AWS Certified Generative AI Developer — Professional (AIP-C01)

A documentation-first study guide. AWS writes the exam from its own documentation, so reading the docs is the highest-leverage thing you can do. This guide is a curated index into the canonical references, FAQs, and a selection of whitepapers — organised around the five exam domains, not around services.

Maps to the published AWS Certified Generative AI Developer — Professional (AIP-C01) exam guide. Domain weights and task statements are quoted from that PDF.

About the exam

Current exam code: AIP-C01 (released March 2026). This is AWS’s first professional-level generative AI certification.

Format: 75 questions (65 scored + 10 unscored) · 180 minutes · $300 USD · scaled score 100–1000, pass at 750.

Question types: Multiple choice, multiple response, ordering (sequence tasks correctly), and matching (pair items correctly). All parts must be correct for credit on ordering/matching questions.

The five domains:

Domain 1 — Foundation Model Integration, Data Management, and Compliance — 31%
Domain 2 — Implementation and Integration — 26%
Domain 3 — AI Safety, Security, and Governance — 20%
Domain 4 — Operational Efficiency and Optimization for GenAI Applications — 12%
Domain 5 — Testing, Validation, and Troubleshooting — 11%

Primary official sources (bookmark these):

Key resources:

Amazon Bedrock User Guide — the primary service for this exam
Generative AI Foundations on AWS (Skill Builder)
Building Generative AI Applications Using Amazon Bedrock
AWS Well-Architected Framework — Machine Learning Lens

Priority tiers: The published domain weights (31/26/20/12/11) tell you how the exam is balanced across the five domains, but they don’t tell you that within each domain a handful of services account for most of the questions. Every section in this guide carries a tier badge based on triangulating the AWS exam guide, the experience reports of recent test takers, and the patterns that appear in the practice-exam community:

★★★ Core Heavily tested. Multiple questions will lean on this. Spend hours, not minutes — if you don’t know it well, you fail.
★★ Important Reliably tested, usually one or two questions. Read every linked page in the section, do the FAQ, understand the comparison points. A few hours per topic.
★ Light Known to appear, but typically as one distinguishing question or as wrong-answer distractors. Skim the docs, learn the one-line distinction, move on. Twenty minutes to an hour.

For an 8–12 week prep cycle the rough split that the data supports is about 60% of your time on Core topics, 30% on Important, and 10% on Light. The biggest single concentration of questions across the whole exam is the cluster around Amazon Bedrock + Knowledge Bases + Prompt Engineering + RAG patterns + Agents — know those cold and you have the foundation of a pass.

How to use this guide:

Each section opens with a one-paragraph summary explaining what to focus on, then has up to three link sections: Core docs (user/developer guides — the canonical reference), FAQ (exam writers love edge cases from FAQs — do not skip), and Deeper reading (whitepapers, blog posts, re:Post articles).
If a link 404s, AWS has reorganised the docs. Search the page title to find the new location — the content almost always still exists.
The What’s New feed is worth a weekly scan in the last month before your exam; generative AI is fast-moving but the exam lags new features by ~6-12 months.

Part I — Domain 1: Foundation Model Integration, Data Management, and Compliance (31%)

The largest domain by weight. This covers the fundamentals of foundation models, Amazon Bedrock, prompt engineering, and data preparation for generative AI applications.

Chapter 1 — Foundation model fundamentals

Maps to Task Statement 1.1 — Select and configure foundation models for specific use cases

Knowledge of:

Foundation model types and their characteristics (for example, large language models, vision models, multimodal models)
Model selection criteria based on use case requirements
Inference parameters and their effects (for example, temperature, top-p, max tokens)
Context window limitations and strategies
Model performance trade-offs (for example, latency, cost, quality)

Skills in:

Selecting appropriate foundation models for different use cases
Configuring inference parameters to optimize model outputs
Managing context window constraints
Evaluating model performance and costs

1.1 Foundation model concepts ★★★ Core

Understand what foundation models are, how they differ from traditional ML models, and the key concepts: pre-training, fine-tuning, inference, tokens, context windows, temperature, top-p, and stop sequences. Know the trade-offs between model size, latency, and cost. This conceptual foundation underpins everything else.

Core docs

What is a foundation model? — pre-trained on massive datasets, adaptable to many tasks
Generative AI on AWS overview — service landscape and use cases
Foundation model concepts — available models in Bedrock, capabilities, and limits
Inference parameters — temperature, top-p, max tokens, stop sequences
Token limits and context windows — input/output limits by model

Deeper reading

Generative AI Foundations on AWS (Skill Builder course) — free training covering FM concepts and AWS services

1.2 Amazon Bedrock overview ★★★ Core

Amazon Bedrock is the central service for this exam. Know what Bedrock is (fully managed service for accessing foundation models via API), the available model providers (Amazon Titan, Anthropic Claude, Meta Llama, Mistral, Cohere, AI21 Labs, Stability AI), and how to access models. Understand model access requests, pricing models (on-demand vs provisioned throughput), and regional availability.

Core docs

What is Amazon Bedrock? — fully managed service for accessing FMs via API
Supported foundation models — all available models, providers, and capabilities
Model access — requesting access to specific models
Amazon Bedrock pricing — on-demand vs provisioned, per-token costs
Provisioned throughput — reserved capacity for consistent performance
Cross-region inference — automatic routing to available regions

FAQ

Amazon Bedrock FAQ — common questions on data privacy, model access, pricing

1.3 Amazon Titan models ★★ Important

Know Amazon’s own foundation models: Titan Text (generation), Titan Embeddings (vector embeddings for RAG), Titan Image Generator, and Titan Multimodal Embeddings. Understand when to use Titan vs third-party models.

Core docs

Amazon Titan models — AWS’s own foundation models overview
Titan Text models — text generation, summarization, Q&A
Titan Embeddings — vector embeddings for RAG and semantic search
Titan Image Generator — text-to-image generation
Titan Multimodal Embeddings — embeddings for text and images together

1.4 Third-party models in Bedrock ★★ Important

Know the key third-party models available: Anthropic Claude (text, vision, long context), Meta Llama (open-weight models), Mistral (efficient inference), Cohere (Command, Embed), AI21 Jurassic, and Stability AI (image generation). Understand model selection criteria based on use case requirements.

