PL-900 Practice Question: Demonstrate the capabilities of Microsoft Copilot Studio
A copilot built in Microsoft Copilot Studio must create a record in a Microsoft Dataverse table after a user confirms a request in chat. The team wants the copilot to perform this action during the conversation without leaving the chat. What should you configure?
⚠ Common exam trap
Many candidates confuse read-oriented knowledge grounding with write-capable actions, assuming that connecting Dataverse as knowledge also lets the copilot create records.
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
✓
Add a Power Automate flow as an action in the topic and call it from a node.
To perform a back-end write during a chat, the copilot must invoke an action. Cloud flows called from topic nodes are the standard integration pattern, letting the copilot create the Dataverse record after confirmation and then respond to the user. Knowledge sources, channels, and publishing settings do not provide transactional write capability.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Enable the copilot's voice channel and use speech recognition.
Why it's wrong here
Voice channel settings affect how users interact with the copilot through speech, not whether it can write to Dataverse. Enabling voice does not provide any record-creation capability. The requirement is a data operation during chat, so channel configuration is irrelevant and fails to deliver the needed behavior.
- ✗
Publish the copilot to a custom website and embed it there.
Why it's wrong here
Embedding the copilot on a website changes where users access it but adds no ability to write records. Publishing is a deployment step, not an integration mechanism. Without a flow or connector action, the copilot still cannot create the Dataverse row, so this option does not meet the scenario.
- ✗
Add the Dataverse table as a knowledge source to the copilot.
Why it's wrong here
A Dataverse knowledge source lets the copilot retrieve and answer questions from table data, but it does not create records. Knowledge sources are read-oriented for grounding responses. The scenario requires a write operation triggered by user confirmation, which knowledge configuration alone cannot perform.
- ✓
Add a Power Automate flow as an action in the topic and call it from a node.
Why this is correct
Calling a cloud flow from a topic action is the supported way to perform back-end operations such as creating a Dataverse record during a conversation. The flow runs when the topic reaches that node, and the copilot can continue the chat afterward. This satisfies the requirement to act within the chat experience.
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.