PL-900 Practice Question: Demonstrate the capabilities of Power Automate
You create a Power Automate flow that uses AI Builder to process invoices. The flow needs to extract text from PDFs and store it in Dataverse. What is the recommended approach?
⚠ Common exam trap
PL-900 often tests whether candidates can match AI Builder model types to their intended use, causing them to choose Entity Extraction or Text Classification when the task requires document field extraction from PDFs.
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
✓
Use AI Builder's Form Processing model to extract fields and then add a 'Create a new row' action for Dataverse.
AI Builder's Form Processing model is purpose-built to extract structured fields such as invoice number, date, and total from PDFs and images. Pairing it with a Dataverse 'Create a new row' action stores the extracted data in the target table, which is the recommended end-to-end pattern.
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 AI Builder's Form Processing model to extract fields and then add a 'Create a new row' action for Dataverse.
Why this is correct
Form Processing is the AI Builder model type trained to extract structured fields such as invoice number and total from PDFs. Pairing it with the Dataverse 'Create a new row' action persists those extracted values, meeting the requirement to store extracted text in Dataverse.
- ✗
Use AI Builder's Entity Extraction model on the raw PDF text.
Why it's wrong here
Entity Extraction expects already-extracted text, not a PDF binary, so it cannot read the document. Document Intelligence's invoice model or the Read text action must run first. The option tempts because Entity Extraction sounds like it pulls fields from invoices, but it operates on text input only.
- ✗
Use AI Builder's Object Detection model to identify text regions.
Why it's wrong here
Object Detection locates and classifies visual objects within images; it does not transcribe text characters. Extracting text from PDFs requires the Read or Document Intelligence text-recognition capability. The option appeals because invoices contain layout regions, but detection returns bounding boxes, not the stored text Dataverse needs.
- ✗
Use AI Builder's Text Classification model to categorize invoices.
Why it's wrong here
Text Classification assigns categories or labels to documents; it does not perform OCR, so it cannot extract raw text from PDFs. It would be the right choice for routing invoices into types such as utilities or supplies, not for populating Dataverse with extracted text.
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.