Option C is the correct solution because Amazon Bedrock guardrails are purpose-built to enforce defense-in- depth safety controls for GenAI applications with minimal operational overhead. Guardrails provide managed, policy-based enforcement that operates before prompts are sent to the foundation model and after responses are generated, which directly satisfies the requirement that PII must not be sent to the model and must not appear in outputs. By configuring a sensitive information policy, the application can automatically detect and redact PII in user inputs and model responses without building custom preprocessing pipelines. This approach is more reliable and scalable than regex or prompt engineering techniques, which are brittle and error-prone for sensitive data handling. The topic policy capability in Amazon Bedrock guardrails allows the bank to explicitly block investment advice topics, ensuring regulatory compliance. This policy-based approach is safer and more auditable than attempting to steer the model only through prompt instructions. Using the Converse API enables structured, standardized interactions with the model and supports consistent logging of requests and responses. Enabling delivery logging and image logging to Amazon S3 ensures that all customer interactions, including documents and images, are captured in a durable, auditable storage layer. This directly supports compliance, regulatory audits, and forensic analysis. Option A incorrectly relies on Amazon Macie, which is designed for data-at-rest discovery rather than real- time conversational filtering. Option B introduces custom Lambda pipelines and topic modeling, increasing operational complexity. Option D relies on regex and prompt engineering, which do not meet financial-grade compliance standards. Therefore, Option C delivers the strongest security, governance, and auditability with the least operational effort.