWS AI Service CardsAWS service capabilities and limitationsUnderstanding managed services
SageMaker Model RegistryVersion tracking and approval statusModel lifecycle management

15.3 Human Oversight

Human-in-the-loop (HITL) workflows route low-confidence or flagged predictions to human reviewers. The exam focus is the purpose of human review, the escalation trigger, and how feedback improves oversight—not implementation of a specific A2I service.

Key Concept

High-stakes decisions about people (hiring, lending, healthcare) require appropriate human review, clear escalation paths, and documented accountability.

15.4 Transparency vs. Explainability

These ideas are related but not identical. Transparency makes relevant information about a model and its use available—for example, its purpose, training-data characteristics, intended use, limitations, and evaluation results. Explainability helps a person understand why a particular output or prediction occurred.

Table 15.2 — Transparency and Explainability Compared
QuestionTransparencyExplainability
What is disclosed?Model purpose, data, limits, intended use, documentationFactors or evidence behind a specific output
Typical artifactModel Card, service documentation, licensing informationFeature attribution, explanation, counterfactual
Who benefits?Users, reviewers, auditors, developers, decision-makersPeople affected by or reviewing a decision
Key limitationDisclosure alone does not make a model understandableAn explanation may be approximate and does not prove the model is correct

15.5 Model Evaluation and Open-Source Considerations

Amazon Bedrock Model Evaluations can help assess foundation-model performance using supported evaluation approaches and metrics. When comparing open-weight or open-source models, review more than model availability: check the license, permitted uses, training-data information where available, evaluation evidence, known limitations, and the organization's ability to operate and secure the model.

Safety and Transparency Trade-Off

More disclosure can help users and reviewers understand a system, but exposing sensitive implementation details, personal data, or abuse-enabling information can create risk. Aim for meaningful, audience-appropriate transparency while protecting security and privacy. Do not assume that maximum disclosure is always safest.

15.6 Human-Centered Explanations and Feedback

  1. Tell users when AI is being used and what role it plays in the decision.
  2. Explain important outcomes in language appropriate to the audience.
  3. Provide a way to ask questions, correct information, or challenge an outcome.
  4. Route uncertain, harmful, or high-impact cases to qualified human review.
  5. Use feedback and review findings to improve the system and its documentation.
Exam Trap

A Model Card improves transparency; it does not automatically explain an individual prediction. SHAP or feature attribution can help explain a prediction; it does not replace documentation, fairness testing, or human accountability.

15.7 Transparency, Interpretability, and Safety Trade-offs

Transparency and explainability improve trust and review, but disclosure must be balanced with security, privacy, intellectual-property protection, and misuse risk. A highly interpretable model may be less capable for a particular task; a more capable complex model may require stronger documentation, evaluation, monitoring, and human oversight. Select the level of explanation that fits the decision’s impact and the audience.

Choosing an appropriate explanation approach
SituationUseful approachImportant limitation
Need to document intended use and known limitsModel Card and service documentationDoes not explain every individual prediction
Need to understand feature contributionFeature importance or SHAP-style attributionAttributions can be approximate and do not prove causation
Need to explain a high-impact outcome to a personAudience-appropriate explanation plus human review and appeal pathMust preserve privacy and avoid overstating certainty

Domain 4 — v1.2 Focus: Responsible Selection and Human-Centred Explanations

Responsible model selection is a multi-factor decision. Consider fairness across relevant groups, robustness to unusual inputs, safety, veracity, licensing and intellectual-property risks, user impact, and environmental cost. A larger or more accurate model is not automatically the most responsible choice.

Transparency helps users understand what a system is intended to do, its limitations, and how it was evaluated. Explainability helps make a particular output or decision understandable. Model Cards can document intended use, evaluation, limitations, and risks; user-feedback mechanisms and clear explanations support human-centred design.

Exam decision rule

When overall performance hides unequal outcomes, examine subgroup results and label quality. When users need to understand a decision, prioritize appropriate explanations and transparent documentation.

Domain 5 · Chapter 16

Securing AI Workloads: IAM, Encryption, and Private Connectivity

This chapter covers IAM, KMS, PrivateLink, and the shared responsibility model for AI services.

16.1 Access Control with IAM

AWS Identity and Access Management (IAM) controls who can access which AWS resources. IAM policies can restrict access to specific Bedrock models, SageMaker endpoints, or datasets.

