AB-100 Agentic AI Business Solutions Architect Questions and Answers

The CFO’s quarterly analysis is focused on comparing:

estimated ROI

actual measured efficiencies

actual adoption

The case study explicitly says the CFO will use the Copilot Studio agent usage estimator . For that kind of analysis, the most relevant design components are the ones that affect how the agent is used operationally and how interactions are processed.

Why C. the average session time per agent is correct:

Average session time is a practical usage and adoption indicator. It helps the CFO understand how much users are engaging with the agent and whether the agent is reducing effort efficiently or creating long, costly interactions.

Why D. the agent orchestration method is correct:

The orchestration method affects how the agent handles requests, invokes tools, uses knowledge sources, and consumes resources. Since this can influence both operational efficiency and cost, it is important for ROI analysis.

Why the other options are not the best fit:

A. the GPT models used for the agent Model choice can matter technically, but the CFO’s quarterly Copilot Studio estimator-based analysis is more centered on usage and orchestration behavior than on model selection details.

B. the average characters in a chat message This is too granular and is not a primary business-facing metric for ROI or adoption analysis.

Verified Answer : =

CISO → Azure Resource Graph Explorer

CIO → Microsoft Purview

Comprehensive and Detailed Explanation from Agentic AI Topics:

The CISO is responsible for discovering and inventorying AI resources for auditing across multiple Azure subscriptions. The best tool for that is Azure Resource Graph Explorer , because it is designed to query Azure resources at scale across subscriptions and provide visibility into what AI-related resources exist for governance and audit purposes.

The CIO is responsible for ensuring that appropriate security labels are assigned to the data used by the AI agents . The best tool for that is Microsoft Purview , because Purview supports data governance, classification, sensitivity labeling, and compliance management across enterprise data assets.

Why the other options are not correct:

Azure Blob Storage is storage, not the primary tool for discovery/inventory or labeling governance.

Copilot Studio is for building and managing agents, not for Azure-wide AI resource inventory or enterprise data labeling.

The custom AI agent must select topics based on a description of the purpose of the query , rather than relying on fixed trigger phrases . That is exactly the scenario where generative orchestration is the right configuration.

Why B is correct:

It enables the agent to choose the best topic, tool, or action based on the semantic meaning of the user’s request

It supports more conversational interactions

It aligns directly with the requirement that topic selection should not depend on trigger phrases

Why the other options are not correct:

A. Azure OpenAI reasoning models concerns model capability, not topic-routing behavior in Copilot Studio

C. classic orchestration relies more on predefined topics and trigger phrases

D. AI-assisted evaluators are for assessment/testing, not runtime orchestration

Verified Answer : =

CFO concerns about Copilot Studio credit usage → Effectiveness

CTO concerns about poor feedback on AI agent responses → Satisfaction

Comprehensive and Detailed Explanation from Agentic AI Topics:

The correct mapping is based on what each executive is trying to measure in Copilot Studio analytics .

For the CFO , the concern is about abandoned interactions compared to resolved conversations and whether Copilot Studio credits are being used efficiently. That aligns with Effectiveness , because effectiveness metrics focus on conversation outcomes such as whether interactions are successfully resolved or dropped before completion.

For the CTO , the concern is specifically about user feedback on the quality of AI agent responses . That maps to Satisfaction , because satisfaction metrics capture user sentiment and feedback about the interaction quality.

Why the other metrics are not the best fit:

Use is more about adoption and interaction volume.

Tool use focuses on how often tools/actions are invoked, not on abandonment versus resolution or feedback quality.

Verified Answer : =

To expose the data to the agent, create: a custom connector

Add to the agent: the MCP server

The custom agent must answer questions about product specifications and compliance information , and the case study states that the R & D department already has a custom Model Context Protocol (MCP) server containing that information.

The best design is:

create a custom connector to expose that external capability cleanly to the low-code Copilot solution

add the MCP server to the agent so the agent can use that external knowledge/tooling source

Why this is correct:

The MCP server already exists and contains the needed product-specification and compliance data.

In a Copilot/agent design, you need a way to expose external functionality and data in a reusable, secure way. A custom connector is the low-code integration mechanism that fits this requirement.

