[Nov-2026] AB-620 Braindumps – AB-620 Questions to Get Better Grades
AB-620 Exam Dumps - Try Best AB-620 Exam Questions - Free4Torrent
NEW QUESTION # 53
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.
A company is configuring an agent in Copilot Studio that uses a generative answers node inside multiple topics.
The company requires responses to meet the following requirements:
- Must use an executive summary format.
- Must apply only within a specific topic.
- Must continue using configured knowledge sources.
- Must comply with connector security controls.
You need to configure a custom prompt to meet the formatting requirements.
Solution: Create a custom prompt tool in the specific topic that instructs the model to respond using an executive-summary structure.
Does the solution meet the goal?
- A. No
- B. Yes
Answer: B
Explanation:
Correct:
* Create a custom prompt tool in the specific topic that instructs the model to respond using an executive-summary structure.
To fulfill all the requirements in the best way, you must configure the custom instructions directly inside the specific Generative Answers node properties within that targeted topic.
By default, editing custom instructions at the global agent level or the Conversational boosting system topic applies globally. To scope formatting changes to only one topic while keeping configured data sources and security intact, you must override the instructions at the node level.
Incorrect:
* Add instructions in the custom prompt tool to restrict connector access during runtime.
* Configure the custom prompt tool at the topic level so that other topics are not affected.
* Remove the generative answers node and rely only on the custom prompt to produce formatted responses.
Reference:
https://learn.microsoft.com/en-us/microsoft-copilot-studio/nlu-boost-node
NEW QUESTION # 54
A company needs an agent in Copilot Studio to complete tasks by interacting with a legacy desktop application that does NOT have APIs.
To meet the business needs, the solution must meet the following requirements:
The agent must interact with the application's UI.
The execution must run on supported infrastructure.
The builder must be able to observe how the tool runs during execution.
You need to configure the agent based on the requirements.
Which setting should you configure for each requirement? To answer, move the appropriate settings to the correct requirements. You may use each setting 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.
Answer:
Explanation:
NEW QUESTION # 55
Users can add content to a paragraph field in a team-managed project, but they cannot @mention other users.
Identify the cause.
- A. Screen settings
- B. Notification settings
- C. Project permissions
- D. Global permissions
- E. Field settings
- F. Issue-level security settings
Answer: D
NEW QUESTION # 56
You need to determine which authentication model should be applied to each Blue Yonder Copilot interaction scenario to comply with the company's security and governance requirements.
Which authentication requirement should you apply to each scenario? To answer, move the appropriate authentication requirements to the correct user scenarios. You may use each authentication requirement 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.
Answer:
Explanation:
NEW QUESTION # 57
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.
A company is configuring an agent in Copilot Studio that uses a generative answers node inside multiple topics.
The company requires responses to meet the following requirements:
- Must use an executive summary format.
- Must apply only within a specific topic.
- Must continue using configured knowledge sources.
- Must comply with connector security controls.
You need to configure a custom prompt to meet the formatting requirements.
Solution: Configure the custom prompt tool at the topic level so that other topics are not affected.
Does the solution meet the goal?
- A. No
- B. Yes
Answer: A
Explanation:
Correct:
* Create a custom prompt tool in the specific topic that instructs the model to respond using an executive-summary structure.
To fulfill all the requirements in the best way, you must configure the custom instructions directly inside the specific Generative Answers node properties within that targeted topic.
By default, editing custom instructions at the global agent level or the Conversational boosting system topic applies globally. To scope formatting changes to only one topic while keeping configured data sources and security intact, you must override the instructions at the node level.
Incorrect:
* Add instructions in the custom prompt tool to restrict connector access during runtime.
* Configure the custom prompt tool at the topic level so that other topics are not affected.
* Remove the generative answers node and rely only on the custom prompt to produce formatted responses.
Reference:
https://learn.microsoft.com/en-us/microsoft-copilot-studio/nlu-boost-node
NEW QUESTION # 58
A solution containing an agent in Copilot Studio is deployed to multiple environments that require different configuration values.
Configuration values must vary by environment without modifying the solution contents.
Configuration values must meet the following requirements:
Allow values to be set during import.
Exclude values from the agent definition.
Run a dedicated agent instance for each individual environment.
You need to configure the application lifecycle management solution.