16.2 Encryption with KMS

AWS Key Management Service (KMS) manages encryption keys. For Bedrock, you can use customer-managed keys to encrypt custom model artifacts. The API parameter is modelKmsKeyArn.

16.3 Private Connectivity with PrivateLink

AWS PrivateLink creates a private connection between your VPC and Amazon Bedrock. Traffic stays on the AWS private network and never traverses the public internet.

flowchart LR
    A[VPC] --> B[VPC Endpoint]
    B --> C[AWS PrivateLink]
    C --> D[Amazon Bedrock]
    A --> E[No Internet Gateway]
    style A fill:#0b2545,color:#fff
    style C fill:#1d4e89,color:#fff
    style D fill:#2d6a9f,color:#fff
    style E fill:#c53030,color:#fff
    

Figure 16.1 — Private connectivity to Bedrock via AWS PrivateLink. Traffic never traverses the public internet.

16.4 Shared Responsibility for AI

Table 16.1 — Shared Responsibility for AI Services
LayerAWS ResponsibilityYour Responsibility
InfrastructureData centers, hardware, networkingNone
Managed service endpointsAPI availability, patchingConfigure VPC endpoints
Foundation models (Bedrock)Model hosting, base model integrityModel access policies, guardrails
Training dataStorage durabilityData classification, encryption, access control
Application logicNoneInput validation, output filtering, logging
Key Concept

Amazon Bedrock does not share your inputs or outputs with third-party model providers, and it does not use them to train base models unless you explicitly opt in.

16.5 Securing Agent Identity and Tool Access

AI agents may call tools, access APIs, and interact with business systems. Treat an agent's identity and permissions as security boundaries: grant only the access needed for its task, scope credentials to the intended resources, and monitor its actions.

Table 16.2 — Agent Identity and Authorization
ConceptPurposeExam Clue
IAM role and policyDefines which AWS actions a workload identity may performLeast privilege for AWS resources
Amazon Bedrock AgentCore IdentitySupports identity and authentication for agents accessing tools and resourcesSecure agent identity and credential handling
Policy in AgentCoreProvides policy-based controls over agent actions and tool useRestrict what an agent is permitted to do
Amazon Bedrock GuardrailsApplies configured safeguards to model inputs and outputsFilter harmful content or sensitive information

16.6 Data Lineage and Secure Data Engineering

  • Data lineage: record where data originated, how it was transformed, and where it was used.
  • Data cataloging: maintain searchable descriptions, ownership, classification, and context for datasets.
  • Data integrity: protect data from unauthorized or accidental alteration.
  • Access control: restrict datasets to approved users, roles, services, and workloads.
  • Privacy-enhancing practices: minimize collected data, mask or redact sensitive fields where appropriate, and consider de-identification or synthetic data when suitable.
AWS Service Association

Amazon Macie helps discover and assess sensitive data in Amazon S3. Amazon SageMaker Model Cards can document model details and intended use. Use lineage and catalog information to understand the origin and handling of data used by an AI solution.

16.7 Protect Inputs, Outputs, and AI Interaction Logs

  1. Validate and constrain user inputs; do not treat retrieved documents or tool output as trusted instructions.
  2. Defend against prompt injection and unauthorized tool requests with layered controls.
  3. Filter and validate model outputs before displaying them or using them to trigger actions.
  4. Use grounding, source checks, and confidence thresholds to identify answers that need review.
  5. Log relevant prompts, model versions, tool calls, decisions, and outcomes while applying data minimization, retention limits, and access controls.
  6. Monitor for toxicity, sensitive-data leakage, anomalous activity, and policy violations.
Exam Trap

Encryption protects data at rest or in transit; it does not prevent a model from generating harmful or incorrect text. Guardrails and output validation address different risks. Logging supports investigation and audit, but logs themselves must be protected and governed.

16.8 Grounding, Hallucination Detection, and Output Validation

Grounding connects a generated response to trusted evidence, such as approved documents retrieved through RAG. It can reduce unsupported claims, but it does not guarantee correctness: retrieval can return irrelevant or outdated material, and a model can still misinterpret evidence.

