AB-620 Exam Dumps and Practice Questions

Comprehensive and Detailed Explanation From Microsoft AB-620 Study Guide: The tenant administrator has already configured a Copilot connector that indexes the external system into Microsoft Graph. The agent should consume that approved enterprise knowledge source from its Knowledge configuration. This lets generative answers retrieve authorized indexed content without recreating the connector, uploading duplicate documents, or treating the source as a callable transaction. Copilot connectors are designed for enterprise search and knowledge grounding; the user's access is evaluated so that responses surface only content the user is permitted to see. A custom connector is appropriate when the agent must call an API or perform an operation, which the scenario explicitly excludes. Adding the connector as a tool would likewise shift the design from retrieval to invocation. Manual file upload would create a second, potentially stale copy and break the administrator-managed indexing lifecycle. After adding the source, the builder should provide a clear name and description, test representative questions, confirm citations or source attribution, and verify that restricted users cannot retrieve unauthorized material. Study Guide alignment: Integrate and extend agents in Copilot Studio > Connect to enterprise knowledge sources > Connect to Copilot connectors.

Comprehensive and Detailed Explanation From [Atlassian Jira Cloud Documentation]

The cause is the Jira Browse users and groups global permission. Atlassian states that users with this permission can view user names when working with user-picker fields or @mentioning users. Without it, Jira cannot provide the affected users with the complete user directory required to search for and select another person through an @mention.

The fact that users can enter and save ordinary text in the paragraph field confirms that the field is present, editable, and available on the applicable work-item layout. Therefore, field settings and screen settings are not responsible. Notification settings determine how users receive updates after an event and do not control whether names appear in the mention picker.

Project permissions and issue-level security can affect whether a particular person can access the project or work item. However, a general inability to search for or mention other users indicates that the initiating users lack the site-wide user-browsing capability.

A Jira administrator should review Settings System Global permissions and grant Browse users and groups to an appropriate group containing the affected users, subject to the organization's privacy policies.

Relevant documentation topic: Jira Cloud administration Global permissions Browse users and groups. See What are global permissions, and what do they control?.

Comprehensive and Detailed Explanation From Microsoft AB-620 Study Guide: Fabrikam needs both reusable prompt behavior and explicit model governance. A reusable custom prompt template provides the stable summarization instructions, expected structure, and input/output contract that can be applied wherever summarization is required. Within that prompt's configuration, selecting the approved model from the Microsoft Foundry model catalog controls which model generates the output. These are separate controls: the template governs the task, while the model selection satisfies the approved-model requirement. Publishing only deploys the configuration already selected; it does not automatically choose or enforce an approved model. Citations are valuable for grounded policy answers but do not determine the model used for summarization. Azure AI Search is the retrieval system for indexed enterprise policy content and is not required merely to apply a long-form summarization template. The prompt should be tested with representative transcripts for completeness, classification accuracy, output schema, safety, and latency. Where Fabrikam already uses a connected Foundry agent for this specialist function, the prompt and model settings should remain owned by that component rather than being duplicated in the primary agent. Study Guide alignment: Integrate and extend agents in Copilot Studio > Integrate agents with Azure > Configure custom prompts to use the Foundry model catalog.

Comprehensive and Detailed Explanation From Microsoft AB-620 Study Guide: Retrying the failing action without an error-handling branch does not meet either stated requirement. The flow can still exhaust its retries and terminate without notifying anyone, and repeated calls may be dangerous if the external operation is not idempotent. A controlled design configures run-after conditions so a notification or handling scope executes on failure and timeout, captures an appropriate error message or correlation identifier, and then terminates or continues intentionally. Retry policy is a separate resilience choice. It can help with transient failures when the operation is safe to repeat, but it is not a substitute for handling the final failure. The number, interval, and backoff should be bounded, and non-idempotent requests should use a deduplication mechanism or disable retries. Administrators need enough diagnostic context to locate the failed run without receiving secrets or sensitive payloads. Because the proposed solution only retries, the correct assessment is No. Study Guide alignment: Plan and configure agent solutions > Create and monitor agent flows in Copilot Studio > Implement error handling in agent flows.

Comprehensive and Detailed Explanation From Microsoft AB-620 Study Guide: Flow run history provides the chronological record needed to identify which executions succeeded, failed, timed out, or behaved differently. Opening the failed run details then exposes the action-level inputs, outputs, status, duration, connection errors, and failure message that explain the inconsistent result. These two views support evidence-based diagnosis without changing the flow before the cause is known. Updating the trigger, increasing a timeout, or changing connection behavior are potential remediations only after the failure pattern has been established. The Analytics summary is useful for aggregate trends but lacks the full payload and step sequence of an individual run. The Activity tab's Error column can help locate failures, but the question asks for the two complete diagnostic actions and the detailed run inspection is the more direct evidence. Reviewers should compare a failed run with a successful run using the same input, check transient versus deterministic errors, and redact or restrict access to sensitive data captured in run history. Study Guide alignment: Plan and configure agent solutions > Create and monitor agent flows in Copilot Studio > Monitor agent flows.