Microsoft AB-731 Online Practice Questions and Exam Preparation

Microsoft AB-731 Online Questions & Answers

• Question 61:

  HOTSPOT

  A team is learning how to improve interactions with generative AI solutions. The team wants to understand what prompt engineering does and how it affects AI-generated responses.

  For each of the following statements, select Yes if the statement is true. Otherwise, select No.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The answer image should be No, Yes, and No. Prompt engineering changes instructions and context, not model training; it focuses on clear context-rich prompts, and using more tokens is not automatically better.

• Question 62:

  Your company is evaluating the use of Microsoft Copilot Studio to support business process automation and employee self-service.

  Which two capabilities are directly supported in Copilot Studio? Each correct answer presents a complete solution.

  NOTE: Each correct selection is worth one point.

  A. drafting and summarizing files in Microsoft Word and PowerPoint
  B. customizing agent behavior and responses
  C. using agents to identify and respond to security incidents
  D. building agents that connect to business data and automate user interactions
  E. configuring document security
  B. customizing agent behavior and responses
  D. building agents that connect to business data and automate user interactions

  ---

  Explanation

  Copilot Studio directly supports building and customizing agents and connecting them to business data and workflows. Drafting Office files is a Microsoft 365 Copilot app experience, security-incident response belongs to Security Copilot, and document security configuration is not the core agent-building feature.

• Question 63:

  HOTSPOT

  You are evaluating Microsoft Foundry for an organization that plans to build and manage generative AI solutions. The organization wants to understand which capabilities are supported by Microsoft Foundry.

  For each of the following statements, select Yes if the statement is true. Otherwise, select No.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The answer image marks all three statements as Yes. Microsoft Foundry supports governed enterprise AI development, scalability for AI workloads, and use of AI tools including vision-related capabilities within the broader Foundry platform.

• Question 64:

  Your company manages a website that publishes daily news articles.

  You need to recommend an AI solution that can analyze text and identify the main people, locations, and companies mentioned in the articles.

  What should you include in the recommendation?

  A. Azure Language in Foundry Tools
  B. Azure Vision in Foundry Tools
  C. Content Safety in Foundry Control Plane
  D. Azure Speech in Foundry Tools
  A. Azure Language in Foundry Tools

  ---

  Explanation

  Azure Language capabilities support text analytics such as entity recognition, sentiment, key phrase extraction, and language understanding. The requirement is to identify people, locations, and companies in articles, which is a language service task rather than vision, speech, or safety.

• Question 65:

  HOTSPOT

  An organization is evaluating Microsoft Copilot experiences across Microsoft 365, Microsoft Copilot Studio, and Microsoft Security Copilot. The organization wants to understand the purpose of each product.

  For each of the following statements, select Yes if the statement is true. Otherwise, select No.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The answer image should be Yes, No, and No. Microsoft 365 Copilot supports productivity in Microsoft 365 apps, Copilot Studio is broader than customizing Microsoft 365 Copilot only, and Security Copilot is not used to assign sensitivity labels to documents.

• Question 66:

  Your company is preparing to adopt Microsoft 365 Copilot and wants to follow Microsoft responsible AI principles.

  As a business leader, you propose establishing an AI governance council to ensure alignment with the responsible AI principles.

  What is the primary purpose of the council?

  A. to monitor user behavior and enforce compliance with internal IT policies
  B. to train employees on how to use Copilot features effectively
  C. to oversee implementation, manage technical performance, and ensure successful AI deployment
  D. to guide strategy, provide oversight, and ensure cross-functional alignment for responsible AI adoption
  D. to guide strategy, provide oversight, and ensure cross-functional alignment for responsible AI adoption

  ---

  Explanation

  An AI governance council exists to set strategy, provide oversight, and coordinate responsible adoption across business, legal, compliance, security, and technology groups. Training and technical monitoring matter, but they are narrower than governance leadership.

• Question 67:

  HOTSPOT

  A company plans to build a generative AI solution that answers employee questions by using the company's internal knowledge sources. The company wants responses to be grounded in current enterprise data without retraining the large language model.

  For each of the following statements, select Yes if the statement is true. Otherwise, select No.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The answer image should be No, Yes, and Yes. RAG grounds a language model with retrieved content without retraining it, and the retrieval step can use enterprise or external knowledge sources at response time.

• Question 68:

  A company is preparing to deploy an AI assistant that accesses confidential business documents.

  Which two security considerations should be included in the design?

  A. Enforce user authentication and authorization before retrieving business content
  B. Apply data protection controls so responses respect existing permissions
  C. Permit anonymous access so the assistant can answer more questions
  D. Store all prompts and responses permanently without classification
  E. Bypass review of third-party connectors to accelerate deployment
  A. Enforce user authentication and authorization before retrieving business content
  B. Apply data protection controls so responses respect existing permissions

  ---

  Explanation

  An assistant that retrieves confidential content must authenticate users and enforce authorization before retrieval, and responses must respect data protection and existing permissions. Anonymous access, permanent unclassified logs, or unreviewed connectors would increase exposure risk.

• Question 69:

  Your company plans to use generative AI to help summarize and analyze internal business documents.

  You need to recommend a solution to prevent generative AI from accessing confidential or classified information.

  What should you include in the recommendation?

  A. an information barrier (IB) policy
  B. communication monitoring
  C. a data retention policy
  D. data governance
  D. data governance

  ---

  Explanation

  Data governance is the broad control area for classifying, protecting, and controlling access to confidential information used by generative AI. Information barriers and retention policies are narrower controls and do not replace a governance program for sensitive data access.

• Question 70:

  HOTSPOT

  An organization is evaluating Microsoft 365 Copilot Chat and Microsoft 365 Copilot. The organization wants to understand licensing requirements and how Copilot provides assistance across Microsoft 365 experiences.

  For each of the following statements, select Yes if the statement is true. Otherwise, select No.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The answer image should be No, Yes, and No. Copilot Chat does not require the full Microsoft 365 Copilot license for basic chat, a Microsoft 365 Copilot license provides context-aware assistance in Microsoft 365 apps, and Copilot Chat is not limited to open files or read emails only.