Layered controls for reducing unsupported AI output
ControlWhat it checksWhat it cannot guarantee
Retrieval relevanceWhether retrieved passages match the user’s requestThat the model will use them correctly
Grounding and source citationsWhether claims are supported by retrieved sourcesThat every cited source is complete or current
Output validationRequired fields, format, policy rules, and factual constraintsFull factual truth unless the validation has reliable evidence
Confidence scoring and thresholdsWhether uncertain cases should be escalatedA universally calibrated probability of correctness
Human reviewHigh-impact, ambiguous, or flagged outputsFreedom from human error; reviewers need guidance and evidence

For high-impact workflows, combine retrieval evaluation, citation checks, deterministic validation where possible, monitoring, and human escalation. Treat user-supplied documents and tool outputs as data, not as trusted instructions; this also reduces prompt-injection risk.

Domain 5 · Chapter 17

Data Privacy, Compliance, and Governance for AI

This chapter covers data residency, lifecycle management, compliance services, and governance frameworks.

17.1 Data Privacy and Residency

Data residency is the governance principle that data must be stored and processed within a specific geographic boundary. Data residency requirements depend on the applicable law, contract, sector, and organization policy. GDPR does not impose a blanket requirement to store all personal data in the EU, and HIPAA does not create a general U.S.-only data-residency rule. Organizations must assess cross-border transfer rules, safeguards, contractual commitments, and the locations where data is stored and processed.

17.2 Compliance Services

Table 17.1 — AWS Compliance Services
ServicePurposeWhen to Use
AWS ConfigResource configuration tracking and compliancePolicy adherence monitoring
AWS CloudTrailAPI activity loggingAudit trails
AWS CloudTrail LakeQueryable environment for collecting and analyzing audit eventsSearch and analyze activity over time; apply appropriate retention and access controls
AWS ArtifactAWS compliance reports and certificationsDemonstrating AWS compliance
Amazon MacieSensitive data discovery in S3PII detection
Amazon InspectorVulnerability scanningEC2, container, Lambda security

17.3 Governance Frameworks

AI governance frameworks define policies and guidelines for data, transparency, responsible AI, and compliance. AWS CAF for AI provides guidance across six perspectives: Business, People, Governance, Platform, Security, and Operations.

Coach's Takeaway

Data lifecycle management covers creation, updates, retention, and scheduled deletion. It is a governance component, not a security service.

17.4 Governance Operations and Review Cadence

Governance is an ongoing process, not a one-time approval. Establish ownership and repeatable reviews throughout the AI lifecycle.

  1. Set policies: define acceptable use, data classification, model approval, human oversight, and incident escalation.
  2. Assign owners: identify who is accountable for the data, model, application, security controls, and user impact.
  3. Review before release: assess intended use, data rights, privacy, fairness, security, evaluation results, and limitations.
  4. Monitor after release: review incidents, drift, user feedback, access logs, performance, and policy violations.
  5. Reassess periodically: repeat reviews when the model, data, use case, regulation, or risk level changes.
  6. Train teams: ensure developers, reviewers, operators, and business owners understand their responsibilities.

17.5 Generative AI Security Scoping Matrix

The Generative AI Security Scoping Matrix is a way to reason about security according to the architecture and level of control in a generative AI solution. Identify where the model runs, who controls the model and infrastructure, what data is supplied, which external tools are connected, and where the application boundary lies. Security responsibilities and attack surfaces change with the deployment pattern.

Table 17.2 — Governance Questions by Area
AreaQuestions to AskEvidence or Control
DataWhere did data come from? Is its use permitted? How long is it retained?Data catalog, lineage, classification, retention policy
ModelWho provides it? What are its limitations and intended uses?Model Card, evaluation results, license review
ApplicationCan users inject instructions or extract sensitive data?Threat modeling, guardrails, input/output validation
Identity and toolsWhat can the agent access or execute?Least-privilege IAM, AgentCore identity and policy controls
OperationsCan activity be investigated and controls rechecked?CloudTrail logs, monitoring, incident and review procedures

17.6 Governance and Compliance Service Selection

Table 17.3 — Match the AWS Service to the Governance Need
ServicePrimary UseScenario Clue
AWS ConfigRecords and evaluates resource configurationsCheck whether resources comply with configuration rules
Amazon InspectorFinds software vulnerabilities and exposure risks in supported workloadsAssess vulnerabilities in compute workloads
AWS CloudTrailRecords AWS API activityInvestigate who performed an AWS action and when
AWS ArtifactProvides access to AWS compliance reports and agreementsObtain AWS audit and compliance documentation
AWS Trusted AdvisorProvides recommendations across areas such as security, fault tolerance, performance, and service limitsIdentify opportunities to improve AWS environment posture
Exam Trap

Do not mix up the services: CloudTrail records API activity; Config tracks resource configuration; Artifact provides AWS compliance documents; Inspector identifies vulnerabilities; Trusted Advisor provides recommendations.

