Service that detects and filters harmful content (hate, violence, sexual content, self-harm) in both text and images, whether generated by users or by AI models, returning configurable severity levels.
In AI-901 it's used both to moderate user-generated content and to filter a generative model's outputs. It integrates natively as Content Filtering in Azure OpenAI deployments. Question: automatically block chatbot responses containing violent content → Content Safety.
Azure AI Content Safety is a concept that can show up on the exam. Check the full guide to see it in context.