AI-102 Plan and manage an Azure AI solution Practice Question
You are designing an AI solution that uses Azure AI Document Intelligence to extract data from invoices. The solution must handle a high volume of documents with varying layouts. Which approach should you use?
⚠ Common exam trap
Many candidates assume the prebuilt invoice model (Option C) is sufficient for all invoice scenarios, but it only works for standard layouts and fails when invoices have custom fields or non-standard structures.
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
✓
Train a custom neural model with labeled invoices
Custom neural models in Azure AI Document Intelligence are designed to handle high volumes of documents with varying layouts. Unlike fixed template models, neural models learn from labeled examples and generalize across different invoice structures, making them ideal for diverse, high-volume scenarios.
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 a custom template model with fixed field positions
Why it's wrong here
A custom template model requires fixed field positions, so it fails when invoice layouts vary between suppliers. It is tempting because template models are quick to train with a handful of labelled samples and excel on highly standardised, single-format documents, but the scenario explicitly demands handling varying layouts at volume.
- ✓
Train a custom neural model with labeled invoices
Why this is correct
A custom neural model handles varying invoice layouts because it learns layout and field patterns from labelled examples rather than relying on fixed templates. This satisfies the high-volume, layout-variance constraint, whereas prebuilt models assume consistent formats and would degrade across suppliers.
- ✗
Use the prebuilt invoice model
Why it's wrong here
The prebuilt invoice model extracts a fixed set of common fields and cannot be trained on your own varied layouts, so accuracy suffers when formats differ widely. It is tempting because it needs no labelling and works immediately on standard invoices, making it the right choice only when layouts are consistent and match the supported schema.
- ✗
Extract text using OCR and then use regex parsing
Why it's wrong here
OCR plus regex parsing relies on positional or pattern assumptions that break as layouts vary, and it scales poorly across high document volumes. It is tempting because it avoids model training and works for rigid, machine-generated formats, but it cannot generalise to the varying invoices this scenario requires.
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 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.