Data Residency: A Practical Decision Framework

Do not assume that a regulation automatically requires every copy of data to remain in one country. Identify the data subjects and data types, the organization’s role, the applicable legal and contractual requirements, cross-border transfer mechanisms, and the AWS Regions used by each service. Also check where backups, logs, support data, and model-related processing occur. A residency decision is a documented legal, contractual, and architecture assessment—not simply a Region selection.

Common confusion

Data residency is about where data is stored or processed. Data sovereignty concerns the laws and governmental authority that may apply to data. Data localization is a specific requirement to keep certain data within a jurisdiction. These ideas overlap but are not identical.

Domain 5 — v1.2 Focus: Security and Governance Service Map

The current AWS exam guide groups this domain into two tasks: securing AI systems, and recognizing governance and compliance requirements. The examples below follow the official task statements; the official in-scope service list is broader and non-exhaustive.

Security capabilities explicitly highlighted in Task 5.1
CapabilityWhat it protects or controlsPractical interpretation
IAM roles, policies, and permissionsIdentity and authorizationGrant each user, workload, and agent only the actions and resources it needs
EncryptionData at rest and in transitProtect stored datasets, model artifacts, and network communication; manage keys appropriately
Amazon MacieSensitive data in Amazon S3Discover and help assess sensitive information stored in S3
AWS PrivateLinkPrivate service connectivityReduce exposure to the public internet when connecting to supported AWS services
AWS shared responsibility modelSecurity ownershipSeparate AWS responsibilities for the cloud from customer responsibilities in the cloud; the split changes by service type
Amazon Bedrock AgentCore IdentityAgent identity and authenticationEstablish and manage identity and credentials for agents accessing tools and resources
Policy in AgentCoreAgent action authorizationConstrain which actions an agent is allowed to perform
Amazon Bedrock GuardrailsModel inputs and outputsApply configured safeguards such as content filtering and sensitive-information controls
Governance and compliance examples explicitly highlighted in Task 5.2
AWS servicePrimary purposeChoose it when the requirement is…
AWS ConfigResource configuration tracking and compliance evaluationCheck whether AWS resources meet defined configuration rules
Amazon InspectorVulnerability managementIdentify software vulnerabilities and exposure risks in supported workloads
AWS ArtifactCompliance reports and agreementsObtain AWS audit and compliance documentation
AWS CloudTrailAccount activity and API event historyInvestigate who performed an AWS action and when
AWS Trusted AdvisorRecommendations across AWS environment categoriesFind opportunities to improve security, reliability, performance, and cost posture

Related in-scope capabilities: Amazon CloudWatch supports monitoring and operational logs; AWS Secrets Manager helps manage secrets such as credentials and API keys; Amazon S3 is a common storage layer whose access, encryption, retention, and logging must be governed. These services complement the task-statement examples but do not replace them.

Data provenance: data lineage records where data originated and how it changed; data cataloging makes datasets discoverable and understandable; source citation helps users trace generated claims to supporting material. Amazon SageMaker Model Cards can document model details, intended use, evaluation, and limitations.

Security decision rule

Encryption protects confidentiality of data at rest or in transit. IAM and AgentCore Policy control who or what can act. Guardrails and output validation address model-content risks. CloudTrail supports investigation. These controls solve different problems and should not be treated as interchangeable.

Scope note

Older study materials may contain services that are not in the current AIF-C01 in-scope service list, including AWS Audit Manager, Amazon Kendra, Amazon Fraud Detector, and Amazon Augmented AI (A2I). Focus first on the current Domain 5 task statements and the official in-scope list. AWS states that the in-scope list is non-exhaustive and may change.

AIF-C01 Study Guide: Frequently Asked Questions

Is this AWS AIF-C01 study guide free?

Yes. This study guide is available free on CloudExamPro and is designed to help candidates understand the AWS Certified AI Practitioner (AIF-C01) exam objectives.

What topics does the guide cover?

