Microsoft AB-100 Online Practice Questions and Exam Preparation

Microsoft AB-100 Online Questions & Answers

• Question 41:

  You need to recommend a security solution for agents in a Microsoft Power Platform environment.

  The agents must use only approved connectors and services. The solution must prevent the agents from accessing sensitive data.

  What should you recommend?

  A. Configure Azure Monitor to capture connector activity logs.
  B. Enable a Microsoft Dataverse audit.
  C. Deploy data loss prevention (DLP) policies in Power Platform.
  D. Enable customer-managed keys in Microsoft Dataverse.
  C. Deploy data loss prevention (DLP) policies in Power Platform.

  ---

  Explanation

  Power Platform data loss prevention policies restrict which connectors and services agents and apps can use. They help prevent business data from flowing into unapproved or sensitive destinations. Azure Monitor and Dataverse audit can observe activity, but they do not enforce connector allow and block rules. Use DLP policies when the requirement is to permit only approved connectors and protect data movement.

• Question 42:

  HOTSPOT

  You are designing a testing solution for a Microsoft Copilot Studio agent that integrates with Microsoft Dynamics 365 Customer Service and Dynamics 365 Sales.

  You need to design end-to-end scenarios to test the agent's ability to perform the following actions:

  1. Coordinate tasks and data interactions across both Dynamics 365 apps.

  2. Interpret user input and provide contextually relevant outputs.

  Which test scenario and metric should you include in the design? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The completed hotspot uses task-based scenarios that involve both apps and tracks successful completion of cross-app tasks. The answer image validates the integrated workflow rather than isolated screens or visual consistency. Because the agent spans Dynamics 365 Customer Service and Sales, the test must prove that a user can complete the business task across both systems. The completion metric is stronger than click rate or initial response time because it measures real business success.

• Question 43:

  You add a Dataverse table as a knowledge source for a Copilot Studio agent. The table cannot be selected, and the administrator must enable the prerequisite capability for the environment.

  Which capability should the administrator enable?

  A. Power BI DirectQuery
  B. Dataverse search
  C. Azure Monitor autoscale
  D. SharePoint Syntex content assembly
  B. Dataverse search

  ---

  Explanation

  Dataverse search must be enabled before Dataverse tables can be used as selectable knowledge sources in Copilot Studio. The issue is not with the table content itself; it is that the environment prerequisite is missing. Once Dataverse search is enabled, relevant table data can be indexed and made available for knowledge grounding. This is a common prerequisite clue in Dataverse knowledge-source questions.

• Question 44:

  Which two components in the custom AI agent design should the CFO evaluate in the quarterly agent analysis? (Choose Two)

  A. the GPT models used for the agent
  B. the average characters in a chat message
  C. the agent orchestration method
  D. the average session time per agent
  C. the agent orchestration method
  D. the average session time per agent

  ---

  Explanation

  The CFO is responsible for comparing estimated ROI against actual efficiencies and adoption, and the scenario states that the Copilot Studio agent usage estimator will be used for that analysis. Agent cost and consumption are affected by the agent configuration and usage pattern, so the orchestration method is relevant because classic and generative orchestration change how the agent plans, invokes topics, uses tools, and consumes generative capabilities. Average session time is also relevant because session length is an operational usage pattern that can affect cost efficiency and the comparison between abandoned and resolved work. The GPT model choice is not the best component here because Copilot Studio credit estimation focuses on the agent type, traffic, orchestration, knowledge, tools, and usage assumptions rather than asking the CFO to compare GPT model internals. Average characters in a chat message is too low-level for the quarterly business analysis described in the case.

• Question 45:

  A company plans to deploy a Microsoft Dynamics 365 Contact Center agent.

  You need to ensure that the agent can transfer the conversation to a live customer service representative.

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

  NOTE: Each correct selection is worth one point.

  A. Microsoft Foundry
  B. Microsoft Copilot Studio
  C. Microsoft 365 Agents Toolkit
  D. an Azure AI Bot Service skill
  E. Customer engagement hub
  B. Microsoft Copilot Studio
  E. Customer engagement hub

  ---

  Explanation

  Microsoft Copilot Studio provides the agent experience, and the customer engagement hub provides the live-agent handoff target for Dynamics 365 Contact Center. Together they allow the virtual agent to handle the conversation and transfer it to a human representative when escalation is needed. Foundry and Azure Bot Service skills do not by themselves provide the Dynamics contact-center handoff experience. For live support transfer, pair the bot or agent with the contact-center engagement hub.