Core docs

Anthropic Claude models — advanced reasoning, long context, vision capabilities
Meta Llama models — open-weight models, cost-effective inference
Mistral AI models — efficient inference, multilingual support
Cohere models — Command for generation, Embed for embeddings
AI21 Labs models — Jurassic models for enterprise text generation
Stability AI models — image generation and editing

Chapter 2 — Prompt engineering

Maps to Task Statement 1.2 — Apply prompt engineering techniques to optimize model outputs

Knowledge of:

Prompt engineering concepts and best practices
Prompt patterns (for example, zero-shot, few-shot, chain-of-thought)
System prompts and user prompts
Prompt templates and variables
Output formatting techniques

Skills in:

Designing effective prompts for various tasks
Using prompt patterns to improve output quality
Managing and versioning prompts
Iterating on prompts based on output evaluation

2.1 Prompt engineering fundamentals ★★★ Core

Prompt engineering is heavily tested. Know the components of effective prompts (system prompts, user prompts, context, examples), prompt patterns (zero-shot, few-shot, chain-of-thought), and techniques for improving output quality. Understand how to structure prompts for different tasks (summarization, extraction, generation, classification).

Core docs

Prompt engineering concepts — best practices for effective prompts
Design a prompt — step-by-step guide to prompt construction
Prompt templates and examples — reusable patterns for common tasks
What is a prompt? — components: system prompts, user prompts, context

Deeper reading

Prompt Engineering Guide (Anthropic) — zero-shot, few-shot, chain-of-thought patterns
AWS re:Post - Prompt engineering best practices — community solutions and tips

2.2 Bedrock Prompt Management ★★ Important

Know how to use Bedrock Prompt Management to create, version, and manage prompts. Understand prompt templates with variables, prompt testing, and prompt versioning for production workflows.

Core docs

Bedrock Prompt Management — store, version, and manage prompts centrally
Creating prompts — console and API methods
Prompt templates — variables and dynamic content
Prompt versioning — track changes, rollback capabilities

2.3 Bedrock Prompt Flows ★★ Important

Know Prompt Flows for orchestrating multi-step generative AI workflows. Understand nodes (prompt, condition, iterator, collector, Lambda), flow connections, and how to chain prompts for complex tasks.

Core docs

Bedrock Prompt Flows — visual orchestration of multi-step AI workflows
Creating prompt flows — building flows in console or with API
Flow nodes — prompt, condition, iterator, collector, Lambda nodes
Testing prompt flows — validate flow behaviour before deployment

Chapter 3 — Model customization

Maps to Task Statement 1.3 — Customize foundation models for specific use cases

Knowledge of:

Fine-tuning concepts and approaches
Continued pre-training for domain adaptation
Training data preparation and requirements
Model evaluation metrics and techniques

Skills in:

Preparing training data for model customization
Configuring and running fine-tuning jobs
Evaluating customized model performance
Deploying customized models

3.1 Fine-tuning in Bedrock ★★ Important

Know when and how to fine-tune models. Understand the difference between continued pre-training (domain adaptation) and fine-tuning (task-specific training). Know data preparation requirements, training job configuration, and how to evaluate fine-tuned models.

Core docs

Custom models in Bedrock — overview of customization options
Fine-tuning a model — task-specific training with labelled examples
Continued pre-training — domain adaptation with unlabelled data
Preparing training data — format requirements, data quality guidelines
Creating a fine-tuning job — job configuration and hyperparameters

3.2 Model evaluation ★★ Important

Know how to evaluate model performance. Understand automatic evaluation metrics (ROUGE, BERTScore, accuracy) vs human evaluation. Know how to set up evaluation jobs in Bedrock.

Core docs

Model evaluation in Bedrock — compare models and measure quality
Automatic evaluation — ROUGE, BERTScore, accuracy metrics
Human evaluation — subjective quality ratings with human reviewers
Evaluation metrics — metric definitions and selection criteria

Chapter 4 — Data preparation and embeddings

Maps to Task Statement 1.4 — Prepare and manage data for generative AI applications

Knowledge of:

Vector embeddings and their applications
Data chunking strategies (for example, fixed-size, semantic, hierarchical)
Metadata management for knowledge bases
Data quality and preprocessing requirements

Skills in:

Generating embeddings using embedding models
Implementing data chunking for RAG applications
Managing data sources and synchronization
Handling different document formats

4.1 Vector embeddings ★★★ Core

Vector embeddings are fundamental to RAG. Know what embeddings are (dense vector representations of text/images), how to generate them (Titan Embeddings, Cohere Embed), and their role in semantic search. Understand embedding dimensions, normalization, and similarity metrics (cosine, dot product).

Core docs

Amazon Titan Text Embeddings — dense vectors for semantic search
Titan Text Embeddings V2 — configurable dimensions, normalisation options
Cohere Embed models — multilingual embeddings, input types
Titan Multimodal Embeddings — joint text-image embedding space

4.2 Data ingestion and processing ★★ Important

Know how to prepare data for RAG and fine-tuning. Understand document parsing, chunking strategies (fixed-size, semantic, hierarchical), metadata extraction, and data quality considerations.

Core docs

Connect a data source to your knowledge base — S3, web crawlers, Confluence, SharePoint
Connect to Amazon S3 for your knowledge base — bucket configuration and IAM requirements
How content chunking works — fixed-size, semantic, hierarchical strategies
Include metadata for improved queries — filtering and relevance boosting

Part II — Domain 2: Implementation and Integration (26%)

Building production generative AI applications. This covers RAG, Agents, integrations, and application patterns.

Chapter 5 — Retrieval Augmented Generation (RAG)

Maps to Task Statement 2.1 — Design and implement RAG architectures

Knowledge of:

RAG architecture patterns and components
Vector databases and search strategies
Retrieval optimization techniques
Knowledge base configuration options

Skills in:

Designing RAG pipelines for different use cases
Configuring and managing Bedrock Knowledge Bases
Optimizing retrieval quality and relevance
Integrating knowledge bases with applications

5.1 RAG concepts ★★★ Core

RAG is heavily tested. Know the RAG pattern (retrieve relevant context → augment prompt → generate response), why it’s used (reduce hallucinations, incorporate proprietary data), and the components involved (embeddings, vector store, retrieval, generation). Understand the trade-offs between retrieval quality and latency.

