Key details for this exam, checked against the published exam outline
Each question shows the correct answer and an explanation of why it is right
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:
* Microsoft Dataverse data stored in Canada
* 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?
The key issue is that the agent will run in a Canadian environment and use:
Dataverse data stored in Canada
a connector to Azure OpenAI in the United States
That means data may need to move across regions. Before deployment, the organization must make sure this cross-region use is explicitly allowed under the platform's data movement and residency controls.
That makes C the correct answer.
Why C is correct:
It directly addresses the fact that the solution uses services in different geographic regions
It ensures the environment and its connector dependencies are configured to allow that movement in line with platform policy
It is the most specific action tied to data residency and data movement compliance before deployment
Why the other options are not correct:
A . Ensure that the data processed by Azure OpenAI is stored in the United States. This does not address whether the cross-region movement itself is permitted.
B . From the Microsoft Purview portal, validate the Data loss prevention settings. DLP helps govern connector usage and data exfiltration, but the question is specifically about data residency and cross-region data movement.
D . Migrate the tenant to the United States. This is unnecessary and does not align with the stated Canadian deployment requirement.
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.
For Microsoft Copilot Studio ALM across development, test, and production, the right approach is to package the app components properly and use controlled deployment in production.
A . Include agents and connectors in a solution is correct because solutions are the standard Power Platform ALM container for moving components consistently across environments. Putting both the agents and the custom connectors into the solution ensures they travel together and remain aligned.
D . Deploy managed solutions to production is also correct because managed solutions are intended for production use. They help prevent direct editing in production and support stronger governance and release control.
Why the other options are not correct:
B . Move the agents between environments by using data export and import is not the recommended ALM approach for Copilot Studio components.
C . Manually rebuild the agents in each environment creates inconsistency and increases effort and risk.
E . Deploy unmanaged solutions to production would allow easier direct modification, which conflicts with the requirement to prevent direct editing in production.
A company processes invoices stored across multiple systems in multiple formats.
You need to implement an Al solution to automate the invoice processing. The solution must meet the following requirements:
* Automate multi-step invoice processing tasks, including document analysis, data validation, and approval routing.
* Enable users to interact directly via Microsoft Teams to review and approve invoices.
* Minimize development efforts to define and customize approval workflows.
What should you include in the solution?
This scenario requires an AI solution for invoice processing across multiple systems and formats, while also allowing direct user interaction in Microsoft Teams and keeping workflow customization effort low.
The best option is Microsoft Copilot Studio and AI Builder.
Why this is correct:
AI Builder can be used for document-focused automation tasks such as extracting data from invoices and supporting structured business document processing.
Microsoft Copilot Studio can provide the conversational and workflow-driven layer, including interaction through Microsoft Teams.
Together, they support multi-step automation, including:
document analysis
extracted data handling
validation steps
routing for human review and approval
This combination also aligns with the requirement to minimize development effort, because Copilot Studio and AI Builder are low-code tools designed for rapid business solution delivery.
Why the other options are less suitable:
A . Azure Document Intelligence in Foundry Tools and Azure Logic Apps This can handle extraction and workflow automation, but it usually requires more implementation effort and does not as naturally satisfy the Teams-centric low-code user interaction requirement as Copilot Studio does.
C . Azure OpenAI and Azure Functions This is far more custom-development-heavy and does not meet the goal of minimizing workflow customization effort.
D . a SharePoint agent A SharePoint agent is too narrow for this broader multi-system invoice processing and approval workflow scenario.
A company has an Azure environment that supports multiple business units.
The company plans to implement an Al solution that will pertain sentiment analysis on customer product reviews. You need to evaluate the potential cost of the solution to support return on Al investment (ROAI) analysis. What should you use?
To evaluate the potential cost of an Azure-based AI solution --- including compute, storage, networking, and AI service consumption --- the correct tool is:
Azure Cost Management + Billing
It allows you to:
Estimate and track Azure resource costs
Analyze usage patterns
Forecast spending
Support ROAI calculations by giving real cost baselines and projections
What should you recommend to assist the CEO with their specific responsibilities?