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.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
NEW QUESTION # 59
Case Study 1 - Blue Yonder Airlines
Background
Blue Yonder Airlines is a global carrier headquartered in Los Angeles, California, operating domestic and international flights. The company serves millions of passengers annually through its website, mobile app, and call centers. To improve customer service efficiency and reduce call center volume, Blue Yonder is deploying an AI agent in Microsoft Copilot Studio.
The agent will handle customer inquiries across multiple channels - web chat, mobile app, and Microsoft Teams (for internal support staff). It will answer questions, retrieve data from enterprise systems, and escalate to human agents when needed.
The project is led by a cross-function team:
- Product manager: Defines requirements and success metrics.
- Lead agent author: Designs topics, intents, and generative behavior.
- Flow designers: Build agent flows and integrations.
- IT/security and compliance: Oversees identity, data protection, and Responsible AI (RAI) compliance.
Current environment
Channels
Public website: Embedded web chat
Mobile app: In-app chatbot
Microsoft Teams: Internal support agent access
Identity and access
Customers: Anonymous access for general inquiries (e.g., flight status, baggage policy).
Authentication is required for personal data access (e.g., bookings, loyalty points).
Internal staff: Authenticate via Microsoft Entra ID.
Data sources
Reservation and Ticketing System (internal): REST API, no prebuilt connector with custom enterprise database.
Flight Status and Weather APIs (external): REST APIs with API keys.
Customer Support Knowledge Base: SharePoint library with PDFs and policy documents.
Loyalty Program Data: Stored in Dynamics 365 and Dataverse.
Travel Advisory Content: Uses REST API with partner services.
Integration mechanisms
Custom connectors must be used for internal APIs that lack prebuilt connectors.
HTTP request nodes may be used for lightweight external APIs.
Knowledge sources must be used for unstructured content.
Agent flows must be used to encapsulate reusable logic (e.g., rebooking).
Business requirements
Omnichannel support
Deploy the agent across web, mobile, and Teams with a consistent user experience. The Teams deployment must also support internal staff.
Self-service capabilities
The agent must handle common inquiries such as:
- Flight status
- Booking and rebooking
- Loyalty program questions
- Travel policies and baggage rules
Human escalation
If the agent cannot resolve an issue or the user requests help, it must:
- Escalate to a human agent.
- Transfer the conversation transcript and relevant context.
- Redact any sensitive personal data before escalation.
Knowledge integration
The agent must use scalable methods for knowledge integration and must not rely on manually authored Q&A topics for each document.
Performance metrics
First-contact resolution: +25%
Tier-1 call deflection: ≥20%
Response time: 90% of queries answered within 30 seconds
Accuracy: ≥95% for known FAQs
CSAT: ≥85% for AI-handled interactions
Technical requirements
Platform constraints
No custom code is permitted; only Copilot Studio's built-in tools may be used.
All backend logic must be implemented using agent flows.
Markdown must be used for formatting (e.g., bold, bullet points); HTML is not supported.
Authentication
Sign-in is required for personal data access.
Anonymous access is allowed for general inquiries.
User identity must be used for data access; shared or builder credentials must not be used.
Compliance and security
Power Platform DLP policies must be enforced to block unauthorized data flows.
Responsible AI content moderation filters must be enabled.
Prompt modifications must be added to enforce tone, disclaimers, and refusal behavior.
Disclaimers must be applied consistently across all generative responses. Manual edits to individual topics must be avoided.
Monitoring and maintenance
All conversations and actions must be logged for auditing.
Weekly reviews of transcripts and metrics must be conducted.
Topics, flows, and knowledge sources must be updated as policies or systems evolve.
Issues and constraints
API rate limits: External APIs (e.g., flight status) have usage limits. Agent flows must handle retries and caching to avoid exceeding quotas.
Knowledge base limits: Copilot Studio has limits on the number and size of indexed documents.
Large files must be split or summarized.
Generative answer risks: Generative responses must be constrained to avoid policy violations.
Prompt modifications and filters must be used to enforce tone, safety, and compliance.
User input variability: Users phrase questions in diverse ways. Topics must include varied trigger phrases and fallback handling.
Authentication UX: The agent must clearly explain when sign-in is required and handle transitions smoothly across channels.
Problem statement
Blue Yonder Airlines must deploy a secure, scalable, and policy-compliant AI agent using Microsoft Copilot Studio. The agent must deliver accurate, helpful, and safe responses across multiple channels, integrate with enterprise systems, and support both anonymous and authenticated users. It must adhere to strict data protection and Responsible AI standards while improving customer service efficiency and satisfaction.
