Domain 5·14% of exam·27 concepts
Governance, Safety & Risk Management
Put guardrails and human-in-the-loop controls around Claude systems, identify LLM risks and failure modes, ensure regulatory compliance, and address ethical AI considerations.
Official prep for this domain
Anthropic's own free prep module for this part of the syllabus, on the official prep course. Free with an Anthropic Academy sign-in.
5.1
Implement guardrails and safety controls
- ccarp-5.1.1Training-Time Alignment vs Inference-Time Control
- ccarp-5.1.2The Three-Point Guarded Request Path
- ccarp-5.1.3Model-Based vs Deterministic Check Selection
- ccarp-5.1.4Fail-Open vs Fail-Closed Design
- ccarp-5.1.5Indirect Injection via Retrieved Content and Tool Output
- ccarp-5.1.6Skill Supply-Chain Auditing
5.2
Identify risks, limitations, and failure modes of LLM systems
5.3
Apply human-in-the-loop validation strategies
5.4
Ensure compliance with regulations (e.g., GDPR, HIPAA, FedRAMP)
5.5