Revizo / Microsoft / AB-620

MICROSOFT CERTIFICATION STUDY GUIDE

AB-620 practice questions.
Prepare with a clearer plan.

Validates ability to design, build, extend, and integrate enterprise-grade AI agent solutions using Microsoft Copilot Studio, Power Platform, and Azure AI services.

Download Revizo
Revizo certification practice question on iPhone

What to know about AB-620.

Validates ability to design, build, extend, and integrate enterprise-grade AI agent solutions using Microsoft Copilot Studio, Power Platform, and Azure AI services.

Format
Multiple choice and scenario-based questions (single and multiple response)
Duration
120 minutes
Passing score
700/1000
Recommended experience
Experience building agents in Copilot Studio; intermediate generative AI knowledge; familiarity with REST APIs, Power Platform, Dataverse, and Microsoft Foundry

Exam details are based on the available Microsoft catalogue information. Confirm current requirements with the exam provider before booking.

How to prepare for AB-620.

Use the provider's current objectives as your source of truth, then organise your Revizo sessions around the Microsoft technologies, product capabilities and implementation decisions named in the certification. The AB-620 exam is listed as Multiple choice and scenario-based questions (single and multiple response); your starting point should reflect Experience building agents in Copilot Studio; intermediate generative AI knowledge; familiarity with REST APIs, Power Platform, Dataverse, and Microsoft Foundry.

01

Map the official objectives.

Read the current Microsoft objectives and make a short list of the areas you need to revisit before booking AB-620.

02

Practise one area at a time.

Select AB-620 in Revizo and use focused question sessions to test one topic or decision type at a time, rather than relying on a single long cram session.

03

Review, then repeat.

Use your results to return to incorrect answers, revisit the official material behind them and repeat short AB-620 practice sessions until the gaps are clearer.

FREE PRACTICE PREVIEW

Read the first 20
AB-620 questions.

Review each question, its correct answer and any available source explanation before continuing your certification study in Revizo.

FIRST 20 QUESTIONS

Answers & available explanations

QUESTION 1

DRAG DROP -

Case Study -
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam time as you would like to complete each case study. However, there might be additional case studies or other exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections that follow this case study.
To answer the case study questions, you will need to reference information that is provided in the case. Case studies and associated questions might contain exhibits or other resources that provide more information about the scenario described in the case. Information provided in an individual question does not apply to the other questions in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change your answers before you move to the next exam section. After you leave this case study, you will NOT be able to return to it.

To start the case study -
To display the first question in this case study, select the 'Next' button. To the left of the question, a menu provides links to information such as business requirements, the existing environment, and problem statements. Please read through all this information before answering any questions. When you are ready to answer a question, select the 'Question' button to return to the question.

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.


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.
You need to configure the agent in Copilot Studio to meet Blue Vender's Responsible AI and data protection requirements.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.

Item 1

  1. AA. Add custom prompt modifications.
  2. BB. Conduct adversarial testing.
  3. CC. Define Data Loss Prevention (DLP) policies.
  4. DD. Integrate with Microsoft Purview.
  5. EE. Disable generative answers.
  6. FF. Configure content moderation filters.

Item 2

  1. AA. Add custom prompt modifications.
  2. BB. Conduct adversarial testing.
  3. CC. Define Data Loss Prevention (DLP) policies.
  4. DD. Integrate with Microsoft Purview.
  5. EE. Disable generative answers.
  6. FF. Configure content moderation filters.

Item 3

  1. AA. Add custom prompt modifications.
  2. BB. Conduct adversarial testing.
  3. CC. Define Data Loss Prevention (DLP) policies.
  4. DD. Integrate with Microsoft Purview.
  5. EE. Disable generative answers.
  6. FF. Configure content moderation filters.
Show answer & explanation

Correct answer: Item 1: C · Item 2: F · Item 3: A

ExplanationConfigure DLP policies first, enable Responsible AI content moderation filters, then add custom prompt modifications for tone, disclaimers, and refusal behavior per Blue Yonder requirements. Reference: https://learn.microsoft.com/microsoft-copilot-studio/guidance/rai

QUESTION 2

DRAG DROP -

Case Study -
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam time as you would like to complete each case study. However, there might be additional case studies or other exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections that follow this case study.
To answer the case study questions, you will need to reference information that is provided in the case. Case studies and associated questions might contain exhibits or other resources that provide more information about the scenario described in the case. Information provided in an individual question does not apply to the other questions in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change your answers before you move to the next exam section. After you leave this case study, you will NOT be able to return to it.

