QuestionQ62

VerifiedSecuring and governing agentic workflows

You are deploying an enterprise conversational agent in Google Cloud that connects to sensitive human resources (HR) databases. Your organization’s compliance policy requires all user queries and model completions to be filtered in real time to prevent prompt injection attacks, block harmful content, and sanitize personally identifiable information (PII) before responses reach the user interface. You need to implement a managed security enforcement layer that meets these requirements with minimal latency.

What should you do?

Explanation

Agent Gateway can centrally apply Model Armor filters to supported client requests and agent responses, blocking prompt injection and harmful content. Advanced Sensitive Data Protection settings link inspection and de-identification templates to sanitize matching PII. Configure the Model Armor template with INSPECT_AND_BLOCK enforcement: PII-only violations are redacted, while payloads that also violate other detectors are blocked. Gateway coverage depends on the traffic and methods supported by the integration. (docs.cloud.google.com)

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!