Then the agent can use the MCP server as the connected external capability for answering those questions.

Why the other options are not correct:

Azure AI Bot Service channel is for communication channels, not for exposing this knowledge source.

a custom OData entity is not the right pattern for integrating the existing MCP-based capability.

the Semantic Kernel is a developer orchestration framework, but the requirement emphasizes using the existing MCP technology in a low-code solution.

an event trigger is unrelated to exposing R & D specification/compliance knowledge.

a REST API is too generic here; the scenario specifically points to the existing MCP server .

a tool is close conceptually, but the most direct answer choice tied to the existing R & D technology is the MCP server .

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.

Comprehensive and Detailed Explanation From Agentic AI Business Solutions Topics:

The correct answer is A. Microsoft Dataverse .

This question is asking for a Microsoft Power Platform business solution that can act as a centralized data foundation across multiple AI and business application workloads. The requirements are very specific:

consolidate data from multiple internal and external sources

serve as a centralized source for Copilot Studio agents , Dynamics 365 , and external AI models

support built-in data classification and protection policies

provide data for grounding and analytics

Among the options, Microsoft Dataverse is the best fit.

Why A is correct

Microsoft Dataverse is the native business data platform for Microsoft Power Platform and Dynamics 365. It is designed to act as a structured, centralized, governed source of business data. That makes it the strongest answer when the scenario explicitly involves:

Copilot Studio

Dynamics 365

broader Power Platform

governed enterprise business data

AI grounding and analytics

Dataverse supports these needs because it provides:

a common business data model

secure centralized storage

integration across Power Platform and Dynamics 365

metadata-rich tables and relationships

role-based security

support for business rules and governance

compatibility with analytics and AI-based experiences

From an AI business solutions perspective, Dataverse is especially strong because it can act as the single source of truth for enterprise business data that powers both transactional applications and AI systems.

Why Dataverse fits the AI requirements

For AI systems, especially Copilot and agent scenarios, centralized structured business data is essential for:

grounding responses in current operational data

supporting retrieval across customer, sales, finance, or service records

enabling governed access to sensitive information

providing high-quality data for downstream reporting and analytics

Dataverse also aligns well with the requirement for built-in data classification and protection policies , because it works within Microsoft’s enterprise governance ecosystem and supports security, auditing, and compliance-oriented controls better than the other listed options in a Power Platform business context.

Why the other options are incorrect

B. Azure Data Lake Storage

Azure Data Lake Storage is excellent for large-scale analytics and raw data storage, but it is not the best Power Platform business solution answer here. It lacks the same native business application integration and governed operational data model that Dataverse provides for Copilot Studio and Dynamics 365 scenarios.

C. a Microsoft Power BI semantic model

A semantic model is useful for reporting and analytics, but it is not the central operational data platform for multiple AI systems. It sits more at the reporting layer than the transactional and grounding layer.

D. Azure Cosmos DB

Cosmos DB is a scalable NoSQL database, but it is not the native Microsoft Power Platform business data platform for Dynamics 365 and Copilot Studio integration. It also does not provide the same built-in business data modeling and governance experience expected here.

Expert reasoning

When the question combines:

Power Platform

Dynamics 365

Copilot Studio

centralized business data

governance

AI grounding

the best answer is almost always Microsoft Dataverse .

So the correct choice is:

Answer: A

The agent must deliver accurate and timely responses while customer data is spread across several systems:

ServiceNow

Dynamics 365 Finance

Dynamics 365 Supply Chain Management

Excel files in SharePoint Online

The most appropriate recommendation is Microsoft Power Platform connectors because they are the standard low-code integration mechanism for bringing together data and actions from multiple enterprise systems inside Microsoft Copilot Studio .

Why D is correct:

Connectors let the agent access data across different business systems

They reduce development effort compared with custom integration patterns

They help the agent ground responses on the latest data from connected sources

Why the other options are not the best fit:

A. Enable incremental indexing in Azure AI Search Useful in search-based architectures, but the core issue here is connecting multiple business systems into the agent solution.

B. Implement a model router for query handling A router helps distribute requests, but it does not solve enterprise data access and grounding across these systems.