Core docs

Retrieval Augmented Generation overview — retrieve → augment → generate pattern
How RAG works — embedding, indexing, retrieval, generation flow
RAG best practices — chunking, metadata, retrieval tuning

Deeper reading

Build a RAG application with Amazon Bedrock — end-to-end tutorial with code examples

5.2 Bedrock Knowledge Bases ★★★ Core

Bedrock Knowledge Bases is the managed RAG service. Know how to create knowledge bases, configure data sources (S3, web crawlers, Confluence, SharePoint), set up vector stores (OpenSearch Serverless, Aurora, Pinecone, Redis), and query knowledge bases. Understand sync jobs and incremental updates.

Core docs

Bedrock Knowledge Bases — managed RAG service overview
Creating a knowledge base — step-by-step setup guide
Connect a data source — supported sources and configuration
Vector store prerequisites — OpenSearch, Aurora, Pinecone, Redis setup
Query and retrieve data — testing retrieval in console
RetrieveAndGenerate API — single API call for RAG

5.3 Vector databases ★★ Important

Know the vector database options for Bedrock Knowledge Bases: Amazon OpenSearch Serverless (fully managed, scalable), Aurora PostgreSQL with pgvector, Amazon Neptune Analytics, Pinecone, and Redis Enterprise Cloud. Understand selection criteria (scale, latency, cost, features).

Core docs

Vector store prerequisites — supported vector databases and setup
OpenSearch Serverless — fully managed, scales automatically
Aurora with pgvector — PostgreSQL extension for vector search
OpenSearch k-NN — similarity search algorithms and index types

Chapter 6 — Bedrock Agents

Maps to Task Statement 2.2 — Build and deploy AI agents

Knowledge of:

Agent architectures and orchestration patterns
Action groups and API definitions
Agent instructions and configuration
Agent versioning and deployment

Skills in:

Creating and configuring Bedrock Agents
Defining action groups with Lambda functions or API schemas
Connecting knowledge bases to agents
Testing and deploying agents

6.1 Agents for Bedrock ★★★ Core

Agents orchestrate multi-step tasks by using foundation models to reason, plan, and take actions. Know how to create agents, define action groups (Lambda functions, API schemas), connect knowledge bases, and configure agent instructions. Understand the agent execution flow and how agents break down complex tasks.

Core docs

Agents for Amazon Bedrock — orchestrate multi-step tasks with FMs
How agents work — reasoning, planning, and action execution flow
Creating an agent — configuration, instructions, model selection
Action groups — connect agents to external APIs and Lambda
Agent instructions — guide agent behaviour and personality
Connecting knowledge bases to agents — RAG-enabled agents for grounded responses

6.2 Agent action groups and APIs ★★ Important

Know how to define action groups using OpenAPI schemas or Lambda functions. Understand how agents invoke actions, pass parameters, and handle responses. Know about return of control for human-in-the-loop patterns.

Core docs

Action group Lambda functions — Lambda as action executor
OpenAPI schemas for action groups — define APIs agents can call
Return of control — human-in-the-loop patterns
Agent versioning and aliases — deployment stages, version management

6.3 Bedrock AgentCore ★ Light

Know AgentCore for building custom agent architectures with more control over the orchestration logic. Understand when to use AgentCore vs managed Agents.

Core docs

Amazon Bedrock AgentCore — custom agent orchestration with more control
AgentCore concepts — building blocks for custom agent architectures

Chapter 7 — Application integration

Maps to Task Statement 2.3 — Integrate generative AI into applications

Knowledge of:

Bedrock APIs and SDK integration patterns
Streaming response handling
Application architecture patterns for GenAI
Error handling and retry strategies

Skills in:

Invoking foundation models programmatically
Implementing streaming responses
Integrating Bedrock with application frameworks
Handling API errors and rate limits

7.1 Bedrock APIs and SDKs ★★★ Core

Know how to invoke Bedrock models programmatically. Understand the InvokeModel and InvokeModelWithResponseStream APIs, request/response formats for different models, and how to use the AWS SDKs (Python Boto3, JavaScript, etc.).

Core docs

Bedrock API Reference — complete API documentation
InvokeModel API — synchronous model invocation
Streaming responses — token-by-token output for lower latency
Converse API — unified API for multi-turn conversations
Using Bedrock with Boto3 — Python SDK reference

7.2 Streaming and real-time applications ★★ Important

Know how to implement streaming responses for better user experience. Understand Server-Sent Events (SSE), WebSocket patterns with API Gateway, and how to handle partial responses in the UI.

Core docs

Streaming model responses — implementing streaming in applications
WebSocket APIs in API Gateway — bidirectional real-time communication
Lambda response streaming — stream large responses from Lambda

7.3 AWS AppSync for GenAI ★ Light

Know how to use AppSync for building GraphQL APIs that integrate with Bedrock. Understand resolvers that call Bedrock, subscriptions for real-time updates, and caching strategies.

Core docs

AWS AppSync — managed GraphQL service
HTTP resolvers — connect GraphQL to REST APIs
Lambda resolvers — custom logic for GraphQL operations

Chapter 8 — Conversational AI

Maps to Task Statement 2.4 — Build conversational AI applications

Knowledge of:

Conversational AI architectures
Intent recognition and slot filling
Conversation management and context
Voice and text interface considerations

Skills in:

Building conversational interfaces with Amazon Lex
Integrating Bedrock with conversational applications
Managing conversation state and context
Implementing voice-enabled applications

8.1 Amazon Lex ★★ Important

Know Amazon Lex for building conversational interfaces. Understand intents, slots, fulfillment with Lambda, and integration with Bedrock for more sophisticated responses. Know when to use Lex vs direct Bedrock integration.

