Microsoft AB-100 Online Practice Questions and Exam Preparation

Microsoft AB-100 Online Questions & Answers

• Question 91:

  HOTSPOT

  Which framework should you use to meet the AI agent requirements for the sales cycle enablement? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The completed hotspot selects the ALM Accelerator for Microsoft Power Platform for Copilot Studio best practices and the Microsoft Power Platform Well-Architected framework for conversational user experiences. The answer image separates deployment practice from user-experience architecture. The ALM Accelerator supports repeatable Power Platform lifecycle practices, while Well-Architected guidance covers design quality, reliability, and experience considerations for Power Platform workloads. Cloud Adoption Framework and Success by Design are useful in other contexts but do not match these two Copilot Studio-specific needs as directly.

• Question 92:

  A company frequently updates the training data and evaluation criteria for a custom AI model used by an agent. The compliance team must compare each release with prior versions and verify who approved changes before production deployment.

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

  A. Version the data, prompts, evaluation assets, and model artifacts.
  B. Keep approval decisions only in informal chat messages.
  C. Maintain audit trails for changes and approvals.
  D. Deploy every model update directly to production without testing.
  E. Delete older model versions after each deployment.
  A. Version the data, prompts, evaluation assets, and model artifacts.
  C. Maintain audit trails for changes and approvals.

  ---

  Explanation

  Versioning the data, prompts, evaluation assets, and model artifacts plus maintaining audit trails meets the release-comparison and approval requirements. Compliance teams need to see what changed, who approved it, and how each release compares with prior versions. Updating data without version history would make review and rollback difficult. AI ALM should track all inputs that can change model behavior, not just source code.

• Question 93:

  You are reviewing a proposed responsible AI and security design for an agentic business solution.

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

  A. Content filtering for prompts and completions
  B. Public read access to all grounding data
  C. Disabling all audit logging to reduce storage costs
  D. Mitigations for prompt manipulation and indirect prompt attacks
  E. A rule that custom models never require validation
  A. Content filtering for prompts and completions
  D. Mitigations for prompt manipulation and indirect prompt attacks

  ---

  Explanation

  Content filtering for prompts and completions reduces harmful output risk, and mitigations for prompt manipulation and indirect prompt attacks protect the agent from malicious instructions hidden in user input or retrieved content. These controls address responsible AI and security at both input and output boundaries. Pure monitoring or cost controls would not prevent the unsafe behavior. Responsible agent design includes both safety filters and prompt-attack defenses.

• Question 94:

  A company uses multiple Microsoft Copilot Studio agents across different channels.

  You need to recommend a monitoring solution that provides comprehensive telemetry data and performance insights for the agents.

  What should you include in the recommendation?

  A. Application Insights
  B. Azure Advisor
  C. Azure DevOps
  D. Microsoft Dynamics 365 Customer Voice
  A. Application Insights

  ---

  Explanation

  Application Insights provides comprehensive telemetry and performance insights for Copilot Studio agents across channels. It can collect detailed events, traces, and usage data for monitoring and troubleshooting. Azure Advisor and Customer Voice do not provide the same agent telemetry depth. Use Application Insights when the requirement asks for comprehensive operational monitoring.

• Question 95:

  DRAG DROP

  You are designing end-to-end test scenarios for a business solution that uses Microsoft Dynamics 365 Sales and Dynamics 365 Finance.

  You need to ensure that the business solution meets the following test requirements:

  1. Properly exchanges data between the Dynamics 365 apps

  2. Aligns with defined user workflows and business processes.

  Which type of testing should you use for each requirement? To answer, drag the appropriate testing types to the correct requirements. Each testing 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 uses integration testing to verify that the Dynamics 365 apps exchange data properly and user acceptance testing to verify alignment with workflows and business processes. The answer image distinguishes technical interoperability from business validation. Integration testing proves that Sales and Finance pass data correctly, while user acceptance testing confirms that the process works for real users. This is the expected split for end-to-end business solution testing.