It covers all five AIF-C01 domains: AI and machine learning (20%), generative AI (24%), foundation model applications (28%), responsible AI (14%), and security, compliance, and governance (14%).

Is the study guide aligned with the current AWS exam guide?

The guide was reviewed against AWS AIF-C01 Exam Guide version 1.2, published on 29 October 2026. Always check the official AWS certification page for the latest exam information.

Does this study guide include a full practice exam?

No. This page focuses on explanations, reference tables, decision frameworks, and revision planning. A separate free 25-question AIF-C01 diagnostic is available to check your readiness.

How should I use the guide before the exam?

Start with the exam overview, study the five domains, and use the 7-day or 14-day plan that matches your available time. Finish with the revision sheet and the separate diagnostic exam.

Study Guide Complete

Ready to Check Your AIF-C01 Readiness?

This guide is designed for learning and reference. After reviewing the five domains, use the separate free 25-question AIF-C01 diagnostic to check your current readiness.

Start the Free 25-Question Diagnostic →
Reference Module M10

Final-Day Revision Sheet

A compact, high-value summary of the entire blueprint. Review this the day before your exam.

Domain 1 — AI & ML (20%)

  • AI includes ML; deep learning is a subset of ML. GenAI is a content-generation capability commonly powered by deep-learning FMs; agentic AI is a tool-using system pattern.
  • Supervised (labeled) / Unsupervised (unlabeled) / Reinforcement (rewards)
  • Classification (category) vs. Regression (number)
  • Accuracy misleading on imbalanced data → use F1
  • Train-good/test-bad = overfitting → regularization
  • Business goal first → compliance before data collection

Domain 2 — GenAI (24%)

  • Tokens, embeddings, context window
  • Lower temperature = more focused sampling; it does not guarantee determinism or factuality
  • Zero-shot, few-shot, chain-of-thought, ReAct
  • RAG reduces hallucinations by grounding in sources
  • Prompt injection = override instructions; jailbreak = bypass safety

Domain 3 — FM Applications (28%)

  • Bedrock = managed FMs; SageMaker AI = custom ML
  • Bedrock Knowledge Bases = managed RAG
  • Bedrock Agents = multi-step API orchestration
  • Bedrock Guardrails = safety policies
  • Prompt engineering → RAG → fine-tuning → continued pre-training (increasing effort)
  • On-Demand (unpredictable) vs. Provisioned Throughput (steady)

Domain 4 — Responsible AI (14%)

  • Fairness, explainability, transparency, privacy, safety, robustness, controllability
  • SageMaker Clarify = bias detection + SHAP explainability
  • Model Cards = standardized documentation
  • Human-in-the-loop review = human oversight for low-confidence or high-impact outputs

Domain 5 — Security (14%)

  • IAM = access control; KMS = encryption; PrivateLink = private network
  • Amazon Bedrock customer prompts and outputs are not used to train base FMs by default; data handling and retention vary by feature, model, and Region
  • Macie = sensitive-data discovery in S3; Inspector = vulnerability findings
  • CloudTrail = API activity logs; CloudTrail Lake = queryable event analysis with configured retention and access controls
  • Artifact = AWS compliance reports; Config = resource configuration/compliance evaluation
  • Data residency = where data lives; lifecycle = how long
Last-Minute Reminder

Read every question for the decisive requirement. The exam rewards the candidate who identifies the constraint, not the one who memorizes the most services.

Reference Module M11

Practice-Based Self-Assessment Checklist

Mark each item you can explain confidently. Unchecked items are your review priorities.

Domain 1

Domain 2

Domain 3

Domain 4

Domain 5

Reference Module M12

Acronym and Glossary Reference

Searchable or clearly organized terminology for quick reference.

Table M12.1 — Acronyms and Glossary
Term/AcronymExpansionDefinition
AIArtificial IntelligenceBroad field of simulating human intelligence
HITLHuman-in-the-loopHuman review of low-confidence or high-impact AI outputs
BERTScoreBidirectional Encoder Representations from Transformers ScoreSemantic similarity metric
BLEUBilingual Evaluation UnderstudyTranslation quality metric
CTRClick-Through RateEngagement metric
FMFoundation ModelLarge pre-trained adaptable model
IAMIdentity and Access ManagementAWS access control service
KMSKey Management ServiceAWS encryption key management
LLMLarge Language ModelText-specialized foundation model
MCPModel Context ProtocolStandard for connecting AI to external tools
MLMachine LearningSubset of AI that learns from data
PIIPersonally Identifiable InformationSensitive personal data
RAGRetrieval Augmented GenerationGrounding LLM responses in external data
RLHFReinforcement Learning from Human FeedbackAligning models with human preferences
ROUGERecall-Oriented Understudy for Gisting EvaluationSummarization quality metric
SHAPSHapley Additive exPlanationsFeature importance for explainability
Reference Module M13

Exam-Day Preparation Checklist

Practical preparation advice, with logistics verified against current official guidance where applicable.