Drag and Drop Question
You need to determine which authentication model should be applied to each Blue Yonder Copilot interaction scenario to comply with the company's security and governance requirements.
Which authentication requirement should you apply to each scenario? To answer, move the appropriate authentication requirements to the correct user scenarios. You may use each authentication requirement 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.
Answer:
Explanation:
Explanation:
Box 1: Allow anonymous access.
Scenario: Customers: Anonymous access for general inquiries (e.g., flight status, baggage policy).
Box 2: Require customer sign-in using an account.
Scenario: Authentication is required for personal data access (e.g., bookings, loyalty points).
Box 3: Require internal agent sign-in using Microsoft Entra ID.
Scenario: Internal staff: Authenticate via Microsoft Entra ID.
NEW QUESTION # 60
A company must enable an agent in Copilot Studio to execute operations exposed by an external MCP server.
The MCP server publishes callable tools and requires authentication.
The agent must be able to invoke MCP tools during conversations.
You need to configure MCP tools so the agent can execute MCP tool calls.
What should you do?
- A. Add a Power Platform connector as real-time knowledge to replace MCP tools.
- B. Enable generative answers so the model can automatically invoke MCP tools.
- C. Configure authentication for the MCP server connection used by the agent
- D. Publish the agent and rely on default settings for tool availability.
Answer: C
Explanation:
Comprehensive and Detailed Explanation From Microsoft AB-620 Study Guide: The agent needs a valid authenticated connection to the MCP server before it can discover and invoke the server's published tools. Copilot Studio supports the authentication methods exposed during MCP onboarding, including API key and OAuth 2.0. The choice must match the server: OAuth is appropriate for user-delegated authorization, while an API key is a shared secret mechanism. Publishing does not create credentials or make an unauthenticated server usable. A Power Platform connector used as real-time knowledge would serve a different retrieval pattern and would not replace the MCP tool contract. Generative answers also do not establish MCP connectivity; generative orchestration can select a tool only after that tool is correctly connected and described. The server and individual tools should have clear descriptions, typed inputs, and constrained permissions. Test the connection under the intended identity, confirm that only expected tools are visible, and implement error handling for consent, expired credentials, denied scopes, server unavailability, and invalid tool output. Study Guide alignment: Integrate and extend agents in Copilot Studio > Add tools to agents > Configure MCP tools.
NEW QUESTION # 61
You need to evaluate whether the current configuration decisions for the Blue Yonder Copilot agent comply with the company's security and governance policies.
Which compliance status should you assign to each configuration decision? To answer, move the appropriate compliance statuses to the correct configuration decisions. You may use each compliance status 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.
Answer:
Explanation:
NEW QUESTION # 62
You need to prevent an agent from using connectors that could send data to non-approved cloud services outside your organization. What should you configure?
- A. A knowledge source priority order
- B. A custom topic
- C. A Data Loss Prevention (DLP) policy in the Power Platform admin center
- D. A trigger phrase blocklist
Answer: C
Explanation:
DLP policies classify connectors as business or non-business and block data flow between them, preventing an agent from combining approved and unapproved connectors in the same flow.
NEW QUESTION # 63
You need to configure the Blue Yonder Copilot agent's responses in accordance with the company's content control and platform requirements.
Which two actions should you perform? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.
- A. Use Markdown syntax within response content.
- B. Insert HTML formatting directly into topic responses.
- C. Configure prompt instructions that include disclaimer text.
- D. Duplicate disclaimer text across reusable topics.
- E. Add required disclaimer text inside each individual topic.
Answer: A,C
Explanation:
B . Configure prompt instructions that include disclaimer text. Centralized prompt instructions apply the required disclaimer and behavioral controls consistently to generative responses. This avoids maintaining duplicate text in individual topics and reduces the risk of inconsistent compliance language. Microsoft confirms that prompt modifications can control response content, format, personality, and what the agent should or should not answer. Microsoft Learn: Prompt modification C . Use Markdown syntax within response content. The scenario explicitly requires Markdown for formatting and states that HTML is unsupported. Markdown can provide headings, bold text, lists, and other structured presentation while remaining compatible with the target channels.
Options A and E duplicate disclaimer content across topics, creating unnecessary maintenance and inconsistent responses when the disclaimer changes. Option D violates the stated platform requirement because HTML must not be used.