C. Create custom prompts Prompting alone does not integrate the source systems or ensure current enterprise data access.

Comprehensive and Detailed Explanation From Agentic AI Business Solutions Topics:

The correct answer is E. Microsoft Purview .

This question is centered on governance , specifically the need to:

monitor changes to model configurations

audit data usage

minimize administrative effort

That combination points most strongly to Microsoft Purview .

Why E is correct

Microsoft Purview is Microsoft’s core platform for data governance, compliance, auditing, information protection, and lifecycle oversight . When an organization is using Azure OpenAI models and needs a governance-oriented solution for monitoring and auditing how data is used, Purview is the best fit among the listed options.

From an AI business solutions perspective, governance is broader than infrastructure monitoring. It includes:

understanding how sensitive data is handled

tracking access and usage patterns

supporting audit and compliance needs

helping investigate data exposure concerns

enforcing information governance practices across AI-enabled workloads

Purview is especially strong when the requirement includes auditing data usage because that is a governance and compliance concern, not just a performance or telemetry concern.

It also minimizes administrative effort because it provides centralized governance capabilities rather than requiring the company to stitch together multiple lower-level services for oversight.

Why the other options are incorrect

A. Azure Monitor

Azure Monitor is useful for telemetry, logs, metrics, and operational monitoring. It helps observe system performance and activity, but it is not the best primary governance solution for auditing data usage and broader compliance oversight.

B. Azure Stream Analytics

This service is used for real-time stream processing and analytics. It does not address governance and audit requirements for Azure OpenAI model configurations and data usage.

C. Azure API Management

API Management helps publish, secure, and manage APIs. It is valuable for access mediation and control, but it is not the main governance and auditing platform for data usage and model-configuration oversight.

D. Azure Policy

Azure Policy is very strong for enforcing resource configuration standards and compliance rules at deployment and configuration time. However, the question also emphasizes auditing data usage , which is better aligned to Purview’s governance capabilities. Policy is more about enforcement of resource state; Purview is stronger for governance, auditing, and data oversight.

Expert reasoning

Use this exam shortcut:

Need operational logs and metrics → Azure Monitor

Need deployment/configuration enforcement → Azure Policy

Need data governance, auditing, compliance, and information oversight → Microsoft Purview

Because the question emphasizes both changes and data usage auditing with a governance lens, Microsoft Purview is the strongest answer.

So the correct choice is:

Answer: E

Restricts access to grounding data → Microsoft Purview access policies; Restricts model fine-tuning → Role-based access control (RBAC) in Microsoft Foundry

Why Microsoft Purview access policies is correct

The grounding data is stored in Microsoft Fabric , and the requirement is to restrict access to that data to only assigned roles.

That is a data governance and access control requirement. Microsoft Purview access policies are the best fit because they are designed to govern and control access to data across enterprise data estates. In this case, they help ensure that only authorized roles can access the grounding data used by the agents.

From an AI business solutions perspective, grounding data is often one of the most sensitive parts of the solution because it can contain:

proprietary business knowledge

internal documents

regulated operational information

contextual data used to shape model outputs

Purview helps enforce governed access to that data layer rather than relying only on general infrastructure controls.

Why RBAC in Microsoft Foundry is correct

The second requirement is to ensure that only the AI engineering team can perform model fine-tuning .

That is an action-level platform permission requirement. The best control for that is role-based access control (RBAC) in Microsoft Foundry .

RBAC allows the organization to assign permissions based on job function, so only authorized users or groups can:

create or modify fine-tuning jobs

manage model assets

update training configurations

control deployment-related AI resources

This is the right governance pattern because fine-tuning changes model behavior and can introduce:

security risk

compliance risk

quality drift

misuse of proprietary datasets

Restricting that capability to the AI engineering team through RBAC creates a clear separation of duties.

Why the other options are incorrect

Azure AI Content Safety

This is used to detect and filter harmful content. It does not control access to Fabric grounding data.

Azure Monitor alerts

Alerts help observe activity, but they do not enforce role-based access to data.

Azure Policy compliance rules

Azure Policy is useful for enforcing resource configuration standards, but it is not the best answer for role-based access to Fabric grounding data or for limiting fine-tuning actions to a specific team.

