Coverage AIF-C01
Every item of the official exam guide (retrieved 2026-11-16) and the sections that cover it.
69/69 guide items covered51/51 in-scope services covered
Fundamentals of AI and ML
Task 1.1: Explain basic AI concepts and terminologies.
- objectiveDefine basic AI terms (for example, AI, ML, deep learning, neural networks, computer vision, natural language processing [NLP], model, algorithm, training and inferencing, bias, fairness, fit, large language model [LLM], generative AI [GenAI], agentic AI).AI, ML, deep learning and generative AITraining, overfitting and underfittingFoundation models and LLMsTokens, prompts and embeddingsBias, fairness and datasetsCommon algorithms and model families
- objectiveDescribe the similarities and differences between AI, ML, GenAI, deep learning, and agentic AI.AI, ML, deep learning and generative AIAgents, tools and MCP
- objectiveDescribe various types of inferencing (for example, batch, real-time, asynchronous, serverless).Inference optionsPricing, throughput and inference options
- objectiveDescribe the different types of data in AI models (for example, labeled and unlabeled, tabular, time-series, image, text, structured and unstructured).Types of data for AI models
- objectiveDescribe different types of AI/ML learning (for example, supervised learning, unsupervised learning, reinforcement learning methods).Supervised, unsupervised and reinforcement learning
Task 1.2: Identify practical use cases for AI.
- objectiveRecognize applications where AI/ML can provide value (for example, assist human decision making, solution scalability, automation).AI, ML, deep learning and generative AIWhat generative AI does well and where it failsAgents, tools and MCP
- objectiveDetermine when AI/ML solutions are not appropriate (for example, cost-benefit analyses, situations when a specific outcome is needed instead of a prediction).Phases of the ML lifecycle
- objectiveSelect the appropriate AI/ML techniques for specific use cases (for example, regression, classification, clustering).Supervised, unsupervised and reinforcement learningCommon algorithms and model families
- objectiveIdentify examples of real-world AI applications (for example, computer vision, NLP, speech recognition, recommendation systems, fraud detection, forecasting, knowledge bases, agentic AI).AI, ML, deep learning and generative AIRecommendationsImage and video analysisDocument text extractionKnowledge Bases and RAGAgents, tools and MCPIntelligent search
- objectiveExplain the capabilities of AWS managed AI/ML services (for example, Amazon SageMaker AI, Amazon Transcribe, Amazon Translate, Amazon Comprehend, Amazon Lex, Amazon Polly).Build, train, and deploy modelsSpeech to textSpeakers, privacy and toxicityLanguage translationText analysisCustom analysis and targeted sentimentConversational interfacesText to speechImage and video analysisDocument text extractionRecommendationsIntelligent search
- objectiveIdentify when traditional ML models or foundation models (FMs) are appropriate for a specific use case (for example, based on regulatory concerns, explainability requirements, operational constraints).What generative AI does well and where it failsTransparency and explainability
Task 1.3: Describe the AI/ML development lifecycle.
- objectiveDescribe and differentiate components of an AI/ML pipeline.Phases of the ML lifecycleTraining, overfitting and underfittingThe ML lifecycle on SageMaker AI
- objectiveDescribe sources of FM models (for example, open source pre-trained models, training custom models).JumpStart, Canvas and Unified StudioChoosing an AWS generative AI serviceFoundation models through one API
- objectiveDescribe methods to use a model in production (for example, managed API service, self-hosted API).Choosing an AWS generative AI serviceInference optionsECS basicsEKS basicsLambda basicsThe ML lifecycle on SageMaker AI
- objectiveIdentify relevant AWS services and features for each stage of an AI/ML pipeline (for example, Amazon Bedrock, Amazon Quick, Kiro, SageMaker AI).Foundation models through one APIQuick Sight basicsAgentic development with KiroData preparation and human reviewData integration and catalogGlue DataBrewEMR basicsRedshift basicsThird-party dataStorage classesDynamoDB basicsElastiCache basicsManaged vs self-managed databasesAccelerated computing for AIThe ML lifecycle on SageMaker AI
- objectiveDescribe fundamental concepts of ML operations (MLOps) (for example, experimentation, repeatable processes, scalable systems, managing technical debt, achieving production readiness, model monitoring, model re-training).MLOps, monitoring and governancePhases of the ML lifecycleThe ML lifecycle on SageMaker AI
- objectiveDescribe model performance metrics (for example, accuracy, precision, recall, F1 score) and business metrics (for example, cost per user, development costs, customer feedback, return on investment [ROI]) to evaluate ML models.Model performance metrics
Fundamentals of GenAI
Task 2.1: Explain the basic concepts of generative AI (GenAI).
