1AWS AI Practitioner Complete Study Guide 2026-2027
705.7 Content Generation Applications
2Preface
715.8 Intelligent Search and Question Answering
3Chapter 1.0: Exam Strategy and Overview
725.9 Case Study: Enterprise Knowledge Management
41.1 Understanding the Exam Format
735.10 Prompt Engineering Techniques
51.2 The Five Domain Breakdown
745.11 Measuring Application Performance
61.3 Question Types Explained
755.12 Chapter Summary
71.4 Target Candidate Profile
765.13 Practice Questions
81.5 Case Study: Career Transition Success
77Chapter 6.0: Guidelines for Responsible AI
91.6 Creating Your Study Timeline
786.1 Understanding Bias in AI Systems
101.7 Study Strategies That Work
796.2 Detecting and Measuring Bias
111.8 Using This Book Effectively
806.3 Mitigating Bias
121.9 Test-Taking Strategies
816.4 Case Study: Hiring Recommendation System
131.10 Common Mistakes to Avoid
826.5 Explainability and Interpretability
141.12 Managing Exam Day
836.6 When Explainability Matters Most
151.13 After the Exam
846.7 Privacy and Data Protection
161.14 Chapter Summary
856.8 Case Study: Healthcare Analytics Platform
171.15 Practice Questions: Exam Orientation and Strategy
866.9 Safety and Security
18Chapter 2.0: AI and Machine Learning Fundamentals
876.10 Human Oversight and Control
192.1 Defining AI and Machine Learning
886.11 Accountability and Governance
202.2 Types of Machine Learning
896.12 Environmental Considerations
212.3 Common ML Algorithms
906.13 AWS Services Supporting Responsible AI
222.4 The ML Development Lifecycle
916.14 Chapter Summary
232.5 Key Concepts Explained
926.15 Practice Questions
242.6 Evaluation Metrics Explained
93Chapter 7.0: Security Compliance and Governance
252.7 Case Study: Medical Diagnosis System
947.1 Shared Responsibility Model
262.8 Overfitting and Underfitting
957.2 Data Protection Fundamentals
272.9 Transfer Learning and Pre-Trained Models
967.3 PII and Sensitive Data
282.10 Practical AI Use Cases
977.4 Access Control and Identity
292.11 AWS Services Introduction
987.5 Case Study: Healthcare AI Platform
302.12 Case Study: Retail Demand Forecasting
997.6 Governance and Compliance
312.13 Chapter Summary
1007.7 Monitoring and Observability
322.14 Practice Questions:
1017.8 Data Lineage and Provenance
33Chapter 3.0: Generative AI Fundamentals
1027.9 Case Study: Financial Services Fraud Detection
343.1 What Is Generative AI
1037.10 Algorithm Accountability and Regulations
353.2 Foundation Models Explained
1047.11 Chapter Summary
363.3 Model Architectures for Generation
1057.12 Practice Questions
373.4 Tokenization and Embeddings
106Chapter 8.0: Infrastructure and Architecture Patterns
383.5 Foundation Model Lifecycle
1078.1 Compute Options Overview
393.6 Parameters and Hyperparameters
1088.2 EC2 Instances for ML
403.7 Case Study: Content Generation Platform
1098.3 AWS Purpose Built Chips
413.8 Context Windows and Limitations
1108.4 SageMaker Managed Infrastructure
423.9 Capabilities of Generative AI
1118.5 Case Study: Media Processing Pipeline
433.10 Limitations and Challenges
1128.6 Storage Architecture
443.11 Case Study: Customer Service Automation
1138.7 Networking and Integration
453.12 Practical Use Cases
1148.8 Case Study: Real Time Recommendation Engine
463.13 Chapter Summary
1158.9 Cost Optimization Strategies
473.14 Practice Questions
1168.10 Chapter Summary
48Chapter 4.0: AWS AI Services Overview
1178.11 Practice Questions
494.1 AWS AI Service Categories
118Chapter 9.0: Real World Decision Making
504.2 Amazon SageMaker Ecosystem
1199.1 Decision Framework Foundations
514.3 Amazon Bedrock Platform
1209.2 Industry Use Cases
524.4 Case Study: Healthcare Document Analysis
1219.3 Case Study: Healthcare Clinical Decision Support
534.5 Conversational AI with Amazon Lex
1229.4 Bedrock versus SageMaker Decisions
544.6 Intelligent Search with Amazon Kendra
1239.5 Pre-Trained versus Custom Models
554.7 Personalization and Recommendations
1249.6 Case Study: Retail Fraud Detection
564.8 Case Study: Retail Product Recommendations
1259.7 RAG Implementation Patterns
574.9 Forecasting with Amazon Forecast
1269.8 Migration from Traditional ML
584.10 Language AI Services
1279.9 Build versus Buy Decisions
594.11 Vision AI Services
1289.10 Case Study: Manufacturing Quality Control
604.12 Service Selection Criteria
1299.11 Scalability and Performance Considerations
614.13 Chapter Summary
1309.12 Chapter Summary
624.14 Practice Questions
1319.13 Practice Questions
63Chapter 5.0: Applications of Foundation Models
132Chapter 10.0: Full Practice Exams
645.1 Retrieval Augmented Generation
13310.1 Exam Taking Strategy
655.2 Prompt Engineering Fundamentals
13410.2 Practice Exam 1
665.3 Case Study: Legal Document Analysis
13510.3 Practice Exam 2
675.4 Fine-Tuning Foundation Models
13610.4 Quick Reference Materials
685.5 Agent Architectures and Workflows
13710.5 Final Review
695.6 Case Study: Customer Service Agent
13810.6 Closing Thoughts