Azure Resource Manager (ARM) resource locks

Resource locks help prevent deletion or modification of Azure resources, but they do not provide the right permission model for controlling who can perform model fine-tuning operations.

Microsoft Entra Conditional Access

Conditional Access is mainly about sign-in and access conditions, such as device, location, or risk context. It is not the best direct control for restricting fine-tuning permissions inside Foundry.

Expert reasoning

Use this exam shortcut:

Need to control access to enterprise data → think Purview access policies

Need to restrict who can perform AI platform actions like fine-tuning → think RBAC in the AI platform

So the correct mapping is:

Restricts access to the grounding data: Microsoft Purview access policies

Restricts model fine-tuning: Role-based access control (RBAC) in Microsoft Foundry

For Microsoft Copilot Studio best practices:

???? Microsoft Power Platform Well ‑Architected Framework

Why?

Copilot Studio is part of the Power Platform.

Microsoft’s official guidance for building scalable, secure, compliant Power Platform solutions is the Power Platform Well ‑Architected Framework .

It includes governance, security, reliability, operational excellence, and cost optimization—exactly what Fabrikam needs for AI agent deployment, telemetry, compliance, and ROI.

For conversational user experiences:

???? Success by Design

Why?

Success by Design is Microsoft’s methodology for implementing Dynamics 365 and Power Platform solutions.

It includes conversational design checklists , solution blueprinting, risk assessments, and user ‑adoption strategies.

Fabrikam’s scenario emphasizes:

User adoption

Conversational UX quality

Escalation paths

Compliance

Telemetry

These are all covered in Success by Design’s structured implementation approach.

https://learn.microsoft.com/en-ca/power-platform/well-architected/experience-optimization/conversation-design

The requirement is to evaluate the potential cost of an AI solution before deployment so the company can support a return on AI investment (ROAI) analysis .

The correct choice is C. Azure pricing calculator .

Why C is correct:

The Azure pricing calculator is used to estimate the expected cost of Azure services before implementation. For an AI solution such as sentiment analysis on customer product reviews , it helps estimate likely spending across the relevant Azure components and usage patterns. That makes it the right tool for cost forecasting as part of ROAI planning.

Why the other options are not correct:

A. Total Cost of Ownership (TCO) Calculator TCO is mainly used to compare broader infrastructure costs, often for migration or environment-level cost comparisons, not detailed service pricing estimation for a planned Azure AI solution.

B. Azure Reservations Reservations are a purchasing/discount mechanism, not the primary tool for estimating potential solution cost.

D. Azure Monitor Azure Monitor tracks operational metrics and runtime health after deployment; it is not used for pre-deployment cost estimation.

The key issue in this scenario is that the web app user interface changes frequently , which causes the automation to fail. The requirement also says the solution must minimize changes to the agent .

The best recommendation is Computer Use in Copilot Studio .

Why this is correct:

Computer Use is designed for UI-based automation where the agent interacts with applications much like a human would.

It is especially useful when a system does not provide a stable API or when the UI changes over time.

Compared with rigid selectors or brittle scripted automations, Computer Use is more resilient in dynamic interfaces.

This directly addresses the problem of frequent UI changes while reducing the need to constantly redesign or heavily modify the existing agent.

Why the other options are not the best fit:

A. conversation topics in Copilot Studio Topics help guide dialog and intent handling. They do not solve UI automation fragility caused by changing app screens.

B. an agent flow in Copilot Studio Agent flows help orchestrate logic and process steps, but they do not specifically solve the issue of unreliable UI interaction caused by layout changes.

D. custom models in Azure AI Studio Custom AI models are for specialized intelligence tasks, not for stabilizing web UI automation.

Copilot Studio → Use a Microsoft Power Platform deployment pipeline; Microsoft Foundry → Use an Azure DevOps pipeline

The goal is to use generative AI to answer questions based on a subset of corporate data , and to ensure that this data is available as a grounding data source .

The solution includes:

Dataverse tables

a Power BI workspace

a canvas app

a Power BI semantic model using DirectQuery to Dataverse

The best action is D. Endorse the semantic model.

