A team is training a custom model for a form that has a field with high variability in its location (sometimes top-left, sometimes bottom-right). They have 200 labeled samples. The model's accuracy is below target. They have time to label more data. What is the most effective next step?

Reduce the number of labeled samples to avoid overfitting.

Add more labeled samples that specifically cover the different locations of the variable field.

Use a prebuilt model that includes the field.

Increase the total number of labeled samples uniformly across all fields.

A company processes three types of forms: purchase orders, delivery notes, and return forms. They have trained three separate custom models, each with high accuracy on its own form type. They want to deploy a single endpoint that automatically routes each document to the correct model. What should they do?

Call each model sequentially and use the first non-empty result.

Use the prebuilt layout model to classify the form type first.

Train a new custom model with labeled examples from all three form types.

Create a composed model that includes all three custom models and publish it.

A startup wants to use Document Intelligence to extract data from business cards. They have not yet created any Azure resources. What should they do first?

Create a storage account and upload business card images.

Use the Document Intelligence Studio without a resource.

Create a Document Intelligence resource in the Azure portal and get the endpoint and key.

Train a custom model with business card samples.

Microsoft Certified:Azure AI Engineer Associate

Domain 6Objective 2

Implement an Azure Document Intelligence in Foundry Tools Solution AI-102 Practice Questions (Page 6)

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 26–30

26foundation · easy
You have trained separate custom models for invoices, purchase orders, and delivery notes. You want to use a single endpoint to analyze any of these document types. What should you create?
Select an answer first
27expert · hard
A team is training a custom model for a form that has a field with high variability in its location (sometimes top-left, sometimes bottom-right). They have 200 labeled samples. The model's accuracy is below target. They have time to label more data. What is the most effective next step?
Select an answer first
28application · medium
A company processes three types of forms: purchase orders, delivery notes, and return forms. They have trained three separate custom models, each with high accuracy on its own form type. They want to deploy a single endpoint that automatically routes each document to the correct model. What should they do?
Select an answer first
29application · easy
A startup wants to use Document Intelligence to extract data from business cards. They have not yet created any Azure resources. What should they do first?
Select an answer first
30foundation · easy
You are setting up a new Azure Document Intelligence solution. You need to create the Azure resource that will provide the endpoint and keys for your document analysis calls. Which resource type should you provision in the Azure portal?
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.

Implement an Azure Document Intelligence in Foundry Tools Solution AI-102 Practice Questions (Page 6)

Questions 26–30

You have trained separate custom models for invoices, purchase orders, and delivery notes. You want to use a single endpoint to analyze any of these document types. What should you create?

A team is training a custom model for a form that has a field with high variability in its location (sometimes top-left, sometimes bottom-right). They have 200 labeled samples. The model's accuracy is below target. They have time to label more data. What is the most effective next step?

A startup wants to use Document Intelligence to extract data from business cards. They have not yet created any Azure resources. What should they do first?

You are setting up a new Azure Document Intelligence solution. You need to create the Azure resource that will provide the endpoint and keys for your document analysis calls. Which resource type should you provision in the Azure portal?

Keep studying — Implement knowledge mining and information extraction solutions