- objectiveDefine foundational GenAI concepts (for example, tokens, chunking, embeddings, vectors, prompt engineering, transformer-based large language models [LLMs], foundation models [FMs], multi-modal models, diffusion models).Tokens, prompts and embeddingsFoundation models and LLMsKnowledge Bases and RAGNova modelsA generative AI assistant with RAG
- objectiveIdentify potential use cases for GenAI models (for example, image, video, and audio generation; summarization; AI assistants; translation; code generation; customer service agents; search; recommendation engines).What generative AI does well and where it failsNova modelsAgentic development with KiroAgentic migration and modernization
- objectiveDescribe the FM lifecycle (for example, data selection, model selection, pre-training, fine-tuning, evaluation, deployment, feedback).GenAI lifecycle and choosing a model
- objectiveDescribe the token-based pricing model and its effect on cost and performance for inference.Pricing, throughput and inference options
- objectiveDescribe the role of context engineering in FM applications.Choosing a customization approach
- objectiveDefine foundational agentic AI concepts (for example, multi-agent system patterns for complex AI applications, Model Context Protocol [MCP] and its role in connecting agents to external systems, multi-agent communication patterns, memory management, tool usage, and workflow orchestration).Agents, tools and MCPMulti-agent systems and memoryAn AI agent that uses tools
Task 2.2: Understand the capabilities and limitations of GenAI for solving business problems.
- objectiveDescribe the advantages of GenAI (for example, adaptability, responsiveness, conversational capabilities, ability to generate content).What generative AI does well and where it fails
- objectiveIdentify disadvantages of GenAI solutions (for example, hallucinations, interpretability, inaccuracy, nondeterminism).What generative AI does well and where it fails
- objectiveIdentify factors to consider when selecting GenAI models (for example, model types, performance requirements, capabilities, constraints, compliance, cost, latency, model complexity).GenAI lifecycle and choosing a model
- objectiveDetermine business value and metrics for GenAI applications (for example, cross-domain performance, ROI, efficiency, conversion rate, average revenue per user, accuracy, customer lifetime value).Business and application metrics
Task 2.3: Describe AWS infrastructure and technologies for building GenAI applications.
- objectiveIdentify AWS services and features to develop GenAI applications (for example, Amazon Bedrock, Amazon SageMaker AI, SageMaker JumpStart, Amazon Quick, Kiro, Strands Agents, Amazon Bedrock AgentCore).Choosing an AWS generative AI serviceFoundation models through one APIJumpStart, Canvas and Unified StudioQuick Sight basicsAgentic development with KiroBuilding agents with StrandsAgentCore servicesNova modelsA generative AI assistant with RAGAn AI agent that uses tools
- objectiveDescribe the advantages of using AWS GenAI services to build applications (for example, accessibility, lower barrier to entry, efficiency, cost-effectiveness, speed to market, ability to meet business objectives).Choosing an AWS generative AI serviceFoundation models through one API
- objectiveDescribe the benefits of AWS infrastructure for GenAI applications (for example, security, compliance, responsibility, safety).Securing and monitoring BedrockSecurity of and in the cloudGuardrails
- objectiveDescribe cost tradeoffs of AWS GenAI services (for example, responsiveness, availability, redundancy, performance, regional coverage, token-based pricing, provision throughput, custom models).Pricing, throughput and inference optionsChoosing an AWS generative AI serviceAWS BudgetsAWS Cost Explorer
Applications of Foundation Models
Task 3.1: Describe design considerations for applications that use foundation models (FMs).
- objectiveIdentify selection criteria to choose FMs (for example, cost, modality, latency, multi-lingual, model size, model complexity, customization, input/output length, prompt caching).GenAI lifecycle and choosing a modelPricing, throughput and inference optionsNova models
- objectiveDescribe the effect of inference parameters on model responses (for example, temperature, input/output length).Inference parameters
- objectiveDefine Retrieval Augmented Generation (RAG) and describe its business applications (for example, Amazon Bedrock Knowledge Bases).Knowledge Bases and RAGA generative AI assistant with RAG
- objectiveIdentify AWS services that help store embeddings within vector databases (for example, Amazon OpenSearch Service, Amazon Aurora, Amazon Neptune, Amazon RDS for PostgreSQL).Knowledge Bases and RAGOpenSearch basicsGraph databasesAurora basicsDocumentDB basicsA generative AI assistant with RAG
- objectiveExplain the cost tradeoffs of various approaches to FM customization (for example, pre-training, fine-tuning, in-context learning, RAG, model distillation).Choosing a customization approachCustomizing models in Bedrock
- objectiveDefine the role of AI agents and describe AI agents' business applications.Agents, tools and MCPAgentCore servicesAn AI agent that uses tools
Task 3.2: Choose effective prompt engineering techniques.
