Microsoft AB-100 Online Practice Questions and Exam Preparation

Microsoft AB-100 Online Questions & Answers

• Question 101:

  What should you configure for the custom AI agent?

  A. AI-assisted evaluators
  B. classic orchestration
  C. generative orchestration
  D. Azure OpenAI reasoning models
  C. generative orchestration

  ---

  Explanation

  The custom agent must select topics based on the description of the query purpose instead of relying on trigger phrases. Copilot Studio uses generative orchestration to select the most appropriate topics, tools, knowledge, and agents by using descriptions and available capabilities. Classic orchestration depends on configured trigger phrases for topic matching, which directly conflicts with the requirement that topic selection not be based on trigger phrases. AI-assisted evaluators are used to assess quality, not to route user requests during conversation. Azure OpenAI reasoning models are model resources, not the Copilot Studio orchestration setting that controls topic and tool selection.

• Question 102:

  A company has an AI agent that automates the review of customer feedback stored in a cloud database.

  You plan to generate monthly reports from the agent's output to provide insights into customer sentiment and guide product development and marketing.

  You need to ensure that the data ingested by the agent is clean and suitable for the intended use.

  What should you do to prepare the data?

  A. Create a workflow in Microsoft Power Automate.
  B. Identify and address biased data.
  C. Create an agent flow in Microsoft Copilot Studio.
  D. Sort the database by customer last name.
  C. Create an agent flow in Microsoft Copilot Studio.

  ---

  Explanation

  Creating an agent flow in Copilot Studio is appropriate because the monthly report requires an automated process based on the agent's output. Agent flows can coordinate deterministic actions and backend work that an agent invokes or uses as part of a business process. A prompt alone would not create a reusable reporting process. The key distinction is that generated insights may come from AI, but scheduled or repeatable downstream processing belongs in a flow.

• Question 103:

  HOTSPOT

  A company has a Microsoft 365 E5 subscription and uses Microsoft Copilot Studio.

  The company has a Microsoft SharePoint Online library that contains 10,000 policy PDFs from various departments. The library contains a populated column named Department for each PDF.

  You need to design a Copilot Studio agent that will use the SharePoint library as a knowledge source. The solution must meet the following requirements:

  1. Enable the agent to answer user questions about company policies.

  2. Ensure that the agent can identify which departments and policies are connected.

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

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The completed hotspot enables policy Q&A by adding SharePoint as a knowledge source in Copilot Studio and identifies department-policy connections by configuring the SharePoint tool. The answer image relies on the existing SharePoint library instead of copying all PDFs into a new system. SharePoint knowledge grounding can search approved policy files, while the SharePoint tool can expose list and metadata operations needed to reason about department relationships. AI Builder or a custom Foundry model would add unnecessary processing when the source library is already in Microsoft 365.

• Question 104:

  A company has Microsoft Copilot Studio agents.

  The company plans to deploy custom connectors across development, test and production environments.

  You need to design an application lifecycle management (ALM) process to ensure consistency and prevent direct editing in production.

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

  NOTE: Each correct selection is worth one point.

  A. Deploy managed solutions to production.
  B. Deploy unmanaged solutions to production.
  C. Manually rebuild the agents in each environment.
  D. Move the agents between the environments by using data export and import.
  E. Include agents and connectors in a solution.
  A. Deploy managed solutions to production.
  E. Include agents and connectors in a solution.

  ---

  Explanation

  Deploy managed solutions to production and include the agents and connectors in a solution. Managed solutions prevent direct editing in production, while the solution package keeps the agents, custom connectors, and dependencies together across development, test, and production. Data export and import is not ALM for Copilot Studio agents or custom connector definitions. Unmanaged production deployment would also fail the requirement to prevent direct edits.

• Question 105:

  Which template should you use for the AI agent to meet the requirements for the sales executives?

  A. IT Helpdesk in Microsoft Copilot Studio
  B. AI agents in Microsoft Foundry
  C. Voice in Microsoft Copilot Studio
  D. AI chat in Microsoft Foundry
  C. Voice in Microsoft Copilot Studio

  ---

  Explanation

  The Voice template in Microsoft Copilot Studio matches the sales executive requirement because it is built for conversational voice interactions with users. The other choices focus on general agent creation, Foundry code-first development, or IT helpdesk scenarios. When the requirement emphasizes spoken interaction or voice channel behavior, the Copilot Studio voice capability is the most direct fit. The key is to map the user experience requirement before choosing the authoring tool.