To start the case study -
To display the first question in this case study, select the 'Next' button. To the left of the question, a menu provides links to information such as business requirements, the existing environment, and problem statements. Please read through all this information before answering any questions. When you are ready to answer a question, select the 'Question' button to return to the question.

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.


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.
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.

Item 1

  1. AA. Compliant
  2. BB. Non-compliant

Item 2

  1. AA. Compliant
  2. BB. Non-compliant

Item 3

  1. AA. Compliant
  2. BB. Non-compliant

Item 4

  1. AA. Compliant
  2. BB. Non-compliant
Show answer & explanation

Correct answer: Item 1: A · Item 2: B · Item 3: B · Item 4: B

ExplanationAnonymous access is allowed for general inquiries. Open web search, missing custom RAI instructions, and shared admin credentials violate Blue Yonder security and governance requirements.

QUESTION 3

Case Study -
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam time as you would like to complete each case study. However, there might be additional case studies or other exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections that follow this case study.
To answer the case study questions, you will need to reference information that is provided in the case. Case studies and associated questions might contain exhibits or other resources that provide more information about the scenario described in the case. Information provided in an individual question does not apply to the other questions in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change your answers before you move to the next exam section. After you leave this case study, you will NOT be able to return to it.

To start the case study -
To display the first question in this case study, select the 'Next' button. To the left of the question, a menu provides links to information such as business requirements, the existing environment, and problem statements. Please read through all this information before answering any questions. When you are ready to answer a question, select the 'Question' button to return to the question.

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.


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.
You need to deploy the Blue Yonder Copilot agent to the public website and Microsoft Teams while ensuring compliance with the company's security and Responsible AI requirements.
Which two actions should you perform before making the agent available on both channels? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.

  1. AA. Configure prompt modifications to enforce tone, disclaimers, and refusal behavior at the system level.
  2. BB. Manually add disclaimers to each topic before publishing.
  3. CC. Embed the web channel and then rely on channel-level settings to enforce content moderation.
  4. DD. Configure Power Platform DLP policies to restrict unauthorized data connectors.
  5. EE. Publish the agent and then enable Responsible AI filters individually for each channel.
Show answer & explanation

Correct answer: A, D

ExplanationConfigure system-level prompt modifications and Power Platform DLP policies before publishing to web and Teams channels. Case study requires consistent disclaimers via prompt modifications and DLP enforcement.

QUESTION 4

Case Study -
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam time as you would like to complete each case study. However, there might be additional case studies or other exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections that follow this case study.
To answer the case study questions, you will need to reference information that is provided in the case. Case studies and associated questions might contain exhibits or other resources that provide more information about the scenario described in the case. Information provided in an individual question does not apply to the other questions in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change your answers before you move to the next exam section. After you leave this case study, you will NOT be able to return to it.

To start the case study -
To display the first question in this case study, select the 'Next' button. To the left of the question, a menu provides links to information such as business requirements, the existing environment, and problem statements. Please read through all this information before answering any questions. When you are ready to answer a question, select the 'Question' button to return to the question.

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.


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.
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.

  1. AA. Add required disclaimer text inside each individual topic.
  2. BB. Configure prompt instructions that include disclaimer text.
  3. CC. Use Markdown syntax within response content.
  4. DD. Insert HTML formatting directly into topic responses.
  5. EE. Duplicate disclaimer text across reusable topics.
Show answer & explanation

Correct answer: B, C

ExplanationUse prompt instructions for disclaimer text and Markdown for formatting; HTML is not supported in Copilot Studio.

QUESTION 5

Case Study -
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam time as you would like to complete each case study. However, there might be additional case studies or other exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections that follow this case study.
To answer the case study questions, you will need to reference information that is provided in the case. Case studies and associated questions might contain exhibits or other resources that provide more information about the scenario described in the case. Information provided in an individual question does not apply to the other questions in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change your answers before you move to the next exam section. After you leave this case study, you will NOT be able to return to it.