Core docs

What is Amazon Lex? — conversational interfaces with voice and text
Building bots — bot design and configuration
Intents and slots — user intent recognition, parameter extraction
Lambda fulfillment — backend logic for intent handling
Lex with Bedrock — enhance Lex with generative AI

FAQ

Amazon Lex FAQ — pricing, languages, integration options

8.2 Amazon Q Business ★★ Important

Know Amazon Q Business for enterprise AI assistants. Understand data connectors (S3, SharePoint, Confluence, Salesforce), guardrails, user context, and how it differs from building custom RAG with Bedrock Knowledge Bases.

Core docs

What is Amazon Q Business? — enterprise AI assistant with built-in RAG
Setting up Amazon Q Business — application and index configuration
Data connectors — 40+ enterprise sources (SharePoint, Salesforce, etc.)
Guardrails — topic blocking, response filtering

FAQ

Amazon Q Business FAQ — licensing, data handling, supported sources

8.3 Amazon Connect with GenAI ★ Light

Know how Amazon Connect integrates with generative AI for contact center applications. Understand Q in Connect for agent assistance and Lex integration for IVR.

Core docs

Amazon Connect — cloud contact centre service
Q in Connect — real-time agent assistance with GenAI
Amazon Connect with Lex — conversational IVR integration

Part III — Domain 3: AI Safety, Security, and Governance (20%)

Security, responsible AI, and compliance for generative AI applications.

Chapter 9 — Security for generative AI

Maps to Task Statement 3.1 — Implement security best practices for generative AI applications

Knowledge of:

IAM policies for Bedrock resources
Data protection and encryption options
Network security configurations
Secure credential management

Skills in:

Configuring IAM policies for Bedrock access
Implementing encryption at rest and in transit
Configuring VPC endpoints for private connectivity
Managing access to models and knowledge bases

9.1 IAM for Bedrock ★★★ Core

Know how to secure Bedrock access with IAM. Understand service-linked roles, resource-based policies, identity-based policies for model access, and fine-grained permissions for knowledge bases and agents.

Core docs

Security in Amazon Bedrock — security overview and best practices
IAM for Bedrock — permissions for models, knowledge bases, agents
Bedrock service roles — service-linked roles and trust policies
Resource-based policies — cross-account model sharing

9.2 Data protection and encryption ★★ Important

Know how data is protected in Bedrock. Understand encryption at rest (KMS), encryption in transit (TLS), VPC endpoints for private connectivity, and data residency considerations.

Core docs

Data protection in Bedrock — how data is handled and protected
Encryption at rest — KMS integration for custom models
VPC endpoints — private connectivity without internet
AWS PrivateLink — secure, private API access

9.3 Network security ★ Light

Know how to secure network access to Bedrock and related services. Understand VPC configurations for Lambda functions accessing Bedrock, security groups, and NACLs.

Core docs

VPC endpoints for Bedrock — interface endpoints for private access
Lambda VPC configuration — Lambda in VPC for Bedrock access
Security groups — stateful firewall rules

Chapter 10 — Responsible AI and guardrails

Maps to Task Statement 3.2 — Implement responsible AI practices

Knowledge of:

Bedrock Guardrails configuration options
Content filtering and PII detection
Bias detection and mitigation strategies
Human oversight patterns

Skills in:

Configuring guardrails for content filtering
Implementing PII detection and redaction
Setting up topic blocking and word filters
Testing guardrail effectiveness

10.1 Bedrock Guardrails ★★★ Core

Guardrails is heavily tested. Know how to configure guardrails for content filtering (hate speech, violence, sexual content), PII detection and redaction, topic blocking, and word filters. Understand guardrail evaluation and how guardrails are applied to inputs and outputs.

Core docs

Guardrails for Amazon Bedrock — safety controls for inputs and outputs
Creating guardrails — configuration and deployment
Content filters — hate, violence, sexual, misconduct categories
Denied topics — block specific conversation topics
PII filters — detect and redact personal information
Word filters — block specific words and phrases
Testing guardrails — validate filter effectiveness

10.2 Responsible AI principles ★★ Important

Know AWS’s responsible AI principles and how to implement them. Understand bias detection and mitigation, fairness considerations, transparency requirements, and human oversight patterns.

Core docs

Responsible AI — AWS principles and practices
AWS AI Service Cards — transparency documentation for AI services
SageMaker Clarify for bias detection — detect bias in models and data
Human review with A2I — human-in-the-loop for sensitive predictions

10.3 Model invocation logging ★★ Important

Know how to enable and use invocation logging for auditing and compliance. Understand what’s logged, where logs are stored (S3, CloudWatch), and how to analyze usage patterns.

Core docs

Model invocation logging — log prompts and responses for auditing
Logging to S3 — store logs for long-term analysis
Logging to CloudWatch — real-time monitoring and alerting
CloudTrail for Bedrock — API activity logging for compliance

Chapter 11 — Compliance and governance

Maps to Task Statement 3.3 — Ensure compliance and governance for AI applications

Knowledge of:

Compliance frameworks and certifications
Data governance policies
Model invocation logging requirements
Audit and reporting capabilities

Skills in:

Implementing model invocation logging
Configuring audit trails with CloudTrail
Managing data retention and deletion
Documenting AI governance practices

11.1 Compliance frameworks ★ Light

Know Bedrock’s compliance certifications (SOC, ISO, HIPAA eligibility, FedRAMP). Understand data residency requirements and how to design for compliance.

Core docs

Compliance in Bedrock — SOC, ISO, HIPAA eligibility, FedRAMP
AWS Compliance — compliance programs and certifications
AWS Artifact — download compliance reports and agreements

11.2 Data governance ★ Light

Know how Bedrock handles data: training data usage (your data is not used to train foundation models), data retention policies, and data deletion. Understand the shared responsibility model for AI.

Core docs

Data handling in Bedrock — data not used for training, retention policies
AWS Shared Responsibility Model — AWS vs customer security responsibilities

Part IV — Domain 4: Operational Efficiency and Optimization (12%)

Cost management, performance optimization, and scaling generative AI applications.

