Configure Connector Knowledge Source in Copilot Studio

AB-620 By islever Editorial Last updated

Connect to Copilot connectors Connect to Microsoft Power Platform connectors

Short answer

1. Avoid copying enterprise data into an index -> Retrieve data without indexing. 2. Keep source-system access controls enforced -> Use existing permissions. 3. Access data by calling the system at runtime -> Access data by calling the system at runtime.

Question

DRAG DROP
A company uses a supported Power Platform connector to provide real-time access to enterprise records for knowledge grounding in an agent in Copilot Studio.
To meet the business needs, the knowledge source must provide the following functionality:
• Avoid copying enterprise data into an index.
• Keep source-system access controls enforced.
• Access data by calling the system at runtime.
You need to configure the connector knowledge source.
What should you configure for each requirement? To answer, move the appropriate configurations to the correct requirements. You may use each configuration once, more than once, or not at all. You may need to move the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
Exhibit: Configure Connector Knowledge Source in Copilot Studio

Key Takeaways

The core concept is using a live connector instead of an index, which inherently solves data duplication while requiring explicit permission handling to maintain security.

This question tests configuring a connector knowledge source in Microsoft Copilot Studio to ground agents in real-time enterprise data without indexing. It establishes the correct mapping between business requirements like access control enforcement and specific connector configuration settings.

Common mistake: Learners often incorrectly select options related to 'Indexing' or 'Caching' because they confuse standard search behaviors with real-time connector capabilities, failing to recognize that 'Retrieve data without indexing' is the key to avoiding data copying.

Expert Analysis

Why the Answer Is Correct

The scenario requires a solution that avoids data indexing, enforces source controls, and accesses data at runtime. Configuring the connector to 'Retrieve data without indexing' directly addresses the first requirement by fetching records on demand rather than storing them in a vector database. Using 'Use existing permissions' ensures that the agent respects the underlying system's security model, satisfying the second requirement. Finally, 'Access data by calling the system at runtime' confirms the live connection nature, meeting the third requirement.

Why Other Candidate Answers Are Wrong

Options suggesting 'Index data for faster retrieval' or 'Cache data locally' would violate the requirement to avoid copying enterprise data into an index. Similarly, selecting options that imply 'Bypass security checks' or 'Use service account credentials only' would fail to keep source-system access controls enforced per user context.

Community Comment Notes

Community feedback highlights that 'Retrieve data without indexing' prevents duplication, as noted by MeshMallow. Harshagracy emphasized that using existing permissions ensures users only see authorized data, confirming the importance of native permission inheritance.

Exam Strategy

Focus on understanding the difference between Index-based sources (which copy data) and Connector-based sources (which query live). When 'real-time' and 'no indexing' are mentioned, always look for options that emphasize live retrieval and native permission usage.

Frequently Asked Questions

What is the difference between a Connector Knowledge Source and an Index?

A Connector Knowledge Source queries live data from a connected application (like Dataverse) without copying it, whereas an Index copies data into a vector store for faster but static retrieval.

How does a connector enforce access controls?

It uses the authenticated user's identity to query the source system, ensuring the agent only returns data the user is authorized to view, preserving original security boundaries.

More AB-620 FAQ →

Discussion 2 contributions

Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.

From public community threads 2

  1. harshagracy 👍 1
    Avoid copying enterprise data into an index.Retrieve data without indexing. (By fetching data on demand, you avoid duplicating or indexing enterprise data in Copilot Studio's storage). Keep source-system access controls enforced.Use existing permissions. (The connector uses the authenticated user's credentials to execute the query, ensuring that users only receive data they are authorized to see in the source system). Access data by calling the system at runtime.Use real-time connector. (A real-time connector executes queries directly against the external system's API the moment a user asks a question, rather than relying on a pre-synced database).
  2. MeshMallow 👍 1
    1. Avoid copying enterprise data into an index. -> Retrieve data without indexing. 2. Keep source-system access controls enforced. -> Use existing permissions. 3. Access data by calling the system at runtime. -> Use real-time connector.

Reader comments & corrections

No reader corrections yet — spotted an error or have a note? Share it below.

Log in to comment, report an error, or add a note about this question.

Copilot Studio Generative Answer Disclaimer Strategy

S-grade

Evaluate Copilot Agent Configuration Compliance Status

S-grade

Export Copilot Studio Agent for Production ALM

S-grade

Configuring Copilot Agent Content Control and Formatting

S-grade

← Back to AB-620 Study Guide