AI-102 Plan and manage an Azure AI solution Practice Question
You are planning to use Azure AI Document Intelligence to process a large volume of mixed document types (invoices, receipts, and purchase orders). The solution must automatically classify each document type and extract relevant fields. What should you configure?
⚠ Common exam trap
A common mix-up: candidates assume a single model (like neural or prebuilt) can both classify and extract, but Azure AI Document Intelligence requires a separate classification step before extraction for mixed document types.
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
✓
Create a custom classification model to identify document types, then use extraction models
Azure AI Document Intelligence (formerly Form Recognizer) requires a two-step process for mixed document types: first, a custom classification model identifies each document type (invoice, receipt, purchase order), then separate extraction models (custom or prebuilt) extract the relevant fields from each classified type. This approach ensures accurate routing and field extraction without relying on filenames or brittle regex patterns.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use the Form Recognizer service with neural models
Why it's wrong here
The Form Recognizer name is legacy branding; the requirement is automatic classification of mixed types, which needs a custom classification model plus composed custom extraction models, not neural models alone. Neural models suit custom field extraction from a single known form type, so they fail to route invoices, receipts and purchase orders automatically.
- ✓
Create a custom classification model to identify document types, then use extraction models
Why this is correct
A custom classification model is trained on labelled samples of invoices, receipts and purchase orders, so it identifies each document's type before routing. Extraction models then run per type, satisfying the requirement to classify automatically and pull the relevant fields from mixed documents.
- ✗
Use prebuilt models for each document type and route based on filename
Why it's wrong here
Routing by filename assumes the document type is encoded in the name, which mixed intake does not guarantee; prebuilt models extract fields but do not classify. A custom classification model is required to identify the type from content. Prebuilt models are correct when the type is already known and each document is submitted to its matching endpoint.
- ✗
Use the Read model to extract all text and then use regular expressions to classify
Why it's wrong here
The Read model returns OCR text and language structure only; regular expressions cannot reliably infer document type or extract typed fields such as line items. A custom classification model plus composed custom extraction models is required. Read with regex suits simple, fixed-format text extraction where layout and semantics are irrelevant.
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.