- objectiveDefine the concepts and constructs of prompt engineering (for example, context, instruction, negative prompts).Prompt elements and techniques
- objectiveDefine techniques for prompt engineering (for example, chain-of-thought, zero-shot, single-shot, few-shot, prompt templates).Prompt elements and techniques
- objectiveIdentify and describe the benefits and best practices for prompt engineering (for example, response quality improvement, experimentation, guardrails, discovery, specificity and concision, using multiple comments).Prompt elements and techniquesGuardrails
- objectiveDefine potential risks and limitations of prompt engineering (for example, exposure, poisoning, hijacking, jailbreaking).Prompt attacks and defenses
- objectiveDescribe prompt versioning and management strategies that use Amazon Bedrock Prompt Management.Prompt Management and Flows
Task 3.3: Describe the training and fine-tuning process for FMs.
- objectiveDescribe the key elements of training an FM (for example, pre-training, fine-tuning, continuous pre-training, distillation).Choosing a customization approachCustomizing models in BedrockFoundation models and LLMs
- objectiveDefine methods for fine-tuning an FM (for example, instruction tuning, adapting models for specific domains, transfer learning, continuous pre-training).Fine-tuning methods and training dataCustomizing models in Bedrock
- objectiveDescribe how to prepare data to fine-tune an FM (for example, data curation, governance, size, labeling, representativeness, reinforcement learning from human feedback [RLHF]).Fine-tuning methods and training dataData preparation and human review
Task 3.4: Describe methods to evaluate FM performance.
- objectiveDetermine approaches to evaluate FM performance (for example, human-in-the-loop evaluation, benchmark datasets, Amazon Bedrock Model Evaluation).Evaluation methods and metricsModel and RAG evaluation in Bedrock
- objectiveIdentify relevant metrics to assess FM performance (for example, Recall-Oriented Understudy for Gisting Evaluation [ROUGE], Bilingual Evaluation Understudy [BLEU], BERTScore, LLM-as-a-judge).Evaluation methods and metrics
- objectiveDetermine whether an FM effectively meets business objectives (for example, productivity, user engagement, task engineering).Business and application metrics
- objectiveIdentify approaches to evaluate the performance of applications built with FM (for example, RAG, agents, workflows).Model and RAG evaluation in BedrockAgentCore servicesBusiness and application metrics
- objectiveIdentify business objective alignment metrics for AI applications (for example, task completion rate, user satisfaction, cost per interaction).Business and application metrics
Guidelines for Responsible AI
Task 4.1: Explain the development of AI systems that are responsible.
- objectiveIdentify features of responsible AI (for example, bias, fairness, inclusivity, robustness, safety, veracity).Dimensions of responsible AI
- objectiveExplain how to use tools to identify features of responsible AI (for example, Amazon Bedrock Guardrails).GuardrailsBias, fairness and datasets
- objectiveDefine responsible practices to select a model (for example, environmental considerations, sustainability).GenAI lifecycle and choosing a model
- objectiveIdentify legal risks of working with generative AI (GenAI) (for example, intellectual property infringement claims, biased model outputs, loss of customer trust, end user risk, hallucinations).Legal and business risks of generative AI
- objectiveIdentify characteristics of datasets (for example, inclusivity, diversity, curated data sources, balanced datasets).Bias, fairness and datasets
- objectiveDescribe effects of bias and variance (for example, effects on demographic groups, inaccuracy, overfitting, underfitting).Training, overfitting and underfittingBias, fairness and datasets
- objectiveDescribe tools to detect and monitor bias, trustworthiness, and truthfulness (for example, analyzing label quality, human audits, subgroup analysis).Bias, fairness and datasetsMLOps, monitoring and governanceData preparation and human review
Task 4.2: Recognize the importance of transparent and explainable models.
