Microsoft AB-100 Online Practice Questions and Exam Preparation

Microsoft AB-100 Online Questions & Answers

• Question 61:

  DRAG DROP

  You need to design a Microsoft Copilot Studio agent that meets the following requirements:

  1. Supports interactive speech responses

  2. Optimizes decision-making and the accuracy of responses.

  What should you include in the design 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.

  Select and Place:

  

  

  ---

  The completed drag-and-drop maps interactive speech responses to Copilot Studio voice features and improved decision accuracy to a deep reasoning model. The answer image separates channel capability from reasoning capability. Voice features support spoken, interactive responses, while a deep reasoning model is used when the agent needs stronger multi-step reasoning and decision quality. Azure AI Speech or SSML can support speech output, but the Copilot Studio voice feature is the agent-level capability named by the scenario.

• Question 62:

  A company exposes order-status APIs and reference documents through an existing Model Context Protocol (MCP) server. You need a Copilot Studio agent to use the server's tools and resources, and the agent must pick the right capability during the conversation.

  What should you do?

  A. Turn on generative orchestration and add the MCP server to the agent.
  B. Disable generative orchestration and create one trigger phrase per API endpoint.
  C. Export the MCP server as a Power BI semantic model.
  D. Deploy a separate model router for every MCP tool.
  A. Turn on generative orchestration and add the MCP server to the agent.

  ---

  Explanation

  Turning on generative orchestration and adding the MCP server lets the Copilot Studio agent reason over the server's exposed tools and resources. MCP provides the existing tool surface, while generative orchestration lets the agent choose when to use those tools in the conversation. A static topic or simple knowledge source would not provide dynamic API/tool use. Use MCP plus generative orchestration when the agent must work with external tools that are already exposed by an MCP server.

• Question 63:

  A company uses Microsoft Dynamics 365 Sales to manage leads that are stored in a Microsoft Dataverse table named Lead and use non-standard terminology and custom columns.

  You need to configure business terms in the Lead table so that Microsoft Copilot controls can summarize the leads efficiently. The solution must minimize administrative effort.

  How should you configure the business terms?

  A. Combine all the fields into one custom field.
  B. Map the field display names as business terms.
  C. Add the schema names as business terms.
  D. Create new business terms for each field.
  B. Map the field display names as business terms.

  ---

  Explanation

  Mapping the field display names as business terms fits the requirement because the table uses custom columns and non-standard terminology. Business users and AI experiences need terminology that reflects how the organization refers to lead data. Changing the schema or building unrelated automation is unnecessary when the problem is semantic understanding of existing fields. The practical rule is to align business vocabulary with Dataverse metadata before relying on AI over custom data.

• Question 64:

  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 uses Microsoft 365 and Dynamics 365.

  You need to recommend a solution to automatically summarize email threads, generate suggested replies in Microsoft Outlook, and provide meeting preparation summaries that include relevant customer relationship management (CRM) data.

  Solution: You recommend a Microsoft 365 Copilot agent template.

  Does this meet the goal?

  A. Yes
  B. No
  B. No

  ---

  Explanation

  A Microsoft 365 Copilot agent template does not meet the full goal because the scenario specifically requires sales email and meeting assistance tied to Dynamics 365 CRM data. A template can start a custom agent, but it does not automatically provide the Copilot for Sales experiences in Outlook and Teams. The goal is an existing product capability, not a generic agent shell. When the requirements name sales emails, suggested replies, and CRM meeting preparation, Copilot for Sales is the fit.

• Question 65:

  HOTSPOT

  You need to design a shared prompt library that will be used across multiple business units. The solution must meet the following requirements:

  1. Ensure consistent AI responses with reusable formats.

  2. Support governance and version control.

  3. Minimize administrative effort.

  4. Minimize ongoing costs.

  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 selects standardized prompt templates for consistent AI responses and maintaining prompt history for governance and version control. The answer image shows a library-management pattern rather than a one-off prompt. Templates create repeatable response structure, while history provides traceability of changes and rollback context. Prompt governance requires both reusable standards and a record of version changes.

• Question 66:

  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 build Microsoft Power Automate flows to trigger customized Copilot summaries.

  Does this meet the goal?

