PL-900 Demonstrate the capabilities of Power Apps Practice Question
A company wants to build a Power App that uses AI to extract information from uploaded invoices. Which capability should they use?
⚠ Common exam trap
PL-900 often tests whether candidates confuse conversational AI tools (Copilot Studio, Power Virtual Agents) with document-processing AI (AI Builder), so match 'extract information from invoices' to AI Builder's prebuilt invoice model.
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 invoice processing model
AI Builder's invoice processing model is a prebuilt AI capability in Power Platform specifically designed to extract structured data (vendor, total, line items) from invoices using OCR plus machine learning. It integrates directly with Power Apps and Power Automate and requires no custom model training. This is the purpose-built solution for the stated 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.
- ✗
Power Automate with OCR actions
Why it's wrong here
Power Automate with OCR actions orchestrates flows and reads text, but cannot return structured invoice fields directly into a canvas app's AI Builder extraction pipeline. It is tempting because OCR suits bulk document digitisation in scheduled background flows, yet the scenario requires AI Builder's invoice processing model invoked from the app.
- ✓
AI Builder invoice processing model
Why this is correct
The AI Builder invoice processing model is prebuilt to extract header and line-item fields such as vendor, total and date from invoice documents. It satisfies the stem's requirement to extract information from uploaded invoices without training a custom model.
- ✗
Power Virtual Agents
Why it's wrong here
Power Virtual Agents creates conversational chatbots for customer or employee dialogue, not AI models that parse invoice documents into structured data. It is tempting because it is a Microsoft AI tool, but it is correct when the requirement is a conversational bot, not document extraction.
- ✗
Copilot Studio
Why it's wrong here
Copilot Studio builds conversational agents and chatbots, not document-processing AI models that extract structured fields from invoices. It is tempting as a Microsoft AI builder, but it is the right choice for designing custom copilots, not for invoice data extraction.
Go deeper
Related to this question
About these practice questions
One of 701 original PL-900 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 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.