PRODUCTION SCENARIO
A retailer runs one chatbot on Google Cloud and another on a different cloud. Security wants both to block prompt injection, stop responses that leak personal data, and record which filters fired, without rewriting either application.
Which Google Cloud service meets this?
Answering here is anonymous. Nothing is saved unless you sign in.
Show answer and explanation
Answer: Model Armor, which screens both prompts and responses for a range of risks
Model Armor screens LLM prompts and responses for prompt injection and jailbreak attempts and for sensitive data, returns which filters triggered and which did not, and works on Google Cloud or another provider. Gemini's configurable filters cover Gemini's own responses only, IAM governs who may call a resource rather than what a prompt contains, and AI Protection manages security posture instead of screening requests.
Official Source: https://docs.cloud.google.com/model-armor/overview ↗