Microsoft AB-100 Online Practice Questions and Exam Preparation

Microsoft AB-100 Online Questions & Answers

• Question 111:

  A company extends Copilot in Microsoft Dynamics 365 Customer Service.

  You need to recommend an automated application lifecycle management (ALM) process so that the Copilot components can be safely developed, tested, and promoted to production.

  Which two actions should you include in the ALM process? Each correct answer presents part of the solution.

  NOTE: Each correct selection is worth one point.

  A. Use an unmanaged solution in production.
  B. Rebuild the agents in each environment.
  C. Use Microsoft Power Platform pipelines.
  D. Include the components in a solution.
  E. Store the agent transcripts in source control.
  C. Use Microsoft Power Platform pipelines.
  D. Include the components in a solution.

  ---

  Explanation

  Power Platform pipelines automate promotion across environments, and including the components in a solution keeps the Copilot assets and dependencies together. This supports safe development, testing, and production deployment.

  Unmanaged production edits or rebuilding agents manually would break ALM discipline. The standard pattern is solution packaging plus pipeline-based environment promotion.

• Question 112:

  You need to recommend a Microsoft Power Platform business solution that consolidates data from multiple internal and external data sources. The solution must meet the following requirements:

  1. Provide the data as a centralized source for multiple AI systems, including Microsoft Copilot Studio agents, Dynamics 365 applications, and external AI models.

  2. Support built-in data classification and protection policies.

  3. Provide data for grounding and analytics.

  What should you include in the recommendation?

  A. Microsoft Dataverse
  B. Azure Data Lake Storage
  C. a Microsoft Power BI semantic model
  D. Azure Cosmos DB
  A. Microsoft Dataverse

  ---

  Explanation

  Microsoft Dataverse is the correct business data platform because it consolidates internal and external data into governed tables that Power Platform apps, agents, and automation can use. It provides security, relationships, business rules, and integration with low-code experiences. A reporting-only or storage-only service would not provide the same operational data foundation. For Power Platform business solutions, Dataverse is the default choice when the data must be shared, secured, and acted on.

• Question 113:

  You need to recommend a solution to integrate a Microsoft Copilot agent with a Microsoft Dynamics 365 Contact Center chat channel.

  The agent must respond to customer questions and hand off the conversation to a live customer service representative when the customer requests an escalation.

  What should you recommend?

  A. Build an agent flow.
  B. Configure the Conversation Start topic.
  C. Configure a skill.
  D. Call a Microsoft Power Automate connector.
  E. Configure the Escalate topic.
  E. Configure the Escalate topic.

  ---

  Explanation

  The Escalate topic is the correct configuration for handing a customer conversation to a live representative. It is built for escalation behavior and can pass conversation context to the engagement channel. A generic flow or connector might call an external process, but it does not represent the standard escalation path in the conversation design. In Copilot Studio contact-center scenarios, escalation is handled through the escalation topic and connected engagement hub.

• Question 114:

  HOTSPOT

  You use Microsoft Copilot Studio analytics to analyze the performance of a deployed Copilot Studio agent.

  You need to identify which performance metrics to use to measure the following:

  1. The percentage of engaged sessions that are escalated to a live customer service representative.

  2. The number of agent queries that cause a knowledge source error.

  What should you identify for each requirement? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The completed hotspot maps the percentage of engaged sessions escalated to a representative to escalation rate and maps knowledge-source-error queries to answer quality. The answer image uses Copilot Studio analytics where escalation rate measures handoff behavior and answer quality includes generated-answer and knowledge-source health signals. CSAT measures user satisfaction and engagement rate measures meaningful interaction, not the specific failure count. The key is to distinguish session outcome metrics from generated-answer quality metrics.

• Question 115:

  A company uses Microsoft Dynamics 365 Finance to manage accounts payable.

  You are designing an AI invoice processing solution.

  You need to recommend the prerequisites to configure a prebuilt copilot for accounts payable.

  What should you recommend?

  A. From Microsoft Copilot Studio, create an accounts payable agent.
  B. Extend Microsoft 365 Copilot for Sales to an accounts payable agent.
  C. Build an AI tool in Microsoft Foundry.
  D. From the Power Platform admin center, assign the Finance and Operations AI security role to users.
  D. From the Power Platform admin center, assign the Finance and Operations AI security role to users.

  ---

  Explanation

  Assigning the Finance and Operations AI security role in the Power Platform admin center is a prerequisite for the prebuilt finance copilot capability. Users need the proper security role before they can use AI features in finance and operations apps. Building a custom model or connector would not satisfy the prerequisite for the prebuilt capability. In Dynamics finance scenarios, check required roles and feature enablement before designing custom extensions.