Before the Exam

During the Exam

After the Exam

References

All references are official AWS documentation, AWS Builder Center articles, or AWS whitepapers. Time-sensitive details were verified against the current documentation as of this guide's publication.

  1. AWS Certified AI Practitioner (AIF-C01) Exam Guide — Official exam domains, task statements, and weights.
  2. AIF-C01 Domain 1 Objectives — AI/ML fundamentals, practical use cases, and lifecycle.
  3. AIF-C01 Domain 2 Objectives — GenAI concepts, agentic AI, and AWS infrastructure.
  4. AIF-C01 Domain 3 Objectives — Foundation model applications, prompting, customization, and evaluation.
  5. AIF-C01 Exam Guide Revision History — Version changes and publication dates.
  6. AIF-C01 In-Scope AWS Services — Official list of in-scope services.
  7. Amazon Bedrock User Guide — Service overview, models, capabilities.
  8. Amazon Bedrock Knowledge Bases — Managed RAG implementation.
  9. Amazon Bedrock Guardrails — Content filters, denied topics, PII filters, contextual grounding.
  10. Amazon Bedrock Agents — Multi-step orchestration and API calls.
  11. Amazon Bedrock Model Evaluation — Automatic and human evaluation metrics.
  12. Amazon Bedrock Data Protection — Data-handling guarantees and third-party sharing policy.
  13. AWS PrivateLink for Amazon Bedrock — Private VPC connectivity.
  14. SageMaker Model Cards — Standardized model documentation.
  15. SageMaker Clarify — Bias detection and explainability.
  16. SageMaker Model Monitor — Production drift detection.
  17. SageMaker Automatic Model Tuning — Hyperparameter optimization.
  18. SageMaker Canvas — No-code ML.
  19. SageMaker JumpStart — Pre-trained models and templates.
  20. SageMaker Data Wrangler — Visual data preparation.
  21. SageMaker Ground Truth — Data labeling.
  22. AWS Trusted Advisor — Recommendations for security, reliability, performance, and cost.
  23. AWS Config — Resource configuration and compliance.
  24. AWS CloudTrail — API activity logging.
  25. AWS CloudTrail Lake — Queryable event data store for audit analysis.
  26. Amazon Macie — Sensitive data discovery.
  27. Amazon Inspector — Vulnerability scanning.
  28. AWS Artifact — AWS compliance reports.
  29. Amazon Q Business — Enterprise AI assistant.
  30. Amazon Q Developer — Developer productivity.
  31. Amazon Nova — Multimodal foundation models.
  32. Amazon Nova Canvas — Image generation.
  33. Amazon Nova Reel — Video generation.
  34. AWS — What is RAG? — RAG explanation.
  35. AWS — What is Prompt Engineering? — Prompting techniques.
  36. AWS — What are Embeddings? — Embeddings explanation.
  37. AWS — What is Overfitting? — Overfitting explanation.
  38. AWS Responsible AI — Responsible AI dimensions and resources.
  39. AWS Well-Architected Machine Learning Lens — ML lifecycle phases.
  40. AWS CAF for AI — AI governance framework.
  41. AWS Data Residency — Data residency compliance.
  42. AWS Prescriptive Guidance — Common LLM Attacks — Prompt injection and jailbreak.
  43. Amazon Bedrock Prompt Management — Store and reuse prompts.
  44. Amazon Bedrock Provisioned Throughput — Dedicated capacity.
  45. Amazon Bedrock Batch Inference — Bulk generation.
Reference Verification

All references were verified against current official AWS documentation at the time of writing. Time-sensitive details (service features, pricing models, metric names) should be re-verified against the latest AWS documentation before relying on them in production.

Limited-time offer · ends in -- Days : -- Hrs : -- Min : -- Sec
Get Instant Access