• Question 46:

  HOTSPOT

  A company uses Microsoft Dynamics 365 Supply Chain Management.

  You are designing an AI supply chain process that meets the following requirements:

  1. Provides managers with AI-driven insights that surface key information from customer orders

  2. Helps planners use AI to anticipate future product needs more accurately.

  You need to recommend which Microsoft Copilot features to include in the design.

  What should you recommend 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 AI-driven insights from customer orders to AI Summaries with Copilot and future product needs to Generative insights for Demand planning. The answer image distinguishes summarizing current operational information from forecasting demand. AI summaries help managers understand existing customer-order signals, while demand-planning insights anticipate future product requirements. Product information management stores master data, but it does not provide the predictive demand insight requested.

• Question 47:

  A company has an AI solution that uses Azure OpenAI models.

  You need to recommend a governance solution that monitors and audits changes to model configurations and data usage. The solution must minimize administrative effort.

  What should you include in the recommendation?

  A. Azure Monitor
  B. Azure Stream Analytics
  C. Azure API Management
  D. Azure Policy
  E. Microsoft Purview
  A. Azure Monitor

  ---

  Explanation

  Azure Monitor is appropriate for monitoring and auditing operational changes and usage signals for Azure OpenAI resources with minimal administrative overhead. It collects metrics, logs, and diagnostic data that can be reviewed centrally.

  Stream Analytics and API Management solve different integration problems, while Azure Policy focuses more on enforcing configuration rules. For resource-level monitoring and audit telemetry, use Azure Monitor.

• Question 48:

  A company is creating an agent that must decide at runtime whether to use a topic, call a tool, consult a knowledge source, or delegate part of the work to another agent. The agent must also respond to an event that occurs outside a conversation.

  What should you enable?

  A. Classic orchestration
  B. Generative orchestration
  C. A static FAQ topic only
  D. A custom glossary in Dataverse
  B. Generative orchestration

  ---

  Explanation

  Generative orchestration is appropriate because the agent must decide at runtime whether to use a topic, tool, knowledge source, or another agent. It also needs to respond to events and coordinate actions based on intent and context.

  Classic orchestration would require more fixed routing and would not satisfy the dynamic decision requirement as well. The exam clue is runtime selection across multiple capabilities.

• Question 49:

  A company has a Microsoft 365 tenant in Canada and multiple Microsoft Power Platform environments in Canada and the United States.

  The company plans to deploy a Microsoft Copilot Studio agent to the Canadian environment that will use:

  1. Microsoft Dataverse data stored in Canada

  2. A connector that connects to an Azure OpenAI instance in the United States.

  You need to ensure that the agent adheres to data residency and data movement policies before being deployed.

  What should you do?

  A. Ensure that the data processed by Azure OpenAI is stored in the United States.
  B. From the Microsoft Purview portal, validate the Data loss prevention settings.
  C. Migrate the tenant to the United States.
  D. Ensure that cross-region data movement is enabled for the Canadian environment and connector dependencies.
  D. Ensure that cross-region data movement is enabled for the Canadian environment and connector dependencies.

  ---

  Explanation

  Cross-region data movement must be enabled because the tenant and Power Platform environments span Canada and the United States while the agent is deployed to the Canadian environment. Connector dependencies and environment location can affect where data is processed or moved. Governance checks must make sure the regional design complies with the company's residency requirements. When a scenario crosses regions, validate data movement and connector behavior before deployment.

• Question 50:

  DRAG DROP

  You are designing three agents for a business solution.

  The solution must meet the following requirements:

  1. Answer policy questions by retrieving approved knowledge only.

  2. Reconcile duplicate account records when a Dataverse event occurs.

  3. Collect missing invoice fields from a user and start an approval workflow.

  Which agent type should you use for each requirement? To answer, drag the appropriate agent types to the correct requirements. Each agent type may be used once, more than once, or not at all.

  NOTE: Each correct selection is worth one point.

  Select and Place:

  

  

  ---

  The completed drag-and-drop maps approved-policy Q&A to a prompt-and-response agent, duplicate account reconciliation after a Dataverse event to an autonomous agent, and invoice-field collection plus approval workflow to a task agent.

  The answer image matches each agent type to the work pattern. Prompt-and-response agents answer user questions from approved knowledge, autonomous agents react to events and act without an active chat, and task agents guide a user through a bounded workflow. This is a core AB-100 distinction among agent types.