NEW QUESTION # 64
A company is configuring generative answers for an agent in Copilot Studio.
The agent must use Azure AI Search to retrieve enterprise content, and all responses must be generated by a Microsoft Foundry model.
The agent sometimes generates answers that are not grounded in Azure AI Search content. The company requires that the agent only generate responses when relevant indexed content is retrieved.
You need to configure the agent so that its generative answer behavior meets the organization's requirements.
What should you do?
- A. Enable conversational boosting and select a Foundry-approved model.
- B. Require grounding for generative answers and use Azure AI Search as the retrieval source.
- C. Enable citations and configure a public model endpoint.
- D. Use Azure AI Search as a fallback source and enable answer expansion.
- E. Upload documents into the agent and disable fallback responses.
Answer: B
Explanation:
Comprehensive and Detailed 150 to 250 words of Explanation From [Microsoft AB-620 study guide]: Azure AI Search must be configured as the authoritative retrieval source, with ungrounded or general-knowledge responses disabled. In the retrieval-augmented generation process, Copilot Studio first reformulates the user's question, searches the connected vector index, and supplies relevant results to the Microsoft Foundry-hosted model for response generation. Requiring grounding prevents the model from answering solely from its pretrained knowledge when Azure AI Search returns no sufficiently relevant content. In that situation, the agent should return no generated answer and follow its configured fallback or escalation behavior. Selecting a Foundry model alone does not enforce grounding because model selection controls the generation layer, not the retrieval requirement. Citations provide traceability but likewise do not prevent an unsupported answer. Uploading duplicate documents would introduce another knowledge store and undermine Azure AI Search as the controlled enterprise index. The Azure AI Search connection should identify the intended vector index and use semantic ranking where appropriate. Testing should confirm that valid queries return supported answers and citations, while out-of-scope queries produce no ungrounded response. Study Guide alignment: Integrate and extend agents in Copilot Studio → Connect to Azure AI Search; Integrate agents with Azure → Configure generative answers by using Azure AI Search with Foundry.
NEW QUESTION # 65
A company uses an agent in Copilot Studio to generate structured responses for internal users.
The agent must meet the following requirements:
- Consistently follow a reusable instruction template for response tone and structure.
- Use an enterprise-approved foundation model for responses generated
through the template.
You need to configure custom prompts so the agent uses the Microsoft Foundry model catalog.
Which two actions should you perform? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.
- A. Enable citations, so the model is restricted to approved outputs.
- B. Select a model from the Foundry model catalog for the custom prompt configuration.
- C. Allow topic authors to define tone and structure directly in topic steps.
- D. Create a custom prompt template and apply it where the agent generates the structured response.
- E. Publish the agent to apply the Foundry model selection automatically.
- F. Configure Azure AI Search as the grounding source, so the model choice is enforced.
Answer: B,D
Explanation:
To configure your Copilot Studio agent to use an enterprise-approved model from the Microsoft Foundry model catalog and apply a consistent, reusable instruction template, follow these exact technical steps:
[D] Step 1: Select and Connect the Model from the Foundry Catalog
You must bridge your Microsoft Foundry (Azure AI Foundry) deployment with Copilot Studio via the prompt configuration panel.
[E] Step 2: Create the Template and Apply It to the Agent Flow
Now, write the reusable instruction template for structured responses and map it to your conversation topics.
Reference:
https://learn.microsoft.com/en-us/microsoft-365/copilot/employee-self-service/design-best-practices
NEW QUESTION # 66
Drag and Drop Question
A company plans to use Copilot connectors to ground answers from a third-party system for an agent in Copilot Studio.
To meet the business needs, responsibilities for configuring and using Copilot connectors must be separated, based on the following requirements:
- For tenant administration, the connector must be available at the
tenant level.
- For agent runtime behavior, answers must be grounded from authorized
sources.
- For builder configuration, you must add the connector to the agent.
You need to determine how Copilot connector set-up responsibilities are handled across tenant, runtime, and builder stages.
What should you configure for each requirement? To answer, move the appropriate configuration 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.
Answer:
Explanation:
Explanation:
Box 1: Configure the Copilot connector in Microsoft 365 Admin Center
To make a Copilot connector available at the tenant level for grounding agent responses in Microsoft Copilot Studio, you must configure and deploy the connector in the Microsoft 365 Admin Center.