Chapter 12 — Cost optimization

Maps to Task Statement 4.1 — Optimize costs of generative AI applications

Knowledge of:

Bedrock pricing models (on-demand, provisioned, batch)
Token optimization strategies
Cost allocation and tagging
Model selection for cost efficiency

Skills in:

Estimating and tracking Bedrock costs
Implementing token optimization techniques
Configuring cost allocation tags
Selecting models based on cost requirements

12.1 Bedrock pricing and cost management ★★ Important

Know Bedrock pricing models: on-demand (per token), provisioned throughput (reserved capacity), and batch inference (lower cost for non-real-time). Understand how to estimate costs based on input/output tokens and how to optimize for cost.

Core docs

Amazon Bedrock pricing — on-demand, provisioned, batch pricing
Provisioned throughput — reserved capacity for predictable workloads
Batch inference — lower cost for non-real-time processing
Cost allocation tags — track costs by project, team, environment

12.2 Token optimization ★★ Important

Know techniques to reduce token usage: prompt optimization, response length limits, caching strategies, and choosing appropriate models for different tasks.

Core docs

Inference parameters — tuning for quality vs cost trade-offs
Max tokens parameter — limit output length to reduce costs
Prompt caching — reuse context for repeated prefixes

Chapter 13 — Performance optimization

Maps to Task Statement 4.2 — Optimize performance of generative AI applications

Knowledge of:

Latency optimization techniques
Provisioned throughput configurations
Scaling patterns for GenAI applications
Caching strategies

Skills in:

Implementing streaming responses
Configuring provisioned throughput
Designing scalable GenAI architectures
Implementing caching for responses

13.1 Latency optimization ★★ Important

Know techniques to reduce latency: streaming responses, provisioned throughput for consistent performance, model selection based on latency requirements, and cross-region inference for global applications.

Core docs

Streaming responses — reduce time to first token
Provisioned throughput — consistent latency for production workloads
Cross-region inference — automatic routing for global availability
Model selection — smaller models for lower latency

13.2 Scaling patterns ★★ Important

Know how to scale generative AI applications: Lambda concurrency settings, provisioned concurrency for Lambda, API Gateway throttling, AWS Auto Scaling for EC2/ECS, and queue-based architectures with SQS for handling bursts.

Core docs

Lambda concurrency — reserved vs unreserved concurrency limits
Provisioned concurrency — eliminate cold starts
API Gateway throttling — rate limiting and burst control
AWS Auto Scaling — dynamic capacity adjustment
SQS for decoupling — queue-based architecture for burst handling

Chapter 14 — Monitoring and observability

Maps to Task Statement 4.3 — Monitor and troubleshoot generative AI applications

Knowledge of:

CloudWatch metrics for Bedrock
Logging and tracing options
Dashboard and alerting configurations
Performance monitoring strategies

Skills in:

Setting up CloudWatch monitoring for Bedrock
Implementing distributed tracing with X-Ray
Creating dashboards for GenAI metrics
Configuring alarms and notifications

14.1 CloudWatch metrics for Bedrock ★★ Important

Know the key CloudWatch metrics for Bedrock: invocation count, latency, throttling, errors. Understand how to create dashboards and alarms for monitoring generative AI applications.

Core docs

Monitoring Bedrock with CloudWatch — metrics and logging overview
Bedrock metrics — invocation count, latency, throttling, errors
CloudWatch alarms — alerting on metric thresholds
CloudWatch dashboards — visualise GenAI application health

14.2 Distributed tracing ★ Light

Know how to trace requests through generative AI applications using X-Ray. Understand segments, subsegments, and how to instrument Lambda functions and API Gateway.

Core docs

AWS X-Ray — distributed tracing for GenAI pipelines
X-Ray with Lambda — trace Lambda execution time
X-Ray with API Gateway — end-to-end request tracing

Part V — Domain 5: Testing, Validation, and Troubleshooting (11%)

Testing strategies, validation, and debugging generative AI applications.

Chapter 15 — Testing generative AI applications

Maps to Task Statement 5.1 — Test and validate generative AI applications

Knowledge of:

Testing strategies for GenAI applications
Evaluation metrics and benchmarks
A/B testing approaches
Automated testing frameworks

Skills in:

Designing test cases for GenAI outputs
Implementing automatic evaluation
Setting up human evaluation workflows
Creating golden datasets for validation

15.1 Testing strategies ★★ Important

Know testing approaches for generative AI: unit testing for application logic, integration testing for API calls, evaluation testing for model outputs (using golden datasets), A/B testing for comparing models/prompts, and load testing for performance validation.

Core docs

Model evaluation — compare models with evaluation jobs
Testing prompt flows — validate flow behaviour
Testing agents — debug agent reasoning and actions
Testing guardrails — verify content filtering

15.2 Evaluation metrics ★★ Important

Know the evaluation metrics for generative AI: ROUGE (summarization), BERTScore (semantic similarity), accuracy (classification), human evaluation ratings. Understand when to use automatic vs human evaluation.

Core docs

Evaluation metrics — ROUGE, BERTScore, accuracy definitions
Automatic evaluation — programmatic quality assessment
Human evaluation — subjective quality ratings

Chapter 16 — Troubleshooting

Maps to Task Statement 5.2 — Troubleshoot generative AI applications

Knowledge of:

Common issues and error patterns
Debugging techniques and tools
Log analysis methods
Performance bottleneck identification

Skills in:

Diagnosing throttling and quota issues
Debugging prompt and output quality problems
Analyzing model invocation logs
Troubleshooting agent and knowledge base issues

16.1 Common issues and solutions ★★ Important

Know how to diagnose and fix common issues: throttling (increase provisioned throughput or implement backoff), poor output quality (prompt engineering, model selection), high latency (streaming, caching), knowledge base retrieval issues (chunking, metadata), and agent failures (action group configuration).

Core docs

Troubleshooting Bedrock — common issues and solutions
Knowledge base troubleshooting — sync, retrieval, and query issues
Agent troubleshooting — action group and reasoning failures
Error handling — API error codes and meanings

16.2 Debugging techniques ★ Light

Know debugging approaches: enabling verbose logging, using model invocation logging to inspect inputs/outputs, tracing agent reasoning steps, and using CloudWatch Logs Insights for analysis.