To start the case study -
To display the first question in this case study, select the 'Next' button. To the left of the question, a menu provides links to information such as business requirements, the existing environment, and problem statements. Please read through all this information before answering any questions. When you are ready to answer a question, select the 'Question' button to return to the question.

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.


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.
You need to configure the agent in Copilot Studio to use internal and external partner knowledge sources to answer user questions about the airline services.
Which two actions should you perform? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.

  1. AA. Use a Microsoft Graph connector to index the partner's travel advisory content.
  2. BB. Write individual Q&A pairs for each document as separate topics.
  3. CC. Enable unrestricted web search for the agent.
  4. DD. Add the internal policy documents as a knowledge source.
Show answer & explanation

Correct answer: A, D

ExplanationAdd internal policy documents as a knowledge source and use a connector to index partner travel advisory content. Avoid manual Q&A topics and unrestricted web search.

QUESTION 6

Case Study -
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam time as you would like to complete each case study. However, there might be additional case studies or other exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections that follow this case study.
To answer the case study questions, you will need to reference information that is provided in the case. Case studies and associated questions might contain exhibits or other resources that provide more information about the scenario described in the case. Information provided in an individual question does not apply to the other questions in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change your answers before you move to the next exam section. After you leave this case study, you will NOT be able to return to it.

To start the case study -
To display the first question in this case study, select the 'Next' button. To the left of the question, a menu provides links to information such as business requirements, the existing environment, and problem statements. Please read through all this information before answering any questions. When you are ready to answer a question, select the 'Question' button to return to the question.

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.


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.
You need to ensure that every AI-generated response from the agent in Copilot Studio includes a disclaimer that complies with the company's security and governance policies.
Which two actions should you perform? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.

  1. AA. Add a greeting message that includes the disclaimer.
  2. BB. Add a prompt modification in the generative answers node settings.
  3. CC. Create a disclaimer topic that always runs first.
  4. DD. Disable generative answers and use only pre-authored responses.
  5. EE. Edit every topic's first message to include the disclaimer.
Show answer & explanation

Correct answer: A, B

ExplanationAdd prompt modifications in generative answers node settings and include disclaimer text in the greeting message to ensure AI-generated responses include required disclaimers consistently. Reference: https://learn.microsoft.com/microsoft-copilot-studio/generative-answers

QUESTION 7

DRAG DROP -

Case Study -
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam time as you would like to complete each case study. However, there might be additional case studies or other exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections that follow this case study.
To answer the case study questions, you will need to reference information that is provided in the case. Case studies and associated questions might contain exhibits or other resources that provide more information about the scenario described in the case. Information provided in an individual question does not apply to the other questions in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change your answers before you move to the next exam section. After you leave this case study, you will NOT be able to return to it.

To start the case study -
To display the first question in this case study, select the 'Next' button. To the left of the question, a menu provides links to information such as business requirements, the existing environment, and problem statements. Please read through all this information before answering any questions. When you are ready to answer a question, select the 'Question' button to return to the question.

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.


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.
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.

Item 1

  1. AA. Allow anonymous access.
  2. BB. Require customer sign-in using an account.
  3. CC. Require internal agent sign-in using Microsoft Entra ID.
  4. DD. Use agent author credentials for authenticated data calls.

Item 2

  1. AA. Allow anonymous access.
  2. BB. Require customer sign-in using an account.
  3. CC. Require internal agent sign-in using Microsoft Entra ID.
  4. DD. Use agent author credentials for authenticated data calls.

Item 3

  1. AA. Allow anonymous access.
  2. BB. Require customer sign-in using an account.
  3. CC. Require internal agent sign-in using Microsoft Entra ID.
  4. DD. Use agent author credentials for authenticated data calls.
Show answer & explanation

Correct answer: Item 1: A · Item 2: B · Item 3: C

ExplanationGeneral policy questions allow anonymous access; personal booking data requires customer sign-in; internal staff must authenticate with Microsoft Entra ID.

QUESTION 8

DRAG DROP -
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.

Item 1

  1. AA. Map topic variables to the tool inputs.
  2. BB. Add the connector as a tool in the agent.
  3. CC. Add the connector as a knowledge source.
  4. DD. Create or reuse a connection for the connector.

Item 2

  1. AA. Map topic variables to the tool inputs.
  2. BB. Add the connector as a tool in the agent.
  3. CC. Add the connector as a knowledge source.
  4. DD. Create or reuse a connection for the connector.

Item 3

  1. AA. Map topic variables to the tool inputs.
  2. BB. Add the connector as a tool in the agent.
  3. CC. Add the connector as a knowledge source.
  4. DD. Create or reuse a connection for the connector.
Show answer & explanation

Correct answer: Item 1: B · Item 2: D · Item 3: A

ExplanationAdd the connector as an agent tool, create or reuse a connection for authentication, and map topic variables to tool inputs at runtime.

QUESTION 9

DRAG DROP -
A company needs to ground an agent in Copilot Studio answers using live enterprise data from a supported system via a Microsoft Power Platform connector.
To meet the business needs, the builder must meet the following requirements:
Authenticate using a valid connection.
Add the connector as a real-time knowledge source.
Select the tables for knowledge grounding.
You need to add a Power Platform connector as a real-time knowledge source for 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.

Item 1

  1. AA. Select Sign in and create a new connection or reuse an existing connection.
  2. BB. Select the tables to include as the knowledge source.
  3. CC. Select Add knowledge from the agent Knowledge experience.
  4. DD. Select the real-time connector from the Add knowledge dialog.
  5. EE. Select Add to agent to complete the connection.

Item 2

  1. AA. Select Sign in and create a new connection or reuse an existing connection.
  2. BB. Select the tables to include as the knowledge source.
  3. CC. Select Add knowledge from the agent Knowledge experience.
  4. DD. Select the real-time connector from the Add knowledge dialog.
  5. EE. Select Add to agent to complete the connection.

Item 3

  1. AA. Select Sign in and create a new connection or reuse an existing connection.
  2. BB. Select the tables to include as the knowledge source.
  3. CC. Select Add knowledge from the agent Knowledge experience.
  4. DD. Select the real-time connector from the Add knowledge dialog.
  5. EE. Select Add to agent to complete the connection.

Item 4

  1. AA. Select Sign in and create a new connection or reuse an existing connection.
  2. BB. Select the tables to include as the knowledge source.
  3. CC. Select Add knowledge from the agent Knowledge experience.
  4. DD. Select the real-time connector from the Add knowledge dialog.
  5. EE. Select Add to agent to complete the connection.

Item 5

  1. AA. Select Sign in and create a new connection or reuse an existing connection.
  2. BB. Select the tables to include as the knowledge source.
  3. CC. Select Add knowledge from the agent Knowledge experience.
  4. DD. Select the real-time connector from the Add knowledge dialog.
  5. EE. Select Add to agent to complete the connection.
Show answer & explanation

Correct answer: Item 1: C · Item 2: D · Item 3: A · Item 4: B · Item 5: E

ExplanationStart from Knowledge, choose the real-time connector, authenticate, select tables, then add to the agent.

QUESTION 10

HOTSPOT -
You deploy an agent in Microsoft Copilot Studio that triggers a cloud flow to update customer records in Microsoft Dataverse.
You observe the following after deploying the agent:
Several runs fail due to a temporary authentication issue.
The flow continues to trigger and generate additional failed runs.
You must:
Stop additional failed executions while troubleshooting.
Process a failed execution after resolving the authentication issue.
Validate if the most recent executions succeeded immediately after resolution.
You need to use the appropriate monitoring and management actions to restore normal flow operation and validate successful execution.
Which action should you perform for each requirement? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

Item 1

  1. AA. Delete the flow.
  2. BB. Disable the flow.
  3. CC. Cancel the most recent run.
  4. DD. Modify the trigger condition.

Item 2

  1. AA. Restart the flow.
  2. BB. Refresh the flow.
  3. CC. Resubmit the run.
  4. DD. Recreate the trigger.

Item 3

  1. AA. Republish the flow.
  2. BB. Review the Activity history.
  3. CC. Export the flow to a solution.
  4. DD. Inspect the Analytics summary.
Show answer & explanation

Correct answer: Item 1: B · Item 2: C · Item 3: B

ExplanationDisable the flow to stop new failures, resubmit the failed run after fixing auth, then review Activity history to confirm success.