• Question 96:

  A manufacturing company wants to deploy an agent that will automate supplier invoice processing.

  You are designing a solution to evaluate the financial implications of the deployment. The company is especially concerned about budget overruns.

  You need to ensure that the solution considers the total cost of ownership (TCO), the expected savings from using automation, and whether to extend the existing AI capabilities.

  What should you include in the design?

  A. a break-even analysis only
  B. adopting prebuilt agents to reduce the deployment time
  C. training a custom model
  D. a return on AI investment (ROAI) analysis
  D. a return on AI investment (ROAI) analysis

  ---

  Explanation

  A return on AI investment analysis fits because the company wants to evaluate financial implications of supplier invoice automation. ROAI compares the cost of implementation and operation with measurable gains such as reduced manual review, faster processing, and lower exception handling effort. The question is not only about technical feasibility; it asks how to evaluate the business case. For AI investment decisions, quantify both costs and benefits.

• Question 97:

  A company has an AI business solution.

  You need to extend the solution so that Microsoft 365 Copilot can invoke external logic hosted in Azure services.

  What should you include in the solution?

  A. Microsoft Copilot Studio skills
  B. Microsoft Power Platform connectors
  C. custom engine agents
  B. Microsoft Power Platform connectors

  ---

  Explanation

  Microsoft Power Platform connectors are the appropriate extension point because Microsoft 365 Copilot and Copilot Studio solutions can use connectors to invoke external business logic. The external logic is already hosted in Azure services, so the solution needs a secure integration surface rather than a new search index or unrelated channel. Connectors also support authentication and reuse across Power Platform assets. In exam scenarios, external API or Azure logic that must be called from a copilot usually maps to a connector or tool.

• Question 98:

  A company has Microsoft 365 Copilot agents.

  You need to design a security solution for the agents. The solution must meet the following requirements:

  1. Identify and mitigate potential risks that relate to AI use.

  2. Protect AI apps and the sensitive data processed or generated by the agents.

  3. Support responsible AI governance by retaining and logging interactions, detecting policy violations, and investigating incidents.

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

  NOTE: Each correct selection is worth one point.

  A. Microsoft Purview
  B. Azure AI Content Safety
  C. role-based access control (RBAC) in Microsoft Foundry
  D. Microsoft Defender
  A. Microsoft Purview
  D. Microsoft Defender

  ---

  Explanation

  Microsoft Purview and Microsoft Defender together address governance, compliance, and protection for Microsoft 365 Copilot agents. Purview helps with sensitive data, retention, audit, eDiscovery, and compliance investigation, while Defender helps detect and mitigate security risks and incidents. Content Safety and Foundry RBAC cover narrower controls and do not provide the full Microsoft 365 governance and protection scope requested. Use Purview for data compliance and Defender for threat protection.

• Question 99:

  HOTSPOT

  You need to design a multi-agent solution that will include a custom agent. The solution must meet the following requirements:

  1. Define the rules and constraints that the agent must follow.

  2. Automate a backend process that involves data movement between services and runs independently of the agent's reasoning steps.

  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 uses conversation topics to define the agent's rules and constraints and a Microsoft Power Automate cloud flow to automate the backend process. The answer image separates conversational design from process automation. Topics control how the agent behaves in the conversation, while cloud flows execute reusable backend work across services. Agent flows may be useful in some designs, but the listed backend automation requirement is best matched to Power Automate.

• Question 100:

  You are designing safeguards for a generative AI solution in Microsoft Foundry. The solution must inspect both user prompts and model completions for harmful content categories and support configurable filtering policies.

  What should you configure?

  A. Dataverse search
  B. Content filters
  C. Teams meeting transcripts
  D. Power BI row-level security
  B. Content filters

  ---

  Explanation

  Content filters are the safeguard that inspect prompts and completions for harmful content categories with configurable thresholds. They help enforce safety policy before and after model generation. Evaluation metrics and observability can report quality, but they do not block harmful prompt or response content in the same way. For prompt and completion safety screening, choose content filtering.