AWS publishes exactly what the AIP-C01 tests and how much each part is worth. Here it is — every domain, its weight, the topics inside it, and the lessons that cover them.
Domain 1
Foundation Model Integration, Data Management, and Compliance
Designing GenAI solutions and choosing foundation models, preparing data for them, vector stores and retrieval for RAG, and prompt engineering and prompt governance. Official weighting 31%.
6 topics in this domain
- Analyze requirements and design GenAI solutions
- Select and configure FMs
- Implement data validation and processing pipelines for FM consumption
- Design and implement vector store solutions
- Design retrieval mechanisms for FM augmentation
- Implement prompt engineering strategies and governance for FM interactions
Domain 2
Implementation and Integration
Agentic AI and tool integration (including MCP), model deployment, enterprise integration and GenAI gateways, Bedrock API patterns (sync, async, streaming, routing, resilience) and developer tooling. Official weighting 26%.
5 topics in this domain
- Implement agentic AI solutions and tool integrations
- Implement model deployment strategies
- Design and implement enterprise integration architectures
- Implement FM API integrations
- Implement application integration patterns and development tools
Domain 3
AI Safety, Security, and Governance
Input and output safety controls and guardrails, prompt-injection defence, data security and privacy (PII), governance, traceability and compliance, and responsible AI. Official weighting 20%.
4 topics in this domain
- Implement input and output safety controls
- Implement data security and privacy controls
- Implement AI governance and compliance mechanisms
- Implement responsible AI principles
Domain 4
Operational Efficiency and Optimization for GenAI Applications
Token and cost efficiency, caching, throughput and latency tuning, inference parameters, and monitoring and observability for GenAI applications. Official weighting 12%.
3 topics in this domain
- Implement cost optimization and resource efficiency strategies
- Optimize application performance
- Implement monitoring systems for GenAI applications
Domain 5
Testing, Validation, and Troubleshooting
Evaluating FM output, RAG and agents (including LLM-as-a-judge and Bedrock evaluations), quality gates for deployments, and troubleshooting context, API, prompt and retrieval problems. Official weighting 11%.
3 topics in this domain
- Implement evaluation systems for GenAI: output quality, model comparison and quality gates
- Implement evaluation systems for GenAI: RAG, retrieval and agent evaluation
- Troubleshoot GenAI applications