DRAG DROP (Drag and Drop is not supported)A company is building an agent in Copilot Studio topic that must retrieve real-time status information from an external REST API using a Send HTTP request node.To meet the business needs, the topic must meet the following requirements:-The request must include the required authentication header.-The request must call the endpoint using the correct HTTP method.-The response must be configured with an appropriate response data type based on a schema and saved so the topic can reuse the returned values.You need to configure the Send HTTP request node.Which configuration should you use 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.Select and Place:
Answer(s): A
Box 1: Add required headers to the HTTP request To configure the Send HTTP request node to include the required authentication header, you should add required headers to the HTTP request.Authentication details for external REST APIs (such as API keys or Bearer tokens) are almost universally passed inside the metadata of the call, which is managed in the Headers.Box 2: Set the method to GET in the HTTP request. To retrieve real-time status information from an external REST API using a Send HTTP request node in Copilot Studio, you should set the method to GET in the HTTP request.The standard HTTP GET method is specifically designed to fetch or retrieve data from a server without modifying it.Box 3: Select JSON data type and save response to a variable When retrieving real-time data, the primary configuration requirement is telling Copilot Studio how to interpret the incoming data (JSON) and storing it in a custom variable so subsequent nodes in your topic can use it.
https://learn.microsoft.com/en-us/microsoft-copilot-studio/authoring-http-node
A company is deploying an agent for employees.The company has the following requirements:-Access must be restricted to the internal employees only.-End-user authentication must be enforced.You need to configure the agent based on the company requirements.What should you do?
To enforce strict internal-only access and require end-user authentication for a Microsoft Copilot Studio agent, you must configure Microsoft Entra ID authentication.This setup stops external users from chatting with the agent and forces employees to sign in with their corporate accounts before they can access any data.The implementation requires a mix of tenant-level governance policies and specific agent security configurations.
https://learn.microsoft.com/en-us/microsoft-copilot-studio/configuration-end-user-authentication
DRAG DROP (Drag and Drop is not supported)A company is integrating an agent in Copilot Studio into a custom application by using the Microsoft 365 Agents SDK.The company has the following requirements for the application:-The deployment workflow must follow a dependency driven sequence.-The agent must be published before configuration values are retrieved.-End-to-end validation must occur before production deployment.You need to plan the deployment workflow to integrate the agent.In which order should you perform the actions? To answer, move all actions from the list of actions to the answer area and arrange them in the correct order.Select and Place:
Step 1: Publish the agent Based on the second requirement, the agent must be published first before any configuration values can be generated or retrieved.Step 2: Retrieve the current agent configuration values Once published, you can extract the necessary configuration properties (such as the Agent ID and Tenant ID) required to connect your applications and infrastructure.Step 3: Configure and enable the agent's target integration channel Before configuring the SDK code, you must enable the target channel (such as the Custom App or Mobile App channel) within Copilot Studio Channels to permit incoming external connection requests. Step 4: Implement the Microsoft 365 Agents SDK in the app using the agent configuration With the channels enabled and configurations in hand, your developers can now write the code to implement the Microsoft 365 Agents SDK into your custom application.Step 5: Validate the end-to-end conversation workflow in a test environment Following the third requirement, end-to-end validation must happen prior to production deployment. This step ensures the chat interface, authentication, and SDK pipelines function flawlessly.Step 6: Deploy the web app to production Once validation passes successfully, the final step is to push your custom application live to your production environment.
https://www.linkedin.com/pulse/microsoft-365-agents-sdk-integrating-copilot-studio-custom-sokolov-dcche
An agent in Copilot Studio already exists in a development environment.You need to prepare the agent so it can be moved to a production environment using the supported solution-based approach.You need to create an exportable package that contains the existing agent.Which two actions should you perform? Each correct answer presents part of the solution.Note: Each correct selection is worth one point.