Core docs

Model invocation logging — inspect prompts and responses
Agent trace — step-by-step agent reasoning
CloudWatch Logs Insights — query and analyse log data

Chapter 17 — Supporting services

Additional AWS services commonly used with generative AI applications.

17.1 Amazon SageMaker ★★ Important

Know when to use SageMaker vs Bedrock. Understand SageMaker JumpStart for deploying foundation models, SageMaker endpoints for custom model hosting, and SageMaker Clarify for bias detection.

Core docs

Amazon SageMaker — build, train, and deploy ML models
SageMaker JumpStart — pre-trained FMs and quick deployment
SageMaker endpoints — host custom models for inference
SageMaker Clarify — bias detection and model explainability

FAQ

Amazon SageMaker FAQ — pricing, supported frameworks, deployment options

17.2 Amazon Kendra ★ Light

Know Amazon Kendra as an enterprise search service that can be used for RAG. Understand when to use Kendra vs Bedrock Knowledge Bases.

Core docs

What is Amazon Kendra? — intelligent enterprise search service
Kendra data sources — supported connectors and configuration
Kendra with Bedrock — RAG with Kendra as retriever

FAQ

Amazon Kendra FAQ — pricing, document types, language support

17.3 Amazon Comprehend ★ Light

Know Amazon Comprehend for NLP tasks: sentiment analysis, entity recognition, language detection, and PII detection. Understand when to use Comprehend vs foundation models.

Core docs

What is Amazon Comprehend? — NLP service for text analysis
Sentiment analysis — positive, negative, neutral, mixed
Entity recognition — extract people, places, organisations
PII detection — identify personal information in text

FAQ

Amazon Comprehend FAQ — supported languages, custom models

17.4 Amazon Textract and Rekognition ★ Light

Know these services for multimodal AI applications. Textract extracts text from documents (forms, tables). Rekognition provides image and video analysis (object detection, facial analysis, content moderation).

Core docs

Amazon Textract — extract text, tables, forms from documents
Amazon Rekognition — image and video analysis, content moderation

FAQ

Amazon Textract FAQ — supported formats, accuracy, pricing
Amazon Rekognition FAQ — face detection, custom labels, video analysis

17.5 Amazon Q Developer ★ Light

Know Amazon Q Developer for AI-powered coding assistance. Understand code generation, code explanation, debugging assistance, and security scanning capabilities.

Core docs

What is Amazon Q Developer? — AI coding assistant for IDEs and CLI
Code generation — context-aware code completions
Security scanning — identify vulnerabilities in code

FAQ

Amazon Q Developer FAQ — supported languages, IDE integrations

17.6 Amazon Transcribe ★ Light

Know Amazon Transcribe for speech-to-text conversion. Understand real-time vs batch transcription, custom vocabularies, and integration with generative AI for voice-enabled applications.

Core docs

What is Amazon Transcribe? — speech-to-text conversion
Real-time transcription — live audio to text
Custom vocabularies — improve accuracy for domain terms

FAQ

Amazon Transcribe FAQ — languages, accuracy, medical transcription

17.7 Amazon Augmented AI (A2I) ★ Light

Know A2I for human-in-the-loop workflows. Understand when to use human review for AI predictions, creating human review workflows, and integrating with Bedrock for quality assurance.

Core docs

What is Amazon A2I? — human review for ML predictions
Creating human review workflows — configure review triggers and routing
Human review UI — customise reviewer interface

Chapter 18 — Data and analytics services

Supporting services for data processing and analytics in GenAI applications.

18.1 AWS Glue ★ Light

Know AWS Glue for ETL and data preparation. Understand Glue Data Catalog for metadata management, Glue crawlers for schema discovery, and Glue jobs for data transformation before ingestion into knowledge bases.

Core docs

What is AWS Glue? — serverless data integration and ETL
Glue Data Catalog — metadata repository for data assets
Glue ETL jobs — transform data for AI workloads
Glue crawlers — auto-discover schema from data

FAQ

AWS Glue FAQ — pricing, supported sources, Spark version

18.2 Amazon Athena ★ Light

Know Athena for serverless SQL queries on S3 data. Useful for analyzing model invocation logs, querying data lakes, and preparing data for RAG applications.

Core docs

What is Amazon Athena? — serverless SQL queries on S3
Querying data — analyse logs and prepare RAG data
Athena with Glue Data Catalog — shared metadata for tables

FAQ

Amazon Athena FAQ — pricing model, supported formats

18.3 Amazon Kinesis ★ Light

Know Kinesis for real-time data streaming. Understand Kinesis Data Streams for real-time ingestion, Kinesis Data Firehose for delivery to destinations, and use cases like real-time inference pipelines.

Core docs

Amazon Kinesis Data Streams — real-time data ingestion
Amazon Kinesis Data Firehose — load streaming data to destinations
Kinesis with Lambda — process streams with Lambda

FAQ

Amazon Kinesis FAQ — throughput, retention, scaling

18.4 Amazon EMR ★ Light

Know EMR for big data processing. Understand EMR for large-scale data preparation, distributed training data processing, and integration with SageMaker.

Core docs

What is Amazon EMR? — managed big data processing
EMR with Spark — large-scale data transformation

FAQ

Amazon EMR FAQ — instance types, pricing, supported frameworks

18.5 Amazon QuickSight ★ Light

Know QuickSight for business intelligence. Understand QuickSight Q for natural language queries and how to visualize GenAI application metrics.

Core docs

What is Amazon QuickSight? — serverless BI and visualisation
QuickSight Q — natural language queries on dashboards

FAQ

Amazon QuickSight FAQ — pricing, data sources, embedding

18.6 Amazon MSK ★ Light

Know Amazon MSK (Managed Streaming for Apache Kafka) for event streaming. Understand when to use MSK vs Kinesis for GenAI data pipelines.

Core docs

What is Amazon MSK? — managed Apache Kafka
MSK vs Kinesis — when to use each service

FAQ

Amazon MSK FAQ — Kafka versions, scaling, pricing

Chapter 19 — Application integration services

Services for building event-driven and workflow-based GenAI applications.

19.1 AWS Step Functions ★★ Important

Know Step Functions for orchestrating GenAI workflows. Understand state machines, integration with Bedrock, error handling with Retry/Catch, and the difference between Standard and Express workflows.