Tenant Administration (Microsoft 365 Admin Center): Tenant administrators must configure and deploy the specific Copilot connector (e.g., ServiceNow, Salesforce, Box) within the Microsoft 365 Admin Center. This process indexes the necessary content from your third-party system across the enterprise so it can be utilized by your organization's agents.
Box 2: Add the Copilot connector as a knowledge source
To use a Copilot connector as an enterprise knowledge source in Microsoft Copilot Studio, the prerequisite configuration requires the builder to add the Copilot connector as a knowledge source.
The Builder Stage: While your AI or tenant administrator is responsible for deploying and configuring the Copilot connector in the Microsoft 365 admin center, the builder stage handles agent-specific knowledge mapping. [Box 3 below] Knowledge Integration: As an agent builder, you must actively select the preconfigured Copilot connector from the available list and add it as a knowledge source to your agent's generative answers node.
Runtime Behavior: Once this is configured, the Copilot engine indexes and queries the third-party data securely at runtime. Because the connector is tied to your tenant's security parameters, the agent will only ground answers using authorized sources and fully respect source-level permissions.
Box 3: Configure the Copilot connector in Microsoft 365 Admin Center
The initial deployment and central management of a Copilot connector must be performed in the Microsoft 365 Admin Center by a tenant administrator. However, completing the builder configuration to add the connector as a knowledge source for a specific agent is done directly within Microsoft Copilot Studio.
Reference:
https://learn.microsoft.com/en-us/microsoft-365/copilot/connectors/deployment-overview
NEW QUESTION # 67
Case Study 2 - Fabrikam Inc.
Background
Fabrikam Inc. is a Canada-based manufacturer with a growing service organization that supports field technicians and internal operations teams. Fabrikam Inc. plans to launch a new internal agent solution named Operations Concierge to reduce time spent searching policy content, retrieving operational metrics, and executing routine transactions.
The agent will be used by three groups:
- Service coordinators who triage incoming service requests
- Field technicians who need guided procedures and parts availability
- Operations managers who monitor KPIs and exceptions
The agent solution must work in real-world operational conditions. Users often ask questions mid- call with a customer or while coordinating parts shipments. The agents require quick, reliable outcomes. As a result, Fabrikam Inc. requires the solution to:
- Provide grounded answers with traceability when it provides guidance.
- Retrieve real-time metrics when users ask for operational status.
- Execute authenticated updates when users initiate a flow (such as creating a parts request).
Fabrikam Inc. also expects the solution to be maintained by multiple makers and developers across the year. The company has experienced duplicated logic and inconsistent behavior across different agents. This project emphasizes reuse, governance, and maintainability across teams.
Current environment
Fabrikam Inc. runs three Microsoft Power Platform environments for agent development and release: Dev, Test, and Prod.
The team plans to build the agent and validate it in Dev and Test, then promote to Prod by using a controlled release process that supports repeatable deployments.
Fabrikam Inc. already has two assets the team wants to reuse:
- A partially completed Copilot Studio agent named Service Desk Agent, used by IT to create internal tickets and route requests
- A Microsoft Foundry agent created by a central AI team that performs specialized summarization and classification for long-form text (for example, summarizing call transcripts into an incident narrative) Fabrikam Inc. also has operational and knowledge data sources:
- A curated policy library (internal SOPs, service warranty rules, escalation criteria, and standard operating procedures)
- A set of indexed documents and procedures in an Azure AI Search service that supports vector search for the policy library
- A Microsoft Fabric workspace that includes a semantic model used by operations leadership for reporting Business requirements Fabrikam Inc. requires Operations Concierge to meet the following business requirements:
- Traceability requirement: When the agent provides policy guidance or procedural recommendations, users must be able to see where the answer came from.
- Metrics requirement: When users ask about service performance (backlog, SLA risk, parts shortages, dispatch delays), the solution must return up-to-date metrics in a structured format that operations managers can use in weekly reviews.
- Transaction requirement: The solution must support authenticated updates initiated during conversations, including creating a parts request and updating a service case status.
In addition, Fabrikam Inc. wants to avoid duplicating common assets across agents:
- The team must reuse the same set of escalation topics, MCP tool definitions, and a standard safety disclaimer across three different agents.
- Only the platform engineering group as allowed to edit shared assets. However, all agent authors must be able to use them.
Technical requirements
The Fabrikam Inc. solution architecture uses a multi-agent approach so that specialist responsibilities are isolated and can evolve independently.
