PL-900 Demonstrate the capabilities of Power Apps Practice Question
A company wants to create a Power App that uses AI to extract information from uploaded invoices. The app should allow users to upload an invoice image and then automatically populate fields like invoice number, date, and total amount. Which Power Platform feature should you use? A) AI Builder's prebuilt invoice processing model. B) Custom Vision service in Azure. C) Power Automate with OCR actions. D) Use the 'Scan' function in Power Apps.
⚠ Common exam trap
PL-900 often tests the distinction between AI Builder prebuilt models and other Azure AI services, so candidates might choose Custom Vision or generic OCR thinking they are equivalent, but AI Builder is the integrated low-code solution.
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
✓
AI Builder's prebuilt invoice processing model.
AI Builder's prebuilt invoice processing model is specifically designed to extract key fields such as invoice number, date, and total amount from uploaded invoice images. It is a no-code/low-code AI feature within the Power Platform, making it the most appropriate choice for this requirement.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
AI Builder's prebuilt invoice processing model.
Why this is correct
AI Builder's prebuilt invoice processing model extracts invoice number, date and total from uploaded documents using a trained document-understanding model, returning structured fields the app can bind directly. It satisfies the requirement for automatic field population without custom model training or OCR pipeline building.
- ✗
Use the 'Scan' function in Power Apps.
Why it's wrong here
The Scan function reads barcodes and QR codes, not invoice text, so it cannot populate invoice number, date, or total. AI Builder's prebuilt invoice processing model is trained for document extraction. Scan is correct for asset tracking or scanning a product label into a field.
- ✗
Custom Vision service in Azure.
Why it's wrong here
Custom Vision performs image classification and object detection, not field-level extraction of invoice number, date and total from a document. It is tempting because it is a genuine Azure AI vision service, and would fit a scenario requiring bespoke recognition of custom visual categories rather than structured invoice fields.
- ✗
Power Automate with OCR actions.
Why it's wrong here
Generic OCR actions return raw recognised text without mapping it to invoice number, date and total fields, so the app cannot auto-populate them. It is tempting because OCR is the underlying extraction step, and would suit a scenario needing only plain text capture from scanned documents.
Go deeper
Related to this question
About these practice questions
Courseiva writes every PL-900 question from scratch — 701 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 PL-900 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 PL-900 exam.