Courseiva

AI-900 Practice Question: Describe Artificial Intelligence workloads and considerations

What is 'AI enrichment' in the context of Azure AI Search (Cognitive Search)?

⚠ Common exam trap

Watch out — candidates often confuse AI enrichment (which extracts metadata during indexing) with custom ML model training for ranking or with general AI subscription features, leading them to select options that describe unrelated AI capabilities.

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

Applying AI cognitive skills during search indexing to extract and enrich content with metadata

AI enrichment in Azure AI Search refers to the process of applying built-in or custom cognitive skills during the indexing pipeline to extract, transform, and enrich unstructured data (e.g., images, text, PDFs) with additional metadata. This enables capabilities such as OCR, entity recognition, key phrase extraction, and language detection, turning raw content into searchable, structured information without requiring separate ML training.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • Adding premium features to an Azure AI subscription

    Why it's wrong here

    Adding premium features to an Azure AI subscription is an account-management action that adjusts service tiers, quotas, or support levels, not the content-processing behavior of the search service. AI enrichment is a pipeline executed inside Azure Cognitive Search during indexing, where cognitive skills are invoked on source data to create new fields. Subscription tier choices can affect capacity and throughput, but they do not themselves extract or enrich content from documents.

  • Applying AI cognitive skills during search indexing to extract and enrich content with metadata

    Why this is correct

    Applying AI cognitive skills during search indexing is the core definition of AI enrichment, where a skillset in Azure Cognitive Search performs operations like OCR on scanned images, named-entity recognition, language detection, and key phrase extraction. These skills transform unstructured content (e.g., PDFs, photos) into structured, searchable metadata fields that can be queried with standard full-text search. This makes previously hidden information discoverable, such as extracting text from a scanned contract or identifying dates and people in emails.

  • Training custom ML models to improve search result ranking

    Why it's wrong here

    Training custom ML models to improve search result ranking focuses on query-time relevance, such as using learning-to-rank algorithms to reorder results based on click signals or features. AI enrichment is an indexing-time process that operates on each document before any query is received, extracting text from images or PDFs and populating metadata fields. Ranking models do not create or enrich fields; they only affect how existing fields are scored. Thus, the two address different phases of the search pipeline.

  • Encrypting indexed search content with AI-managed keys

    Why it's wrong here

    Encrypting indexed search content with AI-managed keys is a security control that protects data at rest by applying encryption at the storage layer. While encryption ensures confidentiality and compliance, it does not analyze or transform the content itself. AI enrichment, by contrast, runs OCR, entity recognition, sentiment analysis, and other cognitive skills to derive new metadata and make unstructured data searchable. Encryption preserves existing data; enrichment generates additional meaning.

About these practice questions

One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This AI-900 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-900 exam.