AI World 1 · GenAI Foundations · Stage 5

Guard the Gate

Block the jailbreak, deny the topic, mask the PII, ground the answer, enforce it from IAM, and keep the record.

Guardrails
Contextual grounding
Guardrail enforcement
Invocation logs
CloudTrail

Domain: AI and machine learning
World: AI World 1: GenAI Foundations (Associate)
Game type: Evidence desk: Each ticket is the reporter's words: find its cause in the evidence.
Time: About 25 minutes on a first attempt (estimated)
Exam guides: AIF-C01Task 3.2: Choose effective prompt engineering techniques; Task 4.1: Explain the development of AI systems that are responsible; Task 5.1: Explain methods to secure AI systems
MLA-C02Skill 4.3.4: Configure comprehensive monitoring, auditing, compliance, and logging for ML and AI systems (for example, AWS CloudTrail, AWS Config); Skill 4.3.9: Implement safeguards and sensitive data protection to meet application requirements and responsible AI policies (for example, by using Amazon Bedrock Guardrails)
AIP-C01Skill 1.6.1: Create effective model instruction frameworks to control FM behavior and outputs (for example, by using Amazon Bedrock Prompt Management to enforce role definitions, Amazon Bedrock Guardrails to enforce responsible AI guidelines, template configurations to format responses); Skill 3.1.1: Develop comprehensive content safety systems to protect against harmful user inputs to FMs (for example, by using Amazon Bedrock guardrails to filter content, Step Functions and Lambda functions to implement custom moderation workflows, real-time validation mechanisms); Skill 3.1.2: Create content safety frameworks to prevent harmful outputs (for example, by using Amazon Bedrock guardrails to filter responses, specialized FM evaluations for content moderation and toxicity detection); Skill 3.1.3: Develop accuracy verification systems to reduce hallucinations in FM responses (for example, by using Amazon Bedrock Knowledge Base to ground responses and perform fact-checking, confidence scoring and semantic similarity search for verification, JSON Schema to enforce structured outputs); Skill 3.1.5: Implement advanced threat detection to protect against adversarial inputs and security vulnerabilities (for example, by using prompt injection and jailbreak detection mechanisms, input sanitization and content filters, safety classifiers, automated adversarial testing workflows); Skill 3.2.2: Develop privacy-preserving systems to protect sensitive information during FM interactions (for example, by using Amazon Comprehend and Amazon Macie to detect personally identifiable information [PII], Amazon Bedrock native data privacy features, Amazon Bedrock guardrails to filter outputs); Skill 3.2.3: Create privacy-focused AI systems to protect user privacy while maintaining FM utility and effectiveness (for example, by using data masking techniques, Amazon Comprehend PII detection, anonymization strategies for sensitive information, Amazon Bedrock guardrails)