Why D is correct:

Endorsing a semantic model makes it a trusted, discoverable enterprise data asset

It is the appropriate step when you want approved corporate data to be used reliably by downstream AI and analytics experiences

It fits the requirement of exposing a curated subset of data as a grounding source rather than duplicating or manually exporting it

Why the other options are not correct:

A. Export the semantic model Exporting does not make it a governed grounding source.

B. Share WS1 Sharing the workspace grants access, but it does not establish the semantic model itself as the trusted data source for grounding.

C. Populate a Dataverse table The data already exists and is modeled through the semantic layer; creating another table is unnecessary for this requirement.

The requirement is to secure agents in a Microsoft Power Platform environment so that they:

use only approved connectors and services

are prevented from accessing sensitive data

The correct recommendation is B. Deploy data loss prevention (DLP) policies in Power Platform.

Why B is correct:

DLP policies in Power Platform are specifically designed to control which connectors can be used together and which services are allowed in an environment. They help administrators classify connectors as business or non-business and restrict unsafe data flows. This directly supports both requirements:

limiting agents to approved connectors/services

preventing data from being exposed through unapproved or risky connector usage

Why the other options are not correct:

A. Enable customer-managed keys in Microsoft Dataverse This helps with encryption control, not with restricting connector usage or preventing data movement through agents.

C. Configure Azure Monitor to capture connector activity logs Monitoring logs is useful for visibility, but it does not enforce connector restrictions or prevent sensitive data access.

D. Enable a Microsoft Dataverse audit Auditing records activity after the fact. It does not proactively block unapproved connectors or sensitive data exposure.

To improve performance → Move to a multi-agent architecture

To improve accuracy → Add a grounding data source

The current design uses a single agent and a single prompt to complete a series of tasks . That is often a bottleneck. When one agent is responsible for everything, it has to manage multiple steps, multiple reasoning modes, and multiple task transitions in one flow. This commonly leads to:

slower response times

task overload

incomplete outputs

reduced efficiency as complexity grows

Moving to a multi-agent architecture helps performance because tasks can be separated by function. For example:

one agent can handle task planning

another can retrieve domain knowledge

another can perform structured reasoning

another can prepare the final response

From an agentic AI systems perspective, decomposition improves throughput and execution quality. Instead of one overloaded agent trying to do everything, specialized agents handle narrower responsibilities. That often reduces latency in practical enterprise designs and improves the reliability of task completion.

This also addresses the symptom of incomplete results , because a multi-agent architecture can break a large workflow into smaller, controlled substeps.

Why “Add a grounding data source” improves accuracy

The agent struggles with domain-specific reasoning . That strongly suggests it lacks sufficient domain context during inference.

The best way to improve accuracy in this case is to add a grounding data source .

Grounding means giving the model access to trusted, relevant business knowledge at runtime, such as:

internal documentation

product specifications

policy manuals

knowledge bases

industry-specific reference data

This improves domain-specific reasoning because the model no longer relies only on general pretrained knowledge. Instead, it can anchor its responses in authoritative content.

From an AI business solutions standpoint, grounding is one of the most important mechanisms for improving:

factual relevance

domain accuracy

consistency

trustworthiness

explainability in enterprise contexts

When a model is inaccurate because it lacks business context, grounding is usually a better first fix than simply scaling model size.

Why the other actions are not the best fit

Add a prebuilt connector

A prebuilt connector helps with integration to systems and services, but it does not directly solve slow reasoning, incomplete output, or weak domain-specific reasoning unless the issue is specifically missing access to an external system. That is not the main problem described here.

Upgrade to a larger generative AI model

A larger model may sometimes improve reasoning quality, but it usually comes with higher cost and often slower response times , which works against the stated performance issue. It is not the best recommendation when the current agent is already slow.

Also, when domain-specific reasoning is the problem, grounding is usually more efficient and more controllable than simply choosing a larger model.

Expert reasoning shortcut

Use this exam logic:

Slow and overloaded single agent handling many tasks → move to multi-agent architecture

Weak domain-specific reasoning → add grounding data source

Need system integration → prebuilt connector

Need raw generative capability increase, but can accept more cost/latency → larger model