Quiz AB-100: Microsoft Agentic AI Business Solutions Architect

The correct answers are reviewing adherence to responsible AI principles and designing audit trails for changes
to models and data.
Why these are correct: Responsible AI design requires assessing alignment with ethical principles like
fairness, transparency, and accountability. Audit trails provide transparency by documenting how models and
data change over time, enabling organizations to trace decisions and identify potential issues. Access controls
on grounding data ensure only authorized, accurate information influences AI recommendations—this is a
governance and security control essential to responsible AI.
Why the others are incorrect:
l Model Context Protocol automatic filtering: MCP enables extensibility and interoperability for agents,
but it doesn't automatically enforce policy compliance; that requires intentional design and governance.
l Synthetic data replacement: While synthetic data can help with privacy, it doesn't eliminate bias and
creates new risks around data quality and relevance for grounding. The focus should be on data quality
assessment and governance, not wholesale replacement.
l Computer Use without oversight: Computer Use in Copilot Studio enables agents to automate tasks
across apps, but responsible AI requires human oversight and explainability, not full autonomy without
controls.

The correct answer focuses on the planning phase's core requirement: assessing data quality for grounding and
using a build/buy/extend decision framework. The scenario explicitly mentions data quality issues, making data
assessment critical. The AB-100 exam emphasizes that grounding data must be evaluated for accuracy,
relevance, timeliness, cleanliness, and availability before designing agent solutions. Additionally, the 'build,
buy, or extend' analysis is a key ROI and design decision point when planning multi-system implementations.
Building all custom models (option A) skips necessary assessment and wastes resources. Deploying Copilot
before addressing data quality (option C) violates best practices and will result in poor agent performance.
Creating prompts before planning (option D) puts the cart before the horse and ignores the foundational
planning requirements.

The two correct answers address critical multi-agent orchestration requirements. Defining solution rules and
constraints for each platform (Copilot Studio, Microsoft 365 Copilot, Microsoft Foundry) ensures agents operate
safely within organizational policies and data governance boundaries—a key requirement in the design phase.
Implementing a model router is a specific technique mentioned in the exam objectives for intelligently routing
requests to the most suitable model or agent based on context, improving efficiency and user experience.
Option C is incorrect because different agents serve different purposes and may benefit from different models
or knowledge bases optimized for their domain. Option D is incorrect because agents often need to integrate to
provide comprehensive solutions. Option E is incorrect because custom extensibility (through Model Context
Protocol, Computer Use, and agent customization) is often necessary to meet business requirements beyond
prebuilt capabilities.

The correct answer reflects the nuanced decision-making required in the design phase of AI solutions. Standard
NLP, Azure CLU, and generative AI orchestration each have different strengths: NLP excels at pattern matching
with low latency, CLU is optimized for structured entity and intent extraction with labeled training data, and
generative AI orchestration handles complex reasoning and open-ended scenarios. The AB-100 exam
emphasizes that architects must evaluate specific requirements like complexity, data availability, performance
needs, and cost to make appropriate technology choices. Option A is incorrect because generative AI
orchestration adds latency and cost that may be unnecessary for simpler, well-structured tasks. Option C is
incorrect for the opposite reason—not all scenarios require the lightweight approach of NLP. Option D is
incorrect because running all three simultaneously wastes resources and creates unnecessary complexity
without clear business justification.

The correct answer represents the proper post-deployment monitoring and tuning process outlined in the AB-
100 exam. The scenario presents classic symptoms of poor grounding data (outdated product info), stale
knowledge sources (policy changes), and prompt issues (hallucinations). The deployment phase requires
analyzing telemetry, monitoring metrics, assessing user feedback, and iteratively tuning the agent. This
includes validating that grounding data is accurate, relevant, and timely, and ensuring prompts follow best
practices. Option A is incorrect because retraining a large LLM is expensive, time-consuming, and usually
unnecessary—the problem is typically in grounding and prompting, not the model itself. Option C is incorrect
because it abandons the solution rather than improving it through proper tuning. Option D creates a brittle
solution that cannot leverage the agent's strengths and fails to address the root causes of hallucination (poor
grounding and prompts).

The two correct answers directly address the ALM design objectives in the exam. A comprehensive ALM
strategy must account for different artifact types (data, agents, connectors, actions, models) and establish
separate, coordinated processes for each, since they have different update cadences, testing needs, and
rollback requirements. Additionally, audit trails are essential for responsible AI, governance, and
compliance—the exam specifically requires designing audit trails for changes to models and data. These enable
organizations to demonstrate compliance with regulatory requirements and trace issues to their root causes.
Options C and D represent anti-patterns that introduce risk and compliance violations. Option E violates version
control and data governance best practices, making it impossible to audit changes or roll back to known-good
states. Proper ALM requires tooling, versioning, testing gates, and audit trails.
CASE STUDY 1
Background:
Fabrikam, Inc is a global consumer goods company that is undergoing a digital transformation initiative to migrate its
entire infrastructure to the Microsoft cloud. As a key element of this cloud migration, the company will implement
Microsoft Dynamics 365 Sales, moving away from the current on-premises proprietary technologies used by its
business-to-business (B2B) sales team.
As part of the cloud migration, Fabrikam will adopt an AI-first approach to its business solutions and implement AI
solutions, wherever possible, to streamline operations.
Problem Statements
Fabrikam's infrastructure currently relies on various on-premises systems that require sales executives to use
corporate computers with physical keyboards to access business information during customer interactions. Mobile
phones cