AI-103 Certification Practice Question #50

Question

You are deploying a support agent that enables users to upload photos.
You need to automatically classify uploaded images for harmful content. The solution must block content based on severity levels.
What should you do?

Accepted Answer

The requirement is to automatically classify uploaded *images* for harmful content and block based on severity levels. Azure AI Content Safety image moderation (the Analyze image API) does exactly this: it classifies images across the harm categories (hate, sexual, violence, self-harm) and returns severity levels (0/2/4/6), and you configure per-category severity thresholds to accept or reject (block) content. OCR+keyword scanning only handles embedded text, prompt shields address prompt-injection rather than image classification, and blocklists match known strings — none classifies visual content by severity. The official Suggested Answer (D) matches MS Learn directly. Confidence 89% — strong documentation and official-key agreement; only deduction is no community votes in the file.

More AI-103 practice questions