The CEO's responsibility is to ensure that all AI solutions adhere to industry-standard responsible AI practices. The case study also explicitly says the CEO wants a quarterly assessment that must verify:
reliability
interpretability
fairness
compliance
The best recommendation is D. the Responsible AI dashboard.
Why this is correct: The Responsible AI dashboard is the Microsoft-recommended capability for evaluating AI systems against responsible AI dimensions such as fairness, interpretability, error analysis, and model behavior assessment. It aligns directly with the CEO's governance-focused responsibility.
Why the other options are not the best fit:
A . Compliance Center focuses more broadly on Microsoft 365 compliance and governance, not full responsible AI evaluation dimensions like fairness and interpretability.
B . Microsoft Foundry Tools is too broad and not the specific assessment tool for responsible AI measurement.
C . the Microsoft Service Trust Portal provides compliance documentation and trust information, but it does not assess Contoso's AI solutions for fairness and interpretability.
E . Microsoft Purview is strong for data governance, classification, compliance, and auditing, but it is not the dedicated Microsoft tool for responsible AI evaluation across those four dimensions.
A company has an Al solution named Solution1 that is deployed to the production environment. Solution! uses an Azure OpenAI model to generate marketing emails for existing customers.
During an internal review, you identify that Solution1 creates different emails depending on the customers' traits.
You need to recommend a strategy to mitigate the bias. The strategy must adhere to Microsoft responsible Al principles.
What should you recommend?
The scenario describes a deployed AI solution using Azure OpenAI that exhibits bias (creating disparate outcomes based on customer traits). This directly impacts the Fairness principle of Microsoft's Responsible AI framework.
Why 'Modify the system instructions' is the Correct Strategy:
Direct Control via System Metaprompts: In large language model (LLM) applications like those powered by Azure OpenAI, the system instructions (or system message) define the behavior, constraints, and tone of the model. By modifying these instructions, you can explicitly direct the model to treat all customer segments equitably and ignore specific sensitive traits when drafting marketing content.
Mitigation without Re-engineering: * Option B and D (Training/Retraining): Azure OpenAI models are foundation models. Most companies use them via API and do not have access to the original 'training dataset' to modify it. While fine-tuning is possible, it is significantly more expensive and complex than prompt engineering.
Option C (Randomization): Randomization does not solve bias; it creates inconsistency and potentially irrelevant content, violating the Reliability and Safety principle.
Alignment with Responsible AI: Microsoft's documentation on Fairness recommends 'Instructional Mitigation.' This involves adding specific rules to the system prompt, such as: 'You must ensure the tone and value proposition of the email remain consistent across all demographic groups' or 'Do not use customer traits such as age or gender to influence the core marketing message.'
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 configure Al Builder lead scoring models to influence opportunity summaries. Does this meet the goal?
AI Builder lead scoring models are used to score and prioritize leads. They do not control how opportunity summaries in Dynamics 365 Sales Copilot are generated or displayed.
The requirement is specifically about customizing:
how opportunity summaries are generated, or
how they are presented to users
Configuring a lead scoring model affects lead qualification insights, not Copilot's opportunity summary generation or presentation layer.
Exam domains verified against: Official Microsoft AB-100 exam guide, last checked October 2026.
This domain covers analyzing requirements for AI-powered solutions and assessing how agents can automate tasks and enhance decision-making. You'll review data quality dimensions such as accuracy, relevance, and timeliness, then organize business data for use by other AI systems. The domain also includes evaluating costs and benefits of AI solutions through ROI analysis and build versus buy decisions.
Sample question from this domain above: Q1
This domain focuses on designing AI and agents for business processes across Dynamics 365 apps, Copilot Studio, and Power Platform. You'll design customizations, connectors, autonomous agents, and task agents, then apply the Power Platform Well-Architected Framework to intelligent workloads. The domain includes designing data processing for grounding, creating topics for Copilot Studio, and orchestrating configuration for prebuilt agents.
This domain emphasizes analyzing, monitoring, and tuning deployed AI solutions using performance metrics and telemetry data. You'll manage testing through validation criteria and end-to-end test scenarios, design Application Lifecycle Management processes for agents and custom models, and implement responsible AI governance. The domain also covers designing security, access controls, governance frameworks, and audit trails for models and data.
Common questions about the exam itself
