AWS Certified Generative AI Developer - Professional (AIP-C01) Exam Guide Flashcards

Vocabulary flashcards covering core concepts, exam structure, domain weightings, and key technologies from the AWS Certified Generative AI Developer - Professional (AIP-C01) Exam Guide.

Target Candidate Experience (AIP-C01)

Target candidates require $2$ or more years of experience building production-grade applications on AWS or with open-source technologies, general AI/ML or data engineering experience, and $1$ year of hands-on experience implementing GenAI solutions.

Content Domain 1: Foundation Model Integration, Data Management, and Compliance

Represents $31$% of the scored content on the AIP-C01 exam, covering solution design, FM selection and configuration, data processing pipelines, vector stores, retrieval mechanisms, and prompt engineering strategies.

Content Domain 2: Implementation and Integration

Represents $26$% of the scored content on the AIP-C01 exam, focusing on agentic AI solutions, model deployment strategies, enterprise integration architectures, FM API integrations, and development tools.

Content Domain 3: AI Safety, Security, and Governance

Represents $20$% of the scored content on the AIP-C01 exam, covering input and output safety controls, data security and privacy, AI governance and compliance mechanisms, and responsible AI principles.

Content Domain 4: Operational Efficiency and Optimization for GenAI Applications

Represents $12$% of the scored content on the AIP-C01 exam, focusing on cost optimization, resource efficiency strategies, application performance, and monitoring systems.

Content Domain 5: Testing, Validation, and Troubleshooting

Represents $11$% of the scored content on the AIP-C01 exam, focusing on evaluation systems and troubleshooting GenAI applications.

AIP-C01 Exam Scoring Model

A compensatory scoring model evaluating $65$ scored questions and $10$ unscored questions, reporting scaled scores from $100$ to $1,000$ with a minimum passing score of $750$.

Out-of-Scope Candidate Tasks (AIP-C01)

Job tasks excluded from the target candidate scope, including model development and training, advanced ML techniques, and data engineering and feature engineering.

Model Context Protocol (MCP)

A client-server protocol used for agent-tool interactions and vector queries, implemented using stateless MCP servers on AWS Lambda or complex tools on Amazon ECS.

ReAct Pattern

A structured reasoning approach used in agentic AI solutions to give FMs the ability to break down and solve complex problems, orchestrated using AWS Step Functions.

Low-Rank Adaptation (LoRA)

A parameter-efficient adaptation technique used for foundation model customization and deployment.

Amazon Bedrock Cross-Region Inference

An AWS feature used to design resilient AI systems and ensure continuous operation during service disruptions for models with limited regional availability.

AWS Well-Architected Tool Generative AI Lens

A tool used to create standardized technical components to ensure consistent implementation across multiple deployment scenarios.

Amazon Bedrock Prompt Flows

A tool used to design complex prompt systems, manage sequential prompt chains, handle conditional branching, and conduct systematic A/B testing.

Strands Agents and AWS Agent Squad

AWS native tools and frameworks used to develop intelligent autonomous multi-agent systems with memory and state management capabilities.

LLM-as-a-Judge

An automated evaluation technique using foundation models to perform model evaluations and quality assessments for GenAI outputs.

AWS Service Abbreviations Policy (AIP-C01)

Certain official AWS service names include abbreviations that are never expanded (for example, Amazon API Gateway, Amazon EMR); official short names are accessible via the exam Help feature.