• Question 106:

  DRAG DROP

  A company plans to implement an AI business solution for a consumer goods company.

  You need to create agents that meet the following requirements:

  1. Orchestrate the sales order fulfillment and shipping of goods to customers.

  2. Analyze historical data and trends to replenish stock.

  Which type of agent 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. 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 drag-and-drop maps both sales order fulfillment with shipping and historical trend analysis to autonomous agents. The answer image shows autonomous agents because both requirements involve acting across processes or analyzing data without waiting for a single prompt-and-response interaction. Orchestrating fulfillment and shipping is an event-driven business operation, and trend analysis for replenishment can also run as an autonomous decision-support process. Task agents are more bounded, while prompt-and-response agents mainly answer direct user questions.

• Question 107:

  A retrieval-augmented generation solution sometimes produces answers that include details not present in the retrieved context. You need an evaluation metric that measures whether generated responses align with the grounding source and avoid fabricating unsupported content.

  Which evaluator should you use?

  A. Groundedness
  B. Token throughput
  C. Escalation rate
  D. Cost analysis
  A. Groundedness

  ---

  Explanation

  Groundedness measures whether generated responses are supported by the retrieved context. That directly addresses hallucinated details that are not present in the source material. Fluency or general quality could be high even when the answer invents unsupported facts. In retrieval-augmented generation, groundedness is the key metric for context alignment.

• Question 108:

  A team needs to build, deploy, and scale a code-first agent that uses models from the Foundry model catalog. The team wants the platform to handle hosting, scaling, identity, observability, and enterprise security so developers can focus on agent logic.

  Which service should you recommend?

  A. Microsoft Forms
  B. Azure Boards
  C. Microsoft Foundry Agent Service
  D. Microsoft Stream
  C. Microsoft Foundry Agent Service

  ---

  Explanation

  Microsoft Foundry Agent Service is the platform for building, deploying, and operating code-first agents with enterprise hosting, identity, observability, and scaling. The team wants to use models from the Foundry model catalog and have the platform handle operational concerns. Copilot Studio is better for low-code agents, while a general app platform would require more custom work. Choose Foundry Agent Service when the agent is code-first and enterprise-operated.

• Question 109:

  A company has a Microsoft Copilot Studio agent that uses custom connectors to interact with enterprise APIs.

  You need to recommend an application lifecycle management (ALM) process to ensure that the connectors are deployed consistently across development, test, and production environments and meet governance and traceability requirements.

  What should you recommend?

  A. Deploy the APIs as Azure Functions.
  B. Manage the connectors as solution components and deploy the components by using ALM pipelines.
  C. Maintain connector definitions in environment variables.
  D. Export and import the connectors between the environments as unmanaged solutions.
  B. Manage the connectors as solution components and deploy the components by using ALM pipelines.

  ---

  Explanation

  Manage the connectors as solution components and deploy them by using ALM pipelines. Custom connectors are Power Platform solution components, so packaging them in a solution and deploying them through a pipeline provides consistency, traceability, and controlled promotion between development, test, and production. Environment variables can hold environment-specific values, but they do not deploy or govern the connector definition itself. Unmanaged imports into production also allow uncontrolled edits, which conflicts with ALM governance.

• Question 110:

  HOTSPOT

  What should you include in the custom AI agent design to meet the R&D product specifications and the compliance information requirements? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The answer-area image selects "a custom connector" to expose the data to the agent and "a tool" to add the capability to the agent. Copilot Studio tools are the mechanism that lets an agent interact with external systems, and Microsoft lists custom connectors, REST APIs, and Model Context Protocol as supported ways to add tool capabilities. In this scenario, the R&D department already has an MCP server that contains product specifications and compliance data, so the design should expose the existing R&D capability through a connector and make that capability available to the custom agent as a tool. An Azure AI Bot Service channel is about bot channel connectivity, not exposing proprietary data to the Copilot Studio agent. A custom OData entity, Semantic Kernel, event trigger, or standalone REST API does not match the selected low-code design shown in the answer-area image.