Azure AI Content Safety

Content Safety in Foundry Control Plane (Azure AI Content Safety) enhances the safety of generative AI applications with guardrails: it detects and blocks violence, hate, sexual and self-harm content with configurable severity thresholds; supports custom content filter categories; safeguards against prompt injection and jailbreak attempts via prompt shields; detects and corrects generative AI hallucinations via groundedness detection; and identifies protected/copyrighted material in outputs.