QUESTION 11

DRAG DROP -
A company is preparing an agent flow so that it can be invoked by an agent during conversations.
The agent flow must meet the following requirements:
The agent must be able to trigger the flow.
The agent flow must be verified.
You need to prepare an agent flow so that it can be used by the agent.
In which order should you perform the actions to prepare the agent flow? To answer, move all actions from the list of actions to the answer area and arrange them in the correct order.

Item 1

  1. AA. Configure the invocation trigger that allows the agent to call the agent flow.
  2. BB. Make the agent flow available for agent usage.
  3. CC. Validate the agent flow behavior with representative test runs.
  4. DD. Configure the actions that implement the required behavior.
  5. EE. Create a new agent flow artifact in the environment.

Item 2

  1. AA. Configure the invocation trigger that allows the agent to call the agent flow.
  2. BB. Make the agent flow available for agent usage.
  3. CC. Validate the agent flow behavior with representative test runs.
  4. DD. Configure the actions that implement the required behavior.
  5. EE. Create a new agent flow artifact in the environment.

Item 3

  1. AA. Configure the invocation trigger that allows the agent to call the agent flow.
  2. BB. Make the agent flow available for agent usage.
  3. CC. Validate the agent flow behavior with representative test runs.
  4. DD. Configure the actions that implement the required behavior.
  5. EE. Create a new agent flow artifact in the environment.

Item 4

  1. AA. Configure the invocation trigger that allows the agent to call the agent flow.
  2. BB. Make the agent flow available for agent usage.
  3. CC. Validate the agent flow behavior with representative test runs.
  4. DD. Configure the actions that implement the required behavior.
  5. EE. Create a new agent flow artifact in the environment.

Item 5

  1. AA. Configure the invocation trigger that allows the agent to call the agent flow.
  2. BB. Make the agent flow available for agent usage.
  3. CC. Validate the agent flow behavior with representative test runs.
  4. DD. Configure the actions that implement the required behavior.
  5. EE. Create a new agent flow artifact in the environment.
Show answer & explanation

Correct answer: Item 1: E · Item 2: D · Item 3: A · Item 4: C · Item 5: B

ExplanationCreate the flow, configure actions, set the invocation trigger, validate with test runs, then make it available to the agent.

QUESTION 12

HOTSPOT -
A company uses an agent flow that occasionally requires human input before continuing execution.
Some automated actions must pause until a human provides a decision or additional information. The flow must be configured to:
Capture a human response for use in later steps.
Continue processing within the same flow run after the response is submitted.
Wait for a manual decision before proceeding.
You need to configure a human-in-the-loop agent flow.
Which setting should you configure for each requirement? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

Item 1

  1. AA. Send a notification to a user.
  2. BB. Use the action's response outputs in subsequent steps.
  3. CC. Enable analytics logging for the response.

Item 2

  1. AA. Republish the flow after the decision is submitted.
  2. BB. Trigger a new flow run when a response is received.
  3. CC. Allow the action to wait for and return a response before continuing.

Item 3

  1. AA. Add a human approval action.
  2. BB. Add a manual trigger to the flow.
  3. CC. Send a message that asks for input.
Show answer & explanation

Correct answer: Item 1: B · Item 2: C · Item 3: A

ExplanationUse human approval to wait for a decision, capture response outputs in subsequent steps, and allow the action to wait and return before continuing the same run.

QUESTION 13

HOTSPOT -
A company uses an agent that invokes an agent flow to exchange information during a conversation.
The company requires that the agent send data into the flow and receive structured results back from the same flow run. To support this business need, the flow must be configured to do the following:
Capture the data provided by the agent.
Return data results to the agent.
You need to configure the flow so that it can exchange data with the agent.
What should you configure for each requirement? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

Item 1

  1. AA. Use an internal variable.
  2. BB. Add a text input parameter.
  3. CC. Store values only in the topic.

Item 2

  1. AA. Log values to run history.
  2. BB. Store values only in the flow.
  3. CC. Add a text output parameter.
Show answer & explanation

Correct answer: Item 1: B · Item 2: C

ExplanationAgent flows use input and output parameters to exchange data with the calling agent.