• Question 116:

  Which tool should you recommend to help secure funding for future AI agent development?

  A. Evaluations in Microsoft Foundry
  B. the Azure Cost Optimization workbook
  C. Azure Operator Insights
  D. the Analytics tab in Microsoft Copilot Studio
  E. Direct Preference Optimization (DPO)
  D. the Analytics tab in Microsoft Copilot Studio

  ---

  Explanation

  The Analytics tab in Microsoft Copilot Studio helps secure funding because it provides measurable evidence about usage, sessions, outcomes, satisfaction, and agent performance. Funding decisions need operational and business impact data, not only infrastructure cost or model evaluation artifacts. Cost workbooks and Foundry evaluations can support parts of a broader review, but the scenario asks for evidence from the deployed agent. For stakeholder funding, use analytics that show adoption, effectiveness, and user outcomes.

• Question 117:

  What should you recommend to assist the CEO with their specific responsibilities?

  A. the Microsoft Service Trust Portal
  B. Microsoft Foundry Tools
  C. Microsoft Purview
  D. the Responsible AI dashboard
  E. Compliance Center
  D. the Responsible AI dashboard

  ---

  Explanation

  The CEO is responsible for ensuring that solutions follow responsible AI practices and wants quarterly assessment of metrics such as reliability, interpretability, fairness, and compliance. The Responsible AI dashboard is designed to support responsible AI evaluation by helping teams assess model behavior and diagnose issues across areas such as fairness, error analysis, and model interpretability. Microsoft Purview and Compliance Center focus more on data governance, compliance, and security controls, which align better with the CIO and CISO responsibilities in this case. Microsoft Foundry Tools can support AI development, but the question asks for a Microsoft-recommended assessment tool for responsible AI metrics. The Service Trust Portal provides compliance documentation, not an operational responsible AI assessment dashboard for the deployed AI solution.

• Question 118:

  DRAG DROP

  A company has a cloud-based AI solution that uses Azure OpenAI models.

  You need to design a monitoring solution that meets the following requirements:

  1. Monitors performance metrics and operational health for the models

  2. Monitors AI apps and agents for compliance

  3. Uses Azure-native capabilities

  4. Minimizes development effort.

  What should you use for each requirement? To answer, drag the appropriate options to the correct requirements. Each option may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.

  NOTE: Each correct selection is worth one point.

  Select and Place:

  

  

  ---

  The completed monitoring design should use Microsoft Purview for AI app and agent compliance and Azure Monitor for performance metrics and operational health. The answer image shows these two monitoring concerns as separate: compliance and governance are not the same as resource health. Purview supports data governance, audit, and compliance investigation, while Azure Monitor collects resource metrics and logs. Azure Policy can enforce configuration, but it is not the primary performance telemetry service.

• Question 119:

  Note: This section contains one or more sets of questions with the same scenario and problem. Each question presents a unique solution to the problem. You must determine whether the solution meets the stated goals. More than one solution in the set might solve the problem. It is also possible that none of the solutions in the set solve the problem.

  After you answer a question in this section, you will NOT be able to return. As a result, these questions do not appear on the Review Screen.

  A company has a Microsoft Dynamics 365 Sales environment that has Microsoft Copilot enabled.

  You need to customize Copilot by tailoring how opportunity summaries are generated or how they are presented to users.

  Solution: You add fields to the opportunity summary.

  Does this meet the goal?

  A. Yes
  B. No
  A. Yes

  ---

  Explanation

  Adding fields to the opportunity summary meets the goal because Dynamics 365 Sales Copilot allows summary content to be tailored by choosing which opportunity data is included or emphasized. The requirement is to customize how opportunity summaries are generated or presented, not to build a separate automation. Field selection is a direct configuration path for the summary. This keeps the solution inside the supported sales Copilot experience.

• Question 120:

  Which tool should you recommend to address the sensitive information concerns in the sales process?

  A. the Analytics tab in Microsoft Copilot Studio
  B. Model Context Protocol (MCP)
  C. Application Insights
  D. Microsoft Foundry Tracing UI
  E. Monitoring in Microsoft Foundry
  D. Microsoft Foundry Tracing UI

  ---

  Explanation

  Microsoft Foundry Tracing UI is the best fit for investigating sensitive-information concerns because tracing shows how an AI application processes requests, tool calls, context, and generated outputs. That traceability helps teams find where sensitive data may enter or leave the workflow. The Analytics tab is better for aggregate agent performance, and Application Insights is broader telemetry rather than AI reasoning trace inspection. Use tracing when the question asks for visibility into AI execution details and data flow.