Requirement

Correct configuration

Tenant administration

Configure the Copilot connector in Microsoft 365 Admin Center.

Agent runtime behavior

Call the connector knowledge source.

Builder configuration

Add the Copilot connector as a knowledge source.

Comprehensive and Detailed Explanation From [Microsoft AB-620 Study Guide]

Copilot connector deployment separates administrative provisioning, agent configuration, and runtime retrieval. At the tenant-administration stage, an administrator configures the connector in the Microsoft 365 Admin Center . The administrator selects or creates the connector, defines its schema and semantic labels, and completes the process that indexes external content into Microsoft Graph. This makes the enterprise connection discoverable across the tenant.

The agent builder does not recreate the connector in Copilot Studio. Instead, the builder opens the agent’s Knowledge page, selects Add knowledge , chooses the previously configured Copilot connector, and adds the required connection to the agent. Power Platform Admin Center is not the provisioning location for Microsoft 365 Copilot connectors; it is primarily used for environment administration and data-policy governance.

At runtime, the agent calls the configured connector knowledge source to retrieve indexed content and ground its generated response. Copilot connectors preserve source-level access controls, so the agent returns only information the current authenticated user is authorized to access. This provides secure semantic grounding and supports citations without directly calling the third-party system for each conversation.

Relevant study-guide area: Integrate and extend agents in Copilot Studio → Connect to enterprise knowledge sources → Connect to Copilot connectors . See Add Copilot connectors as a knowledge source and Copilot connectors versus Power Platform connectors .

Capture response → Use the action ' s response outputs in later steps; Continue the same run → Allow the action to wait for and return a response before continuing; Require a manual decision → Add a human approval action.

Comprehensive and Detailed Explanation From Microsoft AB-620 Study Guide: A human-in-the-loop flow must preserve execution state while it waits. The approval or information action pauses the current run and returns a response when the designated person acts; triggering a new flow would lose that direct continuation contract. The response outputs—decision, comments, supplied fields, responder, and timestamps as applicable—are then referenced by downstream conditions and actions. A human approval action provides the explicit decision gate required before processing continues. Sending a notification or message alone does not wait and cannot guarantee that the decision controls the flow. The designer should configure expiration, escalation, reassignment, and rejection paths so the run cannot remain suspended without governance. Responses should be validated before use, and sensitive values should be protected in variables and history. Test approval, rejection, timeout, duplicate response, and unauthorized response scenarios. These controls ensure that human oversight changes execution deterministically instead of acting as an informational side channel. Study Guide alignment: Plan and configure agent solutions > Create and monitor agent flows in Copilot Studio > Create a human-in-the-loop agent flow.

===============

Approval stage → Wait for a response and branch according to the decision; Information-collection stage → Wait for a response and capture the submitted inputs.

Comprehensive and Detailed Explanation From Microsoft AB-620 Study Guide: An approval is a decision gate. The flow must pause until the reviewer responds, then branch to the appropriate approved, rejected, or other outcome path. Information collection also pauses, but its purpose is to capture supplied values and make them available to later actions in the same run. Sending a request or notification and continuing immediately would break both requirements because downstream processing could occur before the human response exists. The action should have a defined timeout and an escalation or cancellation path so a missing response does not leave the process suspended indefinitely. The flow should store the response, responder identity, timestamp, and any comments needed for audit. Sensitive information should not be requested through an inappropriate channel and should be protected in logs and variables. Testing must cover approval, rejection, corrected information, timeout, and unauthorized-responder cases. This produces a controlled human-in-the-loop design rather than a simple alert that has no effect on execution. Study Guide alignment: Plan and configure agent solutions > Create and monitor agent flows in Copilot Studio > Create a human-in-the-loop agent flow.

===============