- objectiveDescribe the differences between models that are transparent and explainable and models that are not transparent and explainable.Transparency and explainability
- objectiveDescribe tools to identify transparent and explainable models (for example, Amazon SageMaker Model Cards, Amazon Bedrock Model Evaluations, open source models, data, licensing).Transparency and explainabilityMLOps, monitoring and governanceModel and RAG evaluation in Bedrock
- objectiveIdentify tradeoffs between model safety and transparency (for example, measure interpretability and performance).Transparency and explainability
- objectiveDescribe principles of human-centered design for explainable AI (for example, user-feedback mechanisms, AI decision transparency).Transparency and explainabilityDimensions of responsible AI
Security, Compliance, and Governance for AI Solutions
Task 5.1: Explain methods to secure AI systems.
- objectiveIdentify AWS services and features to secure AI systems (for example, IAM roles, policies, and permissions; encryption; Amazon Macie; AWS PrivateLink; AWS shared responsibility model; Amazon Bedrock AgentCore Identity; Policy in AgentCore; Amazon Bedrock Guardrails).Scoping and securing AI workloadsSecuring and monitoring BedrockUsers, groups, and policiesIAM roles basicsEncryption at rest and in transitMacie basicsPrivateLink basicsSecurity of and in the cloudSecrets Manager basicsAgentCore servicesGuardrailsA generative AI assistant with RAG
- objectiveDescribe the concept of source citation and documenting data origins (for example, data lineage, data cataloging, Amazon SageMaker Model Cards).Data governance for AIKnowledge Bases and RAGData integration and catalogMLOps, monitoring and governance
- objectiveDescribe best practices for secure data engineering (for example, assessing data quality, implementing privacy-enhancing technologies, data access control, data integrity).Data governance for AIData lake governanceGlue DataBrew
- objectiveDescribe security and privacy considerations for AI systems (for example, application security, threat detection, vulnerability management, infrastructure protection, prompt injection, encryption at rest and in transit, data leakage prevention, output filtering and validation, audit trail and logging requirements for AI interactions, toxicity).Scoping and securing AI workloadsPrompt attacks and defensesGuardrailsSecuring and monitoring BedrockInspector basicsVPC security basicsCloudFront basicsAn AI agent that uses tools
- objectiveDescribe hallucination detection methods and grounding techniques to improve output accuracy (for example, Retrieval Augmented Generation [RAG] grounding, output validation, confidence scoring).Detecting and reducing hallucinationsGuardrailsA generative AI assistant with RAG
Task 5.2: Recognize governance and compliance regulations for AI systems.
- objectiveIdentify AWS services and features to assist with governance and regulation compliance (for example, AWS Config, Amazon Inspector, AWS Artifact, AWS CloudTrail, AWS Trusted Advisor).AWS Config basicsInspector basicsReports and agreementsCloudTrail basicsTrusted Advisor basics
- objectiveDescribe data governance strategies (for example, data lifecycles, logging, residency, monitoring, observation, retention).Data governance for AIS3 Lifecycle basicsStorage classesCloudWatch basicsCloudTrail basics
- objectiveDescribe processes to follow governance protocols (for example, policies, review cadence, review strategies, governance frameworks such as the Generative AI Security Scoping Matrix, transparency standards, team training requirements).Scoping and securing AI workloadsData governance for AIWell-Architected Tool
In-scope services
Analytics
- AWS Data Exchange1
- Amazon EMR1
- AWS Glue2
- AWS Glue DataBrew1
- AWS Lake Formation1
- Amazon OpenSearch Service1
- Amazon Quick1
- Amazon Redshift1
Cloud Financial Management
Compute
Containers
Database
- Amazon Aurora1
- Amazon DocumentDB (with MongoDB compatibility)1
- Amazon DynamoDB1
- Amazon ElastiCache1
- Amazon Neptune1
- Amazon RDS1
Developer Tools
Machine Learning
- Amazon Bedrock8
- Amazon Bedrock AgentCore1
- Amazon Comprehend2
- Amazon Lex1
- Amazon Nova1
- Amazon Personalize1
- Amazon Polly1
- Amazon Rekognition1
- Amazon SageMaker AI5
- Amazon SageMaker JumpStart1
- Amazon Textract1
- Amazon Transcribe2
- Amazon Translate1
- AWS Transform1
Management and Governance
Networking and Content Delivery
Security, Identity, and Compliance
- AWS Artifact1
- AWS Identity and Access Management (IAM)2
- Amazon Inspector1
- AWS Key Management Service (AWS KMS)1
- Amazon Macie1
- AWS Secrets Manager1