PL-900 Practice Question: Demonstrate the capabilities of Microsoft Copilot Studio
A nonprofit's IT coordinator has built a Copilot Studio copilot that answers questions about volunteer policies. The coordinator wants the copilot to look up answers from the organization's existing public website instead of manually authoring every question-and-answer pair. Which Copilot Studio capability should the coordinator use?
⚠ Common exam trap
The trap here is overlooking the built-in knowledge source option and instead reaching for manual topics or custom flows to reuse website 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
✓
Generative answers with a public website as a knowledge source.
Generative answers allow a copilot to ground responses in external knowledge sources, and a public website can be added as one such source. This lets the copilot retrieve and summarize existing policy content without manually building question-and-answer topics. Manual topics, custom scraping flows, and entities do not provide built-in website retrieval.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A Power Automate cloud flow that scrapes the website nightly into a SharePoint list.
Why it's wrong here
Building a scraping flow plus a SharePoint list introduces custom development and maintenance that the coordinator did not ask for. It also requires the copilot to query that list, adding another layer of configuration. While technically possible, it is far more complex than using a built-in knowledge source and does not leverage Copilot Studio's native retrieval capabilities for websites.
- ✗
A manual topic with a series of Question nodes for each policy.
Why it's wrong here
Question nodes require the author to write each question, define the expected response, and maintain the branching logic. This is precisely the manual authoring effort the coordinator wants to avoid, and it does not dynamically read the website. Because policies change, manual topics would also become stale, so this approach fails both the automation and the accuracy goals of the scenario.
- ✗
An entity that extracts website URLs from user messages.
Why it's wrong here
Entities recognize and extract values such as URLs or dates from what the user types; they do not retrieve or summarize website content. An entity would only help the copilot identify that a user mentioned a link, not answer policy questions from the site. This capability is unrelated to grounding responses in external knowledge, so it cannot fulfill the requirement.
- ✓
Generative answers with a public website as a knowledge source.
Why this is correct
Generative answers let a copilot retrieve content from configured knowledge sources and compose a natural language response grounded in that content. Adding a public website as a knowledge source means the copilot can search the site and answer volunteer policy questions without manually creating topic pairs. This directly matches the goal of reusing existing published content rather than authoring every answer by hand.
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.