AI-102 Practice Question: Implement knowledge mining and document intelligence solutions
A company uses Azure Document Intelligence to analyze prebuilt invoices. They need to extract the invoice total and the due date from each invoice. They call the Analyze Invoice operation and receive a result. Which part of the JSON response contains the extracted fields?
⚠ Common exam trap
The trap here is assuming that all extracted data is in a generic key-value format, when the prebuilt invoice model uses a specialized fields object.
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
✓
The documents array, where each document has a fields object with named fields such as InvoiceTotal and DueDate.
The prebuilt invoice model returns a structured JSON with a documents array. Each document includes a fields object that contains named fields such as InvoiceTotal and DueDate, along with their values and confidence scores. This is the correct location to extract specific invoice data.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
The documents array, where each document has a fields object with named fields such as InvoiceTotal and DueDate.
Why this is correct
The Analyze Invoice operation returns a result with a documents array. Each document contains a fields object where each field (e.g., InvoiceTotal, DueDate) includes its value, confidence, and bounding regions. This is the standard structure for prebuilt models, allowing you to access extracted fields by name.
- ✗
The tables array, where each table has cells that contain the extracted values.
Why it's wrong here
The tables array is used to represent tabular data extracted from the document, such as line items. It does not contain the named fields like InvoiceTotal or DueDate. While some fields might be in tables, the prebuilt model extracts them into the fields object, not the tables array.
- ✗
The pages array, where each page has a lines array containing text and bounding boxes.
Why it's wrong here
The pages array contains the raw OCR output, including lines of text and their positions. While you could parse the text to find the total and due date, this is not the structured extraction provided by the prebuilt invoice model. The fields object is specifically designed for this purpose and includes confidence scores.
- ✗
The analyzeResult object, which contains a keyValuePairs array with keys and values.
Why it's wrong here
The keyValuePairs array is part of the general document model (prebuilt-document) and is used for generic key-value extraction. The prebuilt invoice model uses a structured fields object instead. Relying on keyValuePairs would not give you the specific named fields like InvoiceTotal and DueDate with their trained accuracy.
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.