QUESTION 14

DRAG DROP -
You are configuring an agent in Copilot Studio for an organization. The organization uses Microsoft Dataverse, Dynamics 365, and SharePoint Online.
The agent must retrieve information from enterprise systems and internal documents. The agent must meet the following requirements:
Must retrieve the current balance of a customer account stored in Dataverse.
Must retrieve the real-time shipping status of an order that updates throughout the day in Dynamics 365.
Must answer questions based on the content of a static PDF policy document.
Must provide a welcome message that does NOT depend on enterprise data.
You need to configure the agent to meet the requirements.
How should the agent retrieve the data? To answer, move the appropriate solutions to the correct requirements. You may use each solution 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.

Item 1

  1. AA. Create a manual response in the topic.
  2. BB. Connect to a Power Platform connector.
  3. CC. Upload a file to Agents Knowledge Base.
  4. DD. Configure a generative answer without enterprise data.

Item 2

  1. AA. Create a manual response in the topic.
  2. BB. Connect to a Power Platform connector.
  3. CC. Upload a file to Agents Knowledge Base.
  4. DD. Configure a generative answer without enterprise data.

Item 3

  1. AA. Create a manual response in the topic.
  2. BB. Connect to a Power Platform connector.
  3. CC. Upload a file to Agents Knowledge Base.
  4. DD. Configure a generative answer without enterprise data.

Item 4

  1. AA. Create a manual response in the topic.
  2. BB. Connect to a Power Platform connector.
  3. CC. Upload a file to Agents Knowledge Base.
  4. DD. Configure a generative answer without enterprise data.
Show answer & explanation

Correct answer: Item 1: B · Item 2: B · Item 3: C · Item 4: A

ExplanationUse Power Platform connectors for live Dataverse/Dynamics data, upload static PDFs to the knowledge base, and use manual topic responses for static greetings.

QUESTION 15

An agent calls a flow. The agent requires structured output values to be returned.
The agent receives unexpected or empty values.
You need to configure the agent so that data is exchanged correctly between the agent and the flow.
What should you do?

  1. AA. Validate parameter definitions.
  2. BB. Change the trigger schema.
  3. CC. Review the flow run history.
  4. DD. Add a Parse JSON inside the flow.
  5. EE. Republish the agent.
Show answer & explanation

Correct answer: A

ExplanationValidate parameter definitions between the agent and the flow to ensure structured input/output values are exchanged correctly.

QUESTION 16

A company is building an agent in Copilot Studio.
The agent must meet the following requirements:
Responses must be grounded in approved internal content.
The agent must be able to retrieve information from configured data sources in a topic.
You need to configure the agent so that topic responses are grounded from custom data sources.
What should you configure?

  1. AA. Enable analytics to review which topics users trigger most often.
  2. BB. Add a custom prompt that tells the agent to answer only from company data.
  3. CC. Configure knowledge sources in a generative answers node.
  4. DD. Add SharePoint as a knowledge source only at the agent level.
  5. EE. Increase the response length limit to improve answer completeness.
Show answer & explanation

Correct answer: C

ExplanationConfigure knowledge sources in a generative answers node to ground topic responses from approved internal content.

QUESTION 17

DRAG DROP -
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.

Item 1

  1. AA. Add required headers to the HTTP request.
  2. BB. Set the method to GET in the HTTP request.
  3. CC. Select JSON data type and save response to a variable.
  4. DD. Set the method to POST and send JSON in a request body.

Item 2

  1. AA. Add required headers to the HTTP request.
  2. BB. Set the method to GET in the HTTP request.
  3. CC. Select JSON data type and save response to a variable.
  4. DD. Set the method to POST and send JSON in a request body.

Item 3

  1. AA. Add required headers to the HTTP request.
  2. BB. Set the method to GET in the HTTP request.
  3. CC. Select JSON data type and save response to a variable.
  4. DD. Set the method to POST and send JSON in a request body.
Show answer & explanation

Correct answer: Item 1: A · Item 2: B · Item 3: C

ExplanationAdd auth headers, use GET to retrieve data, and parse JSON into a topic variable for reuse.

QUESTION 18

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?

