AI World 3 · Agents and Tools · Stage 5

Guard the Agent

A guardrail on the model sees the user and the answer. What comes back from a tool needs its own check.

Guardrails on agents
Tool-boundary checks
ApplyGuardrail

Domain: AI and machine learning
World: AI World 3: Agents and Tools (Associate)
Game type: Solution board: Drop services into each row's slots, then run records through them.
Time: About 25 minutes on a first attempt (estimated)
Exam guides: AIF-C01Task 4.1: Explain the development of AI systems that are responsible; Task 5.1: Explain methods to secure AI systems
MLA-C02Skill 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 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 3.1.4: Create defense-in-depth safety systems to provide comprehensive protection against FM misuse (for example, by using Amazon Comprehend to develop pre-processing filters, Amazon Bedrock to implement model-based guardrails, Lambda functions to perform post-processing validation, API Gateway to implement API response filtering); 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 3.2.3: 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)