Answer(s): B,E
To move a Copilot Studio agent to a production environment using a solution-based approach, you must create a custom unmanaged solution, add your existing agent [E] and its required objects to it, publish all customizations, and export the solution as a managed package [B] [.zip file].
https://techcommunity.microsoft.com/blog/modernworkappconsult/how-to-export-an-agent-developed-in-copilot-studio/4391562
HOTSPOT (Drag and Drop is not supported)A company wants to use content from a non-Microsoft enterprise knowledge base to ground agent responses.To meet the business needs, the knowledge source must meet the following requirements:-Support grounding from indexed data.-Use existing access controls from the source system.-Support read-only operations.You need to determine the correct behavior to meet the requirements.Which behavior meets each requirement? To answer, select the appropriate options in the answer area.Note: Each correct selection is worth one point.Hot Area:
Box 1: Retrieve indexed content To ground a Copilot agent in an external enterprise knowledge base using indexed data, you need to configure Retrieve indexed content.This process relies on Retrieval-Augmented Generation (RAG). Instead of relying on a pre-trained model or executing live API queries during the conversation, the system references a periodically updated, synchronized index of your knowledge base.Box 2: Respect existing permissions. To ensure that the Copilot agent responses respect the existing access controls and source-level permissions of your non-Microsoft enterprise knowledge base, you must configure Respect existing permissions.Respect existing permissions: This setting ensures the agent operates on a user-delegated permission model. The Copilot agent dynamically trims and limits search results at runtime, meaning the end-user will only receive answers derived from data they explicitly have authorization to view in the external source system.Incorrect: Respect existing permissions from agent authors: This incorrect option would ground responses based entirely on the author's access level during the creation process, potentially leaking sensitive data to unauthorized end-users.Box 3: Prevent transactional updates To ground Microsoft Copilot agent responses using a non-Microsoft enterprise knowledge base with read-only operations, you must configure Prevent transactional updates.This configuration ensures that the Copilot agent can only fetch, read, and query data from your enterprise knowledge base. It explicitly blocks any modifications, insertions, or deletions, adhering strictly to your read-only requirement and protecting your source data from accidental alterations.
https://learn.microsoft.com/en-us/microsoft-copilot-studio/knowledge-copilot-connectors
Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear on the review screen.An agent uses a flow that calls an external service which can occasionally fail or time out.When a failure occurs, the agent must meet the following requirements:-Must not terminate silently.-Must send a notification containing the error details.You need to configure the agent flow so that failures are handled in a controlled and predictable way.Solution: Retry the failing action without handling failure.Does the solution meet the goal?
Answer(s): B
Correct: * Configure run after conditions for failure paths. You should configure the "Run after" conditions in Power Automate (the underlying flow engine) to handle these failures in a controlled and predictable way.By default, a cloud flow step only runs if the previous step is successful. If your external service fails or times out, all subsequent steps will normally skip, causing the flow to fail silently from the perspective of the Copilot Studio agent.How to Configure the Flow for Failure Handling To meet your requirements, you need to create a parallel or sequential failure path using the following steps:1. Add your Notification Action2. Configure "Run After" SettingsIncorrect:* Retry the failing action without handling failure.* Send a notification with relevant error details.
https://www.matthewdevaney.com/3-power-automate-error-handling-patterns-you-must-know/
Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear on the review screen.An agent uses a flow that calls an external service which can occasionally fail or time out.When a failure occurs, the agent must meet the following requirements:-Must not terminate silently.-Must send a notification containing the error details.You need to configure the agent flow so that failures are handled in a controlled and predictable way.Solution: Configure run after conditions for failure paths.Does the solution meet the goal?
Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear on the review screen.An agent uses a flow that calls an external service which can occasionally fail or time out.When a failure occurs, the agent must meet the following requirements:-Must not terminate silently.-Must send a notification containing the error details.You need to configure the agent flow so that failures are handled in a controlled and predictable way.Solution: Send a notification with relevant error details.Does the solution meet the goal?
Post your Comments and Discuss Microsoft AB-620 exam prep with other Community members:
Our website is free, but we have to fight against AI bots and content theft. We're sorry for the inconvenience caused by these security measures. You can access the rest of the AB-620 content, but please register or login to continue.