AI-102 Implement generative AI solutions Practice Question
You are working for a healthcare organization that uses Azure AI Document Intelligence to process patient intake forms. The forms are scanned and uploaded as multi-page PDFs. The extraction accuracy for the 'diagnosis code' field is poor. You have a labeled dataset of 200 forms. You need to improve the extraction accuracy without writing custom code. The solution must also handle forms with varying layouts. What should you do?
⚠ Common exam trap
It's easy for candidates to confuse the 'Form processing' custom model (template-based) with the custom neural model, assuming any custom model handles varying layouts, but only the neural model is designed for layout variation without custom code.
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
✓
Create a custom neural model and train it with the labeled dataset.
A custom neural model in Azure AI Document Intelligence is specifically designed to handle complex, variable-layout documents like patient intake forms. It uses deep learning to learn from labeled datasets (200 forms) and improves extraction accuracy for fields like 'diagnosis code' without requiring custom code. Neural models are superior to template-based models for varying layouts, as they generalize from patterns rather than relying on fixed spatial positions.
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 the 'Form processing' custom extraction model.
Why it's wrong here
Form processing is for fixed layouts; intake forms vary.
- ✗
Use the US Tax W-2 predefined model as a base and customize it.
Why it's wrong here
W-2 model is for tax forms, not healthcare intake.
- ✗
Use the General Document model to extract all text and then parse.
Why it's wrong here
General model extracts text but not structured fields accurately.
- ✓
Create a custom neural model and train it with the labeled dataset.
Why this is correct
Custom neural models handle varied layouts and improve field accuracy.
Go deeper
Related to this question
About these practice questions
One of 945 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.