AWS Certified AI Practitioner

Explore Fundamentals of AI and ML

Explain Basic AI Concepts and Terminologies

• Machine Learning Fundamentals and Risks
• Agentic AI Concepts and Multi-Agent Systems

Identify Practical Use Cases for AI

• Generative AI Applications and Output Types
• Chatbots and Customer Support Applications
• Content Creation and Personalization Strategies
• Prototyping and Innovation in Generative AI
• Creative Applications and Semantic Search
• Speech and Language Processing Services
• Computer Vision and Image Analysis Services
• Personalization and Recommendation Engines
• Anomaly Detection and Monitoring Services

Describe the AI/ML Development Lifecycle

• AI Training and Model Parameters
• Data Preparation and Pilot Development
• Lifecycle Phases and Process Management
• Stage Gates and Feedback Mechanisms
• Scoping and Key Performance Indicators
• Model Customization and Deployment Strategies
• Deployment Patterns and Options
• Deployment Patterns and CI/CD Practices
• Monitoring and Drift Management Strategies
• AI Development Tools and Lifecycle Services

Explore Fundamentals of GenAI

Explain the Basic Concepts of Generative AI (GenAI)

• Generative AI Core Concepts and Terminology
• Generative Models and Vector Representations
• Foundation Model Providers and Instruction Tuning
• Model Families and Versioning
• Domain-Specific and Specialized Models
• Model Architectures and Trade-Offs
• Open Models and Size Considerations
• Generative Architectures and Weight Management
• Context Engineering for FM Applications
• Model Context Protocol and Agent Connectivity

Understand the Capabilities and Limitations of GenAI for Solving Business Problems

• Training Techniques and Model Limitations
• High-Stakes Use Cases and Legal Considerations
• Evaluating Use Cases and ROI for Generative AI

Describe AWS Infrastructure and Technologies for Building GenAI Applications

• Agent API Schemas and Tool Integration
• Agent Memory and State Management
• Agent Tracing and Robustness
• Tool Orchestration and Function Calling
• Observability and Error Handling in Agents
• AI Assistants and SageMaker Tools
• Model Lineage and Experiment Tracking
• Centralized Logging and Data Management
• Event-Driven AI Workflows
• Bedrock Services and Model Integration
• Monitoring and Drift Management in AI
• Strands Agents and Agent SDKs
• Amazon Bedrock AgentCore Services

Explore Applications of Foundation Models

Describe Design Considerations for Applications That Use Foundation Models (FMs)

• Foundation Model Selection Criteria
• Language and Modality Considerations
• Task-Specific Model Selection
• Cost and Compliance Considerations
• RAG Benefits and Query Processing
• RAG Architecture and Components
• Knowledge Base Synchronization and Freshness
• RAG Latency and Tuning Considerations
• Prompt Caching and Inference Efficiency

Choose Effective Prompt Engineering Techniques

• Core Elements of Prompt Engineering
• Prompt Types and Techniques
• Prompt Structure and Control
• Iterative Prompt Development
• Prompt Constraints and Specificity
• Prompt Techniques for Desired Outputs
• Output Control and Validation Methods
• Sampling Strategies and Temperature Settings
• System Prompts and Tool Utilization

Describe the Training and Fine-Tuning Process for FMs

• Fine-Tuning and Parameter-Efficient Methods
• Fine-Tuning Risks and Hyperparameters
• Model Customization Techniques

Describe Methods to Evaluate FM Performance

• Model Performance and Experimentation
• Evaluation and Trade-Offs in Model Selection
• Model Evaluation Strategies
• Monitoring and Drift Management
• Retrieval Quality and Trust Metrics
• RAG Suitability and Performance Evaluation
• Data Preparation and Evaluation Techniques
• LLM-as-a-Judge Evaluation
• Business Alignment and Task Completion Metrics

Explore Guidelines for Responsible AI

Explain the Development of AI Systems That Are Responsible

• Ethical Data Practices and Inclusivity
• Fairness, Bias, and Evaluation Techniques
• Privacy, Security, and Human Oversight
• Misuse Prevention and Content Moderation

Recognize the Importance of Transparent and Explainable Models

• Responsible AI Principles and Frameworks

Explore Security, Compliance, and Governance for AI Solutions

Explain Methods to Secure AI Systems

• Bedrock Security and Access Control
• Identity and Access Governance Principles
• Data Protection and Encryption Techniques
• Centralized Logging and Monitoring
• Secure Connectivity and Content Moderation
• Prompt Injection, Guardrails, and Input Validation
• Grounding, Hallucination Detection, and Output Validation
• Data Provenance, Quality, and Source Citation

Recognize Governance and Compliance Regulations for AI Systems

• Governance and Monitoring Practices
• Governance and Compliance in Generative AI
• Project Scoping and Governance Framework
• Decommissioning and Risk Assessment

Explore a topic with sample questions and explanations.