Implement knowledge mining and information extraction solutions →hardMultiple SelectObjective-mapped
AI-102 Practice Question: Implement knowledge mining and information extraction solutions
Which THREE components are essential when building a custom skill for Azure AI Search?
⚠ Common exam trap
Watch out — candidates often assume a custom skill must involve a machine learning model (Option C) or a scheduled trigger (Option D), but the core requirement is simply a Web API endpoint with proper JSON input/output definitions and field mappings to integrate with the indexer.
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
✓
A Web API endpoint that processes documents
A custom skill in Azure AI Search must be implemented as a Web API endpoint that integrates with the AI Search enrichment pipeline. This endpoint receives JSON payloads containing documents to be processed, performs custom logic (e.g., entity extraction, classification), and returns enriched JSON results. The Web API must be hosted (e.g., on Azure Functions, App Service) and conform to the specific request/response schema defined by Azure AI Search.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
A Web API endpoint that processes documents
Why this is correct
Custom skills are implemented as web APIs.
- ✓
Field mappings to pass data between the skill and the indexer
Why this is correct
Mappings connect skill outputs to index fields.
- ✗
A machine learning model trained in Azure Machine Learning
Why it's wrong here
Not required, but can be used inside the skill.
- ✗
An Azure Function to trigger the skill on a schedule
Why it's wrong here
Skills are called during indexing, not scheduled.
- ✓
Input and output definitions in JSON format
Why this is correct
Skills use JSON for context.
Quick reference
Cloud Service Model Comparison
| Model | You Manage | Provider Manages | Examples |
|---|---|---|---|
| IaaS | OS, runtime, apps, data | Hardware, hypervisor, networking | EC2, Azure VMs, GCP Compute Engine |
| PaaS | Apps and data | OS, runtime, middleware, hardware | Elastic Beanstalk, Azure App Service |
| SaaS | Data and settings only | Everything else | Microsoft 365, Salesforce, Workday |
| FaaS / Serverless | Function code only | Infra, scaling, runtime | Lambda, Azure Functions, Cloud Run |
| CaaS | Containers and apps | Kubernetes, OS, hardware | EKS, AKS, GKE |
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 945 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.