Core docs

What is AWS Step Functions? — serverless workflow orchestration
Step Functions with Bedrock — native Bedrock integration
Standard vs Express workflows — long-running vs high-volume
Error handling — Retry, Catch, fallback patterns

FAQ

AWS Step Functions FAQ — pricing, state limits, integrations

19.2 Amazon EventBridge ★ Light

Know EventBridge for event-driven architectures. Understand event buses, rules, targets, and how to trigger GenAI workflows based on events.

Core docs

What is Amazon EventBridge? — serverless event bus
Event patterns — filter and route events
Rules and targets — trigger GenAI workflows from events

FAQ

Amazon EventBridge FAQ — event size, delivery guarantees

Know SNS for pub/sub messaging and SQS for queue-based decoupling. Understand fan-out patterns, dead-letter queues, and how to build resilient GenAI pipelines.

Core docs

Amazon SNS — pub/sub messaging and notifications
Amazon SQS — message queuing for decoupling
SNS to SQS fanout — broadcast to multiple queues
SQS dead-letter queues — handle failed messages

FAQ

Amazon SNS FAQ — delivery, filtering, pricing
Amazon SQS FAQ — visibility timeout, message retention

19.4 Amazon AppFlow ★ Light

Know AppFlow for SaaS data integration. Understand how to bring data from Salesforce, ServiceNow, Slack, etc. into S3 for use with Bedrock Knowledge Bases.

Core docs

What is Amazon AppFlow? — SaaS data integration
Supported sources — Salesforce, ServiceNow, Slack connectors
Creating flows — configure data transfers to S3

FAQ

Amazon AppFlow FAQ — connectors, scheduling, data transformation

19.5 AWS AppConfig ★ Light

Know AppConfig for feature flags and dynamic configuration. Understand deployment strategies and how to use AppConfig for A/B testing prompt variations.

Core docs

What is AWS AppConfig? — dynamic configuration management
Feature flags — toggle features without deploys
Deployment strategies — gradual rollouts, A/B testing prompts

Chapter 20 — Compute and container services

Compute options for hosting GenAI applications.

20.1 AWS Lambda ★★ Important

Lambda is the primary compute for serverless GenAI. Know function configuration, environment variables, layers, VPC access, and integration with Bedrock. Understand timeout and memory settings for GenAI workloads.

Core docs

AWS Lambda — serverless compute for GenAI backends
Lambda with Bedrock — invoke models from Lambda
Lambda environment variables — store configuration securely
Lambda VPC access — private network connectivity
Response streaming — stream large responses

FAQ

AWS Lambda FAQ — timeout limits, memory, pricing

20.2 Amazon EC2 ★ Light

Know EC2 for GenAI workloads requiring GPUs or sustained compute. Understand instance types (GPU instances like P4d, G5), Spot instances for cost optimization, and when to use EC2 vs serverless.

Core docs

Amazon EC2 — virtual servers for sustained workloads
GPU instances — P4d, G5 for model inference
Spot instances — cost savings up to 90%

FAQ

Amazon EC2 FAQ — instance types, pricing, networking

20.3 Container services (ECS, EKS, Fargate) ★ Light

Know container options for GenAI applications. Understand ECS vs EKS, Fargate for serverless containers, ECR for image storage, and when containers make sense vs Lambda.

Core docs

Amazon ECS — managed container orchestration
Amazon EKS — managed Kubernetes
AWS Fargate — serverless containers
Amazon ECR — container image registry

FAQ

Amazon ECS FAQ — task definitions, networking modes
Amazon EKS FAQ — Kubernetes versions, add-ons

20.4 AWS App Runner ★ Light

Know App Runner for fully managed container deployments. Understand when to use App Runner for simple GenAI APIs without managing infrastructure.

Core docs

What is AWS App Runner? — fully managed container deployment
Creating services — deploy from source or image

FAQ

AWS App Runner FAQ — auto-scaling, custom domains

Chapter 21 — Database services

Database options for GenAI applications.

21.1 Amazon DynamoDB ★★ Important

Know DynamoDB for GenAI application state management. Understand table design, DynamoDB Streams for change capture (triggering GenAI workflows), and session storage for conversational AI.

Core docs

Amazon DynamoDB — serverless NoSQL for session state
DynamoDB Streams — trigger GenAI on data changes
Best practices — key design, indexing patterns

FAQ

Amazon DynamoDB FAQ — pricing, consistency, transactions

21.2 Amazon ElastiCache ★ Light

Know ElastiCache for caching GenAI responses. Understand Redis for semantic caching, session management, and reducing Bedrock API costs through response caching.

Core docs

Amazon ElastiCache — in-memory caching for responses
ElastiCache for Redis — semantic caching, session storage
Caching strategies — reduce Bedrock API costs

FAQ

Amazon ElastiCache FAQ — node types, replication, pricing

21.3 Amazon DocumentDB ★ Light

Know DocumentDB for document storage. Understand DocumentDB vector search capabilities for RAG applications as an alternative to OpenSearch.

Core docs

Amazon DocumentDB — MongoDB-compatible document database
Vector search — alternative to OpenSearch for RAG

FAQ

Amazon DocumentDB FAQ — MongoDB compatibility, scaling

Chapter 22 — Developer tools and CI/CD

Tools for building, deploying, and managing GenAI applications.

22.1 AWS CloudFormation and CDK ★ Light

Know CloudFormation for infrastructure as code. Understand CDK for defining infrastructure in programming languages and deploying Bedrock resources.

Core docs

AWS CloudFormation — infrastructure as code
AWS CDK — define infrastructure in code
Bedrock CloudFormation resources — agents, knowledge bases, guardrails

FAQ

AWS CloudFormation FAQ — stack limits, drift detection
AWS CDK FAQ — supported languages, versioning

22.2 CI/CD services (CodePipeline, CodeBuild, CodeDeploy) ★ Light

Know AWS CI/CD services for deploying GenAI applications. Understand CodePipeline for orchestration, CodeBuild for building artifacts, and CodeDeploy for deployment strategies.

