AI-102 Practice Question: Implement knowledge mining and document intelligence solutions
A financial services firm needs to extract structured fields such as invoice date, vendor name, and total amount from thousands of PDF invoices. The documents vary in layout across vendors. The firm wants a pretrained model that requires no custom training and can return field-level confidence scores. Which Azure AI Document Intelligence model should they use?
⚠ Common exam trap
The trap here is choosing a custom model when a pretrained invoice model already covers the required fields without training.
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
✓
Prebuilt invoice model
The firm needs invoice-specific structured fields with confidence scores and no custom training. The prebuilt invoice model in Azure AI Document Intelligence is designed exactly for that, recognizing common invoice fields across varied layouts. General document, custom template, and Read models either lack invoice-specific fields, require training, or return only raw text.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Read model
Why it's wrong here
The Read model extracts printed and handwritten text lines and words but does not identify invoice fields or return field-level confidence for date, vendor, or total. It would provide raw text only, leaving the firm to build its own parsing logic, which does not meet the structured extraction requirement.
- ✗
Custom template model
Why it's wrong here
A custom template model requires you to label at least five sample documents and train the model before use. That contradicts the requirement for a pretrained model with no custom training. It can work well for stable layouts, but it is not the zero-training option needed here.
- ✓
Prebuilt invoice model
Why this is correct
The prebuilt invoice model is trained to extract invoice-specific fields including invoice date, vendor name, and total amount, and it returns confidence scores per field. Because it is pretrained, no custom labeling or training is required, which matches the firm's requirement to process varied vendor layouts quickly.
- ✗
General document model
Why it's wrong here
The general document model extracts key-value pairs and entities from a broad range of documents, but it does not return the invoice-specific schema fields such as InvoiceDate, VendorName, and InvoiceTotal with dedicated confidence scores. It is useful for generic extraction, yet it is not the pretrained model tailored to invoices described in the scenario.
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 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.