  1. AA. Select Authenticate with Microsoft Entra ID for the agent.
  2. BB. Enable Require Secure Access in the Web channel security.
  3. CC. Publish the agent as a public website experience.
  4. DD. Select Authenticate with personal account for the agent.
Show answer & explanation

Correct answer: A

ExplanationSelect Authenticate with Microsoft Entra ID to restrict access to internal employees and enforce end-user authentication.

QUESTION 19

DRAG DROP -
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.

Item 1

  1. AA. Configure and enable the agent's target integration channel.
  2. BB. Retrieve current agent configuration values.
  3. CC. Deploy the web app to production.
  4. DD. Implement the Microsoft 365 Agents SDK in the app using the agent configuration.
  5. EE. Publish the agent.
  6. FF. Validate the end-to-end conversation workflow in a test environment.

Item 2

  1. AA. Configure and enable the agent's target integration channel.
  2. BB. Retrieve current agent configuration values.
  3. CC. Deploy the web app to production.
  4. DD. Implement the Microsoft 365 Agents SDK in the app using the agent configuration.
  5. EE. Publish the agent.
  6. FF. Validate the end-to-end conversation workflow in a test environment.

Item 3

  1. AA. Configure and enable the agent's target integration channel.
  2. BB. Retrieve current agent configuration values.
  3. CC. Deploy the web app to production.
  4. DD. Implement the Microsoft 365 Agents SDK in the app using the agent configuration.
  5. EE. Publish the agent.
  6. FF. Validate the end-to-end conversation workflow in a test environment.

Item 4

  1. AA. Configure and enable the agent's target integration channel.
  2. BB. Retrieve current agent configuration values.
  3. CC. Deploy the web app to production.
  4. DD. Implement the Microsoft 365 Agents SDK in the app using the agent configuration.
  5. EE. Publish the agent.
  6. FF. Validate the end-to-end conversation workflow in a test environment.

Item 5

  1. AA. Configure and enable the agent's target integration channel.
  2. BB. Retrieve current agent configuration values.
  3. CC. Deploy the web app to production.
  4. DD. Implement the Microsoft 365 Agents SDK in the app using the agent configuration.
  5. EE. Publish the agent.
  6. FF. Validate the end-to-end conversation workflow in a test environment.

Item 6

  1. AA. Configure and enable the agent's target integration channel.
  2. BB. Retrieve current agent configuration values.
  3. CC. Deploy the web app to production.
  4. DD. Implement the Microsoft 365 Agents SDK in the app using the agent configuration.
  5. EE. Publish the agent.
  6. FF. Validate the end-to-end conversation workflow in a test environment.
Show answer & explanation

Correct answer: Item 1: E · Item 2: A · Item 3: B · Item 4: D · Item 5: F · Item 6: C

ExplanationPublish the agent, enable the integration channel, retrieve configuration values, implement the SDK, validate end-to-end, then deploy to production.

QUESTION 20

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.

  1. AA. Remove agent topics directly from the solution to prevent export errors.
  2. BB. Convert the solution to a managed solution so it can be exported.
  3. CC. Export the unmanaged solution that contains the agent.
  4. DD. Publish the agent to a channel and export the channel configuration.
  5. EE. Create a custom solution and add the existing agent to the solution.
Show answer & explanation

Correct answer: C, E

ExplanationCreate a custom solution, add the agent, and export the unmanaged solution for ALM transport between environments.

Build a focused AB-620 practice routine.

Choose AB-620 in Revizo and work through original, question-by-question practice on your iPhone. Review results, revisit what needs attention and keep your next session tied to one specific certification objective.

Practise AB-620 with Revizo

AB-620 practice questions.

Is Revizo the official Microsoft exam?

No. Revizo is an independent iPhone app for certification practice. Refer to the provider's official resources for current exam policies and registration.

How should I use these AB-620 practice questions?

Use the exam code to select the matching certification in Revizo, then build short, focused sessions around the areas you want to review.

Are Revizo questions copied from live examinations?

No. Revizo provides original practice questions for certification study. Use the provider's official objectives, documentation and policies as the source of truth for your preparation.

What should I use alongside AB-620 practice questions?

Use the current Microsoft objectives, documentation and registration guidance as your source of truth. Revizo is designed to support focused practice, not replace the provider's official materials.

Where can I confirm current AB-620 requirements?

Check the official Microsoft exam page for the latest objectives, registration details and policies.