Microsoft Certified: Azure AI Engineer AssociateImplement generative AI solutionsMedium
A marketing agency uses Azure OpenAI Service to generate ad copy. They want to ensure that the generated content avoids sensitive topics, hate speech, self-harm, and sexually explicit material, as per their ethical guidelines and platform policies. Which Azure service should they integrate to automatically detect and filter such content from the model's output before it's displayed to users?
- AAzure Monitor
- BAzure Cognitive Search
- CAzure Data Factory
- DAzure AI Content Safety
Show answer & explanationAnswer & explanation
Correct answer: D. Azure AI Content Safety
Azure AI Content Safety is a dedicated service designed to detect and filter harmful user-generated and AI-generated content across various modalities, including text, images, and video. It's ideal for enforcing ethical guidelines and platform policies.
Why the other options are wrong
- A. Azure Monitor is for collecting, analyzing, and acting on telemetry data from Azure resources, not content moderation.
- B. Azure Cognitive Search is a search-as-a-service cloud solution that adds powerful search capabilities to applications, not for content safety filtering.
- C. Azure Data Factory is a cloud-based data integration service for orchestrating data movement and transformation, not content moderation.
Azure AI Content Safety
An Azure AI service that helps detect and moderate harmful user-generated and AI-generated content across text, image, and video.
- Identifies hate, sexual, violence, and self-harm content.
- Provides severity scores for detected content.
- Integrates with other Azure AI services for moderation pipelines.
Memory trick: Content Safety keeps your AI Safe: 'Content Safety' is the 'safe' choice for moderation.