Core docs

AWS CodePipeline — continuous delivery orchestration
AWS CodeBuild — build and test automation
AWS CodeDeploy — deployment automation
AWS CodeArtifact — artifact repository

FAQ

AWS CodePipeline FAQ — triggers, actions, integrations
AWS CodeBuild FAQ — build environments, caching

22.3 AWS Amplify ★ Light

Know Amplify for full-stack GenAI applications. Understand Amplify AI kit for integrating Bedrock into web and mobile applications.

Core docs

AWS Amplify — full-stack web and mobile apps
Amplify AI kit — integrate Bedrock into Amplify apps

FAQ

AWS Amplify FAQ — hosting, authentication, data

Chapter 23 — Networking services

Networking for GenAI applications.

23.1 Amazon CloudFront ★ Light

Know CloudFront for caching and global distribution. Understand CloudFront Functions for edge processing and integration with GenAI APIs.

Core docs

Amazon CloudFront — global content delivery network
CloudFront Functions — edge compute for request handling

FAQ

Amazon CloudFront FAQ — caching, pricing, origins

23.2 Elastic Load Balancing and Global Accelerator ★ Light

Know ELB for distributing traffic to GenAI backends. Understand Global Accelerator for improved global performance and availability.

Core docs

Elastic Load Balancing — distribute traffic across backends
AWS Global Accelerator — improved global performance

FAQ

ELB FAQ — ALB vs NLB, target groups
Global Accelerator FAQ — anycast IPs, failover

23.3 Amazon Route 53 ★ Light

Know Route 53 for DNS management. Understand routing policies and health checks for high-availability GenAI applications.

Core docs

Amazon Route 53 — DNS management and traffic routing
Routing policies — weighted, latency-based, geolocation

FAQ

Amazon Route 53 FAQ — health checks, domain registration

Chapter 24 — Security services

Additional security services for GenAI applications.

24.1 Amazon Cognito ★★ Important

Know Cognito for user authentication in GenAI applications. Understand user pools, identity pools, and token-based authentication for API Gateway and Bedrock access.

Core docs

Amazon Cognito — user authentication for GenAI apps
User pools — user directory and sign-up/sign-in
Identity pools — temporary AWS credentials for users

FAQ

Amazon Cognito FAQ — pricing, MFA, federation

24.2 AWS Secrets Manager ★ Light

Know Secrets Manager for storing API keys and credentials used in GenAI applications. Understand automatic rotation and integration with Lambda.

Core docs

AWS Secrets Manager — store API keys and credentials securely
Automatic rotation — rotate secrets without downtime

FAQ

AWS Secrets Manager FAQ — pricing, Lambda integration

24.3 AWS WAF ★ Light

Know WAF for protecting GenAI APIs from attacks. Understand rate limiting, managed rules, and integration with API Gateway.

Core docs

AWS WAF — web application firewall
Rate-based rules — protect against abuse
WAF with API Gateway — protect GenAI APIs

FAQ

AWS WAF FAQ — managed rules, pricing, logging

24.4 Amazon Macie ★ Light

Know Macie for discovering and protecting sensitive data. Understand how to use Macie to identify PII in S3 buckets used for RAG knowledge bases.

Core docs

Amazon Macie — discover PII in S3 knowledge bases
Discovering sensitive data — automated sensitive data detection

FAQ

Amazon Macie FAQ — supported data types, pricing

24.5 AWS Encryption SDK ★ Light

Know the Encryption SDK for client-side encryption. Understand envelope encryption and when to use client-side encryption for sensitive GenAI data.

Core docs

AWS Encryption SDK — client-side encryption library
How it works — envelope encryption with KMS

Chapter 25 — Storage services

Storage options for GenAI data.

25.1 Amazon S3 ★★ Important

S3 is the primary storage for GenAI data. Know bucket policies, encryption, lifecycle policies, and S3 as a data source for Bedrock Knowledge Bases.

Core docs

Amazon S3 — primary storage for GenAI data
Bucket policies — access control for knowledge base data
Encryption — SSE-S3, SSE-KMS, SSE-C options
Lifecycle policies — manage data retention and archival
S3 Intelligent-Tiering — automatic cost optimisation

FAQ

Amazon S3 FAQ — pricing, storage classes, durability

25.2 Amazon EBS and EFS ★ Light

Know EBS for EC2 block storage and EFS for shared file storage. Understand when to use these for GenAI workloads (model weights, training data).

Core docs

Amazon EBS — block storage for EC2 model hosting
Amazon EFS — shared file storage for model weights

FAQ

Amazon EBS FAQ — volume types, IOPS, snapshots
Amazon EFS FAQ — throughput modes, pricing

Chapter 26 — Management and governance

Operational services for GenAI applications.

26.1 AWS Systems Manager ★ Light

Know Systems Manager for operational management. Understand Parameter Store for configuration, Run Command for fleet management, and Session Manager for secure access.

Core docs

AWS Systems Manager — operational management
Parameter Store — configuration and secrets (simpler than Secrets Manager)

FAQ

AWS Systems Manager FAQ — capabilities, pricing

26.2 AWS Cost Explorer and Budgets ★ Light

Know Cost Explorer for analyzing GenAI costs. Understand cost allocation tags, budgets, and alerts for managing Bedrock spending.

Core docs

AWS Cost Explorer — analyse and visualise Bedrock costs
AWS Budgets — set alerts for GenAI spending
Cost allocation tags — track costs by project or team

26.3 Amazon Managed Grafana ★ Light

Know Managed Grafana for advanced visualization of GenAI metrics. Understand dashboards and integration with CloudWatch.

Core docs

Amazon Managed Grafana — advanced visualisation for GenAI metrics
Data sources — connect CloudWatch, Prometheus, etc.

FAQ

Amazon Managed Grafana FAQ — pricing, authentication, plugins

26.4 AWS Chatbot ★ Light

Know AWS Chatbot for integrating AWS notifications with Slack and Teams. Useful for GenAI application alerting and operational awareness.

Core docs

AWS Chatbot — AWS notifications in Slack/Teams
Setting up Chatbot — configure channels and permissions

FAQ

AWS Chatbot FAQ — supported services, pricing