An organization has an Azure AI Search index containing product specifications. The agent must retrieve information from this index. The developer has the Azure AI Search service name, index name, and an API key. In Copilot Studio, what is the minimum configuration required to connect to this index?

Create a custom connector that calls the Azure AI Search REST API and add it as a knowledge source.

Upload the index data as a SharePoint document library and use SharePoint as a knowledge source.

Add the Azure AI Search index as a Power Platform connector.

Create a new knowledge source, select Azure AI Search, and provide the service name, index name, and API key.

What is a prerequisite for using a Power Platform connector in Copilot Studio?

A connection reference that includes authentication details

An admin is configuring a Copilot agent that needs to access customer data from both Dynamics 365 and a legacy SQL database. The admin has added the Dynamics 365 connector. What should the admin do to also access the SQL database?

Use the Dynamics 365 connector to query the SQL database directly.

Export the SQL database to SharePoint and use the SharePoint connector.

Create a custom connector that wraps the SQL database and use it instead of the Dynamics 365 connector.

Add the SQL Server connector as another data source and configure the connection string.

What is the primary purpose of Azure AI Search in the context of enterprise knowledge access?

To provide a relational database for storing enterprise data

To replace the need for a data warehouse

To enable full-text and vector search over indexed enterprise content

A company uses Azure AI Search to index data from multiple sources. The agent must provide answers that combine data from different indexes. What should the admin do?

Add each index as a separate knowledge source in the agent.

Create a single index that contains all the data.

Create a custom connector that queries multiple indexes and merges the results.

Use Azure AI Search's built-in index merging feature.

Microsoft Certified:AI Agent Builder Associate

Domain 2Objective 1

Connect to Enterprise Knowledge Sources AB-620 Practice Questions (Page 5)

Part of the Integrate and extend agents in Copilot Studio domain, which accounts for 40–45% of the AB-620 exam. Microsoft does not publish an official question count, but from its 120-minute exam (~50–80 total, ~20–36 in this domain), expect 5–9 from this objective — we provide 33 practice questions to prepare you well beyond it. (estimate)

33questions here

7free pages

6concepts

40–45%of the exam

Questions 21–25

21application · medium
An organization has an Azure AI Search index containing product specifications. The agent must retrieve information from this index. The developer has the Azure AI Search service name, index name, and an API key. In Copilot Studio, what is the minimum configuration required to connect to this index?
Select an answer first
22foundation · easy
What is a prerequisite for using a Power Platform connector in Copilot Studio?
Select an answer first
23application · medium
An admin is configuring a Copilot agent that needs to access customer data from both Dynamics 365 and a legacy SQL database. The admin has added the Dynamics 365 connector. What should the admin do to also access the SQL database?
Select an answer first
24foundation · easy
What is the primary purpose of Azure AI Search in the context of enterprise knowledge access?
Select an answer first
25expert · medium
A company uses Azure AI Search to index data from multiple sources. The agent must provide answers that combine data from different indexes. What should the admin do?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to AB-620

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Microsoft. “AB-620” is a trademark of its owner, used for identification only.