AI-102 Practice Question: Implement knowledge mining and information extraction solutions
You need to implement a solution that searches through a collection of scanned invoices and extracts invoice numbers, dates, and total amounts. The solution must run on a schedule without manual intervention. Which Azure service should you use?
⚠ Common exam trap
AI-102 often tests the distinction between Document Intelligence (structured field extraction from forms/invoices) and Azure AI Search with skills (indexing/search enrichment) — candidates who see 'search through a collection' may incorrectly pick AI Search, missing that the requirement is field extraction, not retrieval.
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
✓
Azure AI Document Intelligence
Azure AI Document Intelligence (formerly Form Recognizer) provides prebuilt and custom models specifically designed to extract structured fields like invoice numbers, dates, and totals from scanned documents, including the prebuilt invoice model. It can be invoked programmatically on a schedule via Azure Functions, Logic Apps, or Data Factory, satisfying the no-manual-intervention requirement. This is the canonical Azure service for OCR-plus-field-extraction from forms and invoices.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Azure Bot Service
Why it's wrong here
Azure Bot Service builds conversational interfaces for chat channels, offering no document ingestion, OCR or scheduled extraction pipeline. It would be the correct choice when users must interact with a bot through Teams or a website, not when invoices need parsing unattended.
- ✓
Azure AI Document Intelligence
Why this is correct
Azure AI Document Intelligence provides prebuilt invoice models that extract invoice numbers, dates and totals from scanned documents, and its read model handles OCR. It supports scheduled, unattended runs via the API, satisfying the no-manual-intervention constraint.
- ✗
Azure AI Search with built-in skills
Why it's wrong here
Azure AI Search with built-in skills indexes and enriches content, but its skillsets target general text and entity extraction rather than the structured invoice fields required here. It is the right choice when you need full-text search and enrichment over an existing corpus, not scheduled form-field extraction.
- ✗
Azure AI Foundry model catalog
Why it's wrong here
The model catalog supplies pretrained models for custom development, but provides no built-in invoice parsing, indexing or scheduling; you would have to build the pipeline yourself. It suits selecting and deploying a foundation model for bespoke AI workloads, not turnkey document extraction.
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
One of 761 original AI-102 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 →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.