PL-900 Practice Question: Demonstrate the capabilities of Power Automate
A financial analyst builds a Power Automate cloud flow that runs when a new invoice file is added to a SharePoint document library. The flow must extract the invoice total and vendor name, then write those values into a Dataverse table. The analyst wants to minimize manual configuration and avoid writing parsing expressions. Which action should the analyst use?
⚠ Common exam trap
Many exam-takers confuse actions that move or reshape data, such as Get file content and Parse JSON, with AI Builder actions that actually interpret document content.
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
✓
Extract information from documents (AI Builder)
Document understanding in Power Automate is delivered through AI Builder actions rather than generic file or data actions. 'Extract information from documents' applies a trained model to the invoice and returns named fields that can be mapped straight into Dataverse columns, eliminating hand-written parsing logic and meeting the analyst's low-effort 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.
- ✗
Compose
Why it's wrong here
Compose creates a single data output from an expression or value supplied by the maker. It performs no document understanding, so it cannot identify a total or vendor from a PDF invoice unless the maker already extracted that text elsewhere, which is exactly the manual work the analyst wants to avoid.
- ✗
Get file content using path
Why it's wrong here
This SharePoint action only retrieves the binary content and metadata of a file. It returns raw bytes, not parsed invoice fields, so the analyst would still need to build expressions or another processing step to obtain the total and vendor, which contradicts the no-code requirement.
- ✗
Parse JSON
Why it's wrong here
Parse JSON converts a JSON string into typed tokens using a supplied schema. An invoice file is not JSON, so this action cannot read the document, and the analyst would first have to convert and structure the content manually, which fails the goal of minimal configuration.
- ✓
Extract information from documents (AI Builder)
Why this is correct
The AI Builder 'Extract information from documents' action uses a prebuilt or custom document-processing model to return structured fields such as invoice total and vendor from a file. It is a no-code action that plugs directly into the flow, satisfying the requirement to avoid manual parsing expressions.
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.