AI-102 Plan and manage an Azure AI solution Practice Question
You are designing a solution that uses Azure AI Vision to analyze images for moderation. The solution must detect adult content and identify text in images. You need to minimize latency and cost. Which approach should you recommend?
⚠ Common exam trap
Watch out — candidates often think separate API calls or older API versions (like Computer Vision 3.2) are required for different tasks, but the Analyze Image API supports multiple visual features in a single call, which is the most efficient approach.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Call the Analyze Image API with the 'adult' and 'read' visual features
The Analyze Image API in Azure AI Vision supports multiple visual features in a single call, including 'adult' for adult content detection and 'read' for OCR (text extraction). This minimizes latency by avoiding multiple API calls and reduces cost since you are billed per API call, not per feature.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Call the Analyze Image API twice: once for adult content and once for OCR
Why it's wrong here
Two round trips to the same endpoint duplicate image upload and processing, increasing both latency and per-call charges. Calling twice is tempting for isolating each capability's response, and would be correct when the two operations genuinely require different services or regions.
- ✗
Use the Computer Vision 3.2 API with the 'adult' and 'OCR' parameters
Why it's wrong here
Computer Vision 3.2 is a legacy versioned endpoint; the current Image Analysis API returns adult flags and read text in one call, avoiding the deprecated route. The 3.2 API is tempting for existing integrations pinned to that version, and would be correct when maintaining code already written against it.
- ✓
Call the Analyze Image API with the 'adult' and 'read' visual features
Why this is correct
Requesting the 'adult' and 'read' visual features in a single Analyze Image call returns both moderation and OCR results together, avoiding a second request. This satisfies the latency and cost constraints by consolidating processing into one API transaction.
- ✗
Use the Read API for text and the Content Moderator API for adult content
Why it's wrong here
Two separate service calls double request overhead and billing, and Content Moderator is a distinct resource from Azure AI Vision. Splitting services is tempting for granular moderation scoring, and would be correct when adult-content detection needs custom blocklists or review workflows beyond Vision's built-in flags.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.