Microsoft AB-100 Online Practice Questions and Exam Preparation

Microsoft AB-100 Online Questions & Answers

• Question 51:

  A company is designing a Microsoft Power Platform solution to reduce the manual steps of a business process by deploying an existing AI model.

  You need to calculate the return on AI investment (ROAI) by identifying the metadata and telemetry of the solution.

  What should you use?

  A. Microsoft Power Platform admin center
  B. Success by Design
  C. the Business value toolkit
  D. Microsoft Cloud Adoption Framework for Azure
  C. the Business value toolkit

  ---

  Explanation

  The Business value toolkit helps identify and quantify business value drivers for ROAI. It supports structured value estimation instead of relying only on technical metrics. The requirement is to calculate return by identifying benefits from reduced manual process steps, so a value toolkit is a better fit than monitoring or infrastructure tools. For Power Platform and AI business cases, use business value tooling to connect solution capabilities to measurable outcomes.

• Question 52:

  A company needs an agent to update records in a legacy desktop application. The application has no API, no connector, and no supported import interface. Users currently complete the work by opening the app, clicking buttons, choosing

  menu items, and entering text.

  Which Copilot Studio capability should you recommend?

  A. A Dataverse knowledge source
  B. A public website knowledge source
  C. A topic with only trigger phrases
  D. Computer use
  D. Computer use

  ---

  Explanation

  Computer use is the right design because the legacy desktop application has no API, connector, or import mechanism. The only supported way to complete the work is by simulating the user's screen interactions. Connectors, MCP, and normal flows require programmatic interfaces that do not exist here. Use computer use as a last-mile automation pattern for UI-only systems.

• Question 53:

  HOTSPOT

  A company has a Microsoft Copilot Studio prompt-and-response agent.

  You need to ensure that the agent meets the following requirements:

  1. Provides effective and relevant responses

  2. Provides conversational outcomes.

  Which metric should you use 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 effective and relevant responses to generated answer rate and quality and conversational outcomes to topics by outcome. The answer image points to Copilot Studio analytics that evaluate generated answers and topic results. Generated-answer quality measures how well grounded answers perform, while topics by outcome shows how conversation paths end. Satisfaction and reactions add feedback, but they are not the primary measurements named by the requirements.

• Question 54:

  Which tool should you use for the prospect communication requirements in Dynamics 365 Sales?

  A. Azure AI Search
  B. Copilot email assist
  C. the Voice template Microsoft Copilot Studio
  D. Deep Research in Microsoft Foundry Agent Service
  B. Copilot email assist

  ---

  Explanation

  Copilot email assist is designed for sales communication scenarios because it helps sellers draft and refine prospect emails in the flow of work. The requirement is prospect communication in Dynamics 365 Sales, not search, voice bot creation, or broad research. Email assist keeps the experience close to the seller's sales record and communication workflow. For sales email productivity, choose the embedded sales Copilot capability rather than building a separate custom agent.

• Question 55:

  A company has a portfolio of AI initiatives at different stages of development.

  You need to recommend a structured approach to evaluating the return on AI investment (ROAI) across all the initiatives. The solution must balance immediate results with long-term values and strategic innovations.

  What should you include in the recommendation?

  A. a simple cost and benefit analysis
  B. a horizon-based framework
  C. the internal rate of return (IRR) function
  D. a prioritization grid
  B. a horizon-based framework

  ---

  Explanation

  A horizon-based framework is useful for ROAI because it separates short-term, medium-term, and long-term value from AI initiatives at different maturity levels. Portfolio-level investment decisions need a structured way to compare experiments, scaling projects, and mature deployments. A single cost metric or one-time ROI calculation would not capture the different timelines and risk profiles. Use horizons when the question asks how to evaluate a portfolio of AI opportunities over time.

• Question 56:

  A company has multiple AI models that support generation of sales transactions.

  Each release of the models must be reviewed by a security and compliance team before being deployed to the production environment. The security and compliance team must have access to prior versions to properly determine potential exposures introduced.

  You need to recommend a solution to evaluate the impact of each deployment to production. The solution must enhance business continuity.

  What should you recommend?

  A. Create a central model registry that uses version history.
  B. Establish a promotion process by using a quality gate.
  C. Implement version control for all the AI system components.
  D. Track model retirement schedules to prevent service disruptions.
  C. Implement version control for all the AI system components.

  ---

  Explanation

  Version control for all AI system components lets the security and compliance team compare each release with previous versions before production deployment. Models, prompts, data definitions, tools, and configuration can all introduce exposure, so they need history and review. A quality gate is useful, but without versioned components the team cannot inspect what changed. Business continuity improves when releases are traceable and reversible.

• Question 57:

  HOTSPOT

  Which existing tool and data should you use to gather the required metrics for stakeholder signoff for the AI agents? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The completed hotspot selects Microsoft Foundry as the tool and the current time to complete the task today per instance as the required data. The answer image points to a performance measurement that can support stakeholder signoff by comparing current task duration with the AI-enabled target. Foundry is the appropriate place to evaluate and measure agent behavior, while Dynamics 365 Sales is not the evaluation tool for this metric. For signoff, collect current per-instance task time so improvement can be measured against a practical baseline.

• Question 58:

  A company uses Microsoft Dynamics 365 finance and operations apps.

  The company plans to use Microsoft Copilot in-app help and guidance to generate responses for internal business processes.

  You need to add an additional knowledge source for the business processes. The solution must NOT add new topics to the Copilot agent for the finance and operations apps.

  Which knowledge source should you add?

  A. Microsoft Dataverse
  B. a public website
  C. Azure AI Search
  D. a file upload
  D. a file upload

  ---

  Explanation

  A file upload is the right way to add company-specific content for in-app help and guidance because the requirement is to ground responses in internal business-process material. The goal is not to create a new integration or modify the finance application logic. Uploaded reference content can augment generative help while keeping the product documentation separate from company procedures. For help and guidance scenarios, add the approved documents as knowledge rather than retraining a model first.

• Question 59:

  A support agent has authored topics for common issues. For uncommon questions, the company wants the agent to search approved internal content and generate a grounded response without manually authoring a topic for every possible question.

  What should you add?

  A. A model router deployment
  B. A topic with only trigger phrases and no nodes
  C. A content filter with the lowest moderation level
  D. Generative answers with configured knowledge sources
  D. Generative answers with configured knowledge sources

  ---

  Explanation

  Generative answers with configured knowledge sources are correct because the answer exists in approved internal content but does not match an authored topic. The agent should search the configured knowledge and generate a grounded response rather than forcing authors to create a topic for every uncommon question. A fallback without knowledge would be less accurate, and a tool call is unnecessary if the need is content retrieval. Use generative answers for approved knowledge retrieval outside fixed topics.

• Question 60:

  Which framework should you use for the infrastructure migration?

  A. Microsoft Cloud Adoption Framework for Azure
  B. Success by Design
  C. Microsoft Power Platform Center of Excellence (CoE)
  D. Microsoft Power Platform Project Setup Wizard
  A. Microsoft Cloud Adoption Framework for Azure

  ---

  Explanation

  The Microsoft Cloud Adoption Framework for Azure is the right framework for infrastructure migration because it provides guidance for strategy, planning, readiness, migration, governance, and management in Azure. The requirement is about moving infrastructure, not just designing a business application or a Power Platform center of excellence. Success by Design and Power Platform guidance are useful in their own domains, but they are not the primary Azure infrastructure migration framework. Use the Cloud Adoption Framework when the scenario centers on Azure migration and cloud operating model decisions.