  A. Yes
  B. No
  B. No

  ---

  Explanation

  Power Automate flows do not meet the goal for tailoring Copilot opportunity summaries because they automate business processes rather than control the generated summary layout or fields. A flow could update data before a summary is generated, but that is indirect and does not configure the Copilot summary behavior. The requirement asks for Copilot customization, not workflow automation. Use supported Copilot summary configuration instead of building side-effect automations.

• Question 67:

  You are evaluating a Microsoft Copilot Studio agent that supports Microsoft Dynamics 365 Customer Service representatives.

  You need to recommend a testing solution that meets the following requirements:

  Evaluates agent effectiveness during active sessions

  Validates whether the agent delivers accurate and helpful responses Provides measurable, actionable insights for continuous improvement.

  What should you recommend?

  A. Track resolution, deflection, and accuracy by using dashboards and use scripts to ensure consistent responses.
  B. Perform load testing to validate how the agent scales under a high chat volume.
  C. Review historical tickets to find agents that have the shortest resolution times.
  D. Measure uptime and page load times.
  A. Track resolution, deflection, and accuracy by using dashboards and use scripts to ensure consistent responses.

  ---

  Explanation

  Tracking resolution, deflection, and accuracy with dashboards, and using scripts for consistent response validation, meets the testing requirements. The solution evaluates active-session effectiveness and turns the results into measurable improvement data. Load tests and uptime checks are useful operational tests, but they do not prove answer helpfulness or agent effectiveness. For support-agent quality, combine outcome dashboards with repeatable scripted response checks.

• Question 68:

  A company plans to create a Copilot Studio agent that answers questions from operational manuals. The manuals contain duplicate procedures, outdated sections, and several pages that have not been reviewed by the business owners.

  You need to recommend the first activity before using the manuals as grounding data.

  What should you recommend?

  A. Add all manuals as knowledge sources and tune the agent after users report issues.
  B. Fine-tune a custom model on the manuals so the model can learn the terminology.
  C. Review the data for accuracy, relevance, timeliness, cleanliness, and availability.
  D. Create prompt actions that tell the agent to ignore any outdated information.
  C. Review the data for accuracy, relevance, timeliness, cleanliness, and availability.

  ---

  Explanation

  The first activity is to review the grounding data for accuracy, relevance, timeliness, cleanliness, and availability. Duplicate, stale, or unreviewed manuals can cause the agent to generate inconsistent or incorrect grounded responses. Tuning prompts or fine-tuning a model before cleaning the source content would preserve the underlying quality problem. Grounding quality starts with trusted content.

• Question 69:

  HOTSPOT

  A company has a Microsoft Power Platform environment.

  You need to build two agents named Agent1 and Agent2. The solution must meet the following requirements:

  1. Agent1 must be extendable by using the Semantic Kernel and must connect to multiple business apps and APIs.

  2. Agent2 must connect directly to data stored in Microsoft Dataverse and must be embeddable in a Microsoft Power Apps canvas app.

  What should you use to build each agent? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The completed hotspot should use Microsoft Foundry for Agent1 and Microsoft Copilot Studio for Agent2. Agent1 requires Semantic Kernel extensibility and connections to multiple business apps and APIs, which points to a code-first Foundry agent architecture. Agent2 needs direct Dataverse integration and embedding in a Power Apps canvas app, which fits a Copilot Studio agent in a Power Platform environment. The important visual distinction is between code-first agent extensibility and low-code Dataverse or Power Apps integration.

• Question 70:

  A Copilot Studio agent has authored topics for product returns and warranty claims. Users sometimes ask questions that do not match any topic, but the answer exists in approved knowledge sources.

  What should you configure?

  A. A fallback experience that uses generative answers over the approved knowledge sources
  B. A requirement that every user enter the exact trigger phrase
  C. A lower content moderation setting so the model answers more often
  D. A model router with no knowledge sources
  A. A fallback experience that uses generative answers over the approved knowledge sources

  ---

  Explanation

  A fallback experience that uses generative answers over approved knowledge sources is correct because users ask questions that do not match authored topics but the answer exists in configured content. The fallback route prevents dead ends while keeping answers grounded in approved sources. Creating a topic for every possible wording is inefficient and brittle. Use fallback plus generative answers to handle long-tail knowledge questions.