The Operations Concierge (primary agent) must coordinate the following specialist capabilities:
- Policy and procedure Q&A: Use an enterprise knowledge source that supports indexed retrieval across the curated policy library and service procedures.
- Operational metrics: Delegate metric queries to a Fabric Data Agent that reads governed business data through the Fabric semantic model.
- Authenticated updates: Use tools exposed by an existing internal Model Context Protocol (MCP) server that provides transactional operations for the service organization.
- Specialized processing: Delegate summarization and classification requests to an existing Microsoft Foundry agent.
Fabrikam Inc. will onboard two MCP servers as tools:
- PartsOps MCP server: exposes tools for parts availability checks and parts request creation.
The server requires per-user authentication because actions must be traceable to the requesting user.
- WarrantyRules MCP server: exposes a read-only tool for validating warranty coverage. The server uses an API key shared by the agent team.
Fabrikam Inc. has also defined a collaboration requirement with the existing Service Desk Agent:
- The primary agent must delegate IT-specific requests to the existing Service Desk Agent rather than reimplement ticket creation logic.
Finally, Fabrikarn Inc. plans to support a partner integration:
- For shipment tracking inquiries, Fabrikam Inc. will delegate to a partner-provided agent that is only available through a standardized agent-to-agent endpoint.
Issues and constraints
During early testing, Fabrikam Inc. found three recurring problems:
- Makers are copying and modifying the same components across agents, resulting in inconsistent disclaimers and duplicated tools.
- Users can obtain a correct answer, but the response is not consistently traceable to a source when the agent uses knowledge.
- The primary agent can route some requests, but specialist capabilities are not consistently delegated (for example, some metric questions are answered generatively instead of being routed to the Fabric Data Agent).
You are part of the engineering team responsible for correcting the design and configuration to meet the preceding requirements and constraints.
You need to configure Operations Concierge so that prompt-driven summarization behavior aligns with Fabrikam Inc.'s architectural requirements.
Which two actions should you perform? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.
- A. Select a model from the Foundry model catalog in the custom prompt configuration.
- B. Enable citations to control how summarization output is generated.
- C. Configure Azure AI Search as the grounding source for summarization prompts.
- D. Publish the agent to ensure the selected model is enforced for summarization.
- E. Create a reusable custom prompt template and apply it where summarization responses are generated.
Answer: A,E
Explanation:
Scenario: Specialized processing: Delegate summarization and classification requests to an existing Microsoft Foundry agent.
[C] Model Selection: Choosing a specific model from the Foundry catalog ensures that your classification and summarization requests are routed directly to the correct, optimized LLM backend within the Microsoft Foundry ecosystem.
[E] Custom Prompt Templates: Creating and applying a reusable template ensures consistent formatting, tone, and logic across all areas where your agent handles summarization and classification tasks.
Reference:
https://learn.microsoft.com/en-us/microsoft-copilot-studio/bring-your-own-model-prompts
https://learn.microsoft.com/en-us/microsoft-copilot-studio/nlu-prompt-node
NEW QUESTION # 68
Drag and Drop Question
A company has an existing custom connector that is approved and available in the environment.
A builder wants an agent in Copilot Studio to call the connector during a conversation to retrieve information from an internal system.
To meet the business needs, the solution must meet the following requirements:
- The agent must make the connector available for topic steps.
- The agent must run the connector call with a valid connection.
- The connector call must receive the required input values at runtime.
You need to configure the agent so the custom connector can be used as a tool.
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.
Answer:
Explanation:
Explanation:
Box 1: Add the connector as a tool in the agent.
To make an approved custom connector available for topic steps within Copilot Studio, you must add the connector as a tool in the agent.
In Copilot Studio, actions and custom connectors must be explicitly registered as "Tools" within the agent's capabilities before they can be recognized or called by topics.
Box 2: Create or reuse a connection for the connector
The appropriate action is to create or reuse an existing connection for the custom connector.
Because the connector is already approved and available in your environment, you can simply select it from your tools and link the predefined connection Use connectors in Copilot Studio agents.
Box 3: Map topic variables to the tool inputs
The correct configuration action is to Map topic variables to the tool inputs.
Reference:
https://learn.microsoft.com/en-us/microsoft-copilot-studio/advanced-connectors
NEW QUESTION # 69
......
Verified AB-620 exam dumps Q&As with Correct 101 Questions and Answers: https://validdumps.free4torrent.com/AB-620-valid-dumps-torrent.html