A company processes two types of forms: a new vendor form and an updated vendor form. The fields are mostly the same, but the layout differs. They want one endpoint that can handle both. What should they do?

Train a custom model on a mix of both form types.

Create two custom models and compose them.

Use the prebuilt general document model.

Train a model on one form type and use it for both.

When creating a custom document intelligence model, what do you need to provide to define the fields to extract?

A set of test documents without labels

A list of field names and types

A sample document with labeled fields

A team has 50 labeled samples for a custom model. The model achieves 80% accuracy on the test set. They have the budget to label 100 more documents. They want to maximize accuracy improvement. Which documents should they label?

Documents that are most similar to the ones the model currently gets wrong.

A random sample of documents from the overall population.

Documents that are completely different from anything in the training set.

Documents that the model already predicts correctly with high confidence.

A team has trained a custom model to extract fields from tax forms. During evaluation, they notice that the 'total tax' field is often missing or incorrect. They have already labeled 100 forms. What should they do first to diagnose the issue?

Switch to the prebuilt invoice model.

Publish the model and monitor production usage.

Review the labeled examples for the 'total tax' field to ensure consistency and accuracy.

Increase the number of test documents.

A retail company needs to extract product names, prices, and quantities from a large volume of receipts. The receipts come from various stores with different formats. They want to use a prebuilt model. Which prebuilt model should they use?

The prebuilt business card model.

The prebuilt identity document model.

Microsoft Certified:Azure AI Engineer Associate

Domain 6Objective 2

Implement an Azure Document Intelligence in Foundry Tools Solution AI-102 Practice Questions (Page 3)

Part of the Implement knowledge mining and information extraction solutions domain, which accounts for 15-20% of the AI-102 exam. Microsoft does not publish an official question count, but from its 100-minute exam (~40–65 total, ~6–13 in this domain), expect 2–4 from this objective — we provide 35 practice questions to prepare you well beyond it. (estimate)

35questions here

7free pages

7concepts

15-20%of the exam

Questions 11–15

11application · medium
A company processes two types of forms: a new vendor form and an updated vendor form. The fields are mostly the same, but the layout differs. They want one endpoint that can handle both. What should they do?
Select an answer first
12foundation · easy
When creating a custom document intelligence model, what do you need to provide to define the fields to extract?
Select an answer first
13expert · hard
A team has 50 labeled samples for a custom model. The model achieves 80% accuracy on the test set. They have the budget to label 100 more documents. They want to maximize accuracy improvement. Which documents should they label?
Select an answer first
14application · medium
A team has trained a custom model to extract fields from tax forms. During evaluation, they notice that the 'total tax' field is often missing or incorrect. They have already labeled 100 forms. What should they do first to diagnose the issue?
Select an answer first
15application · easy
A retail company needs to extract product names, prices, and quantities from a large volume of receipts. The receipts come from various stores with different formats. They want to use a prebuilt model. Which prebuilt model should they use?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to AI-102

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Microsoft. “AI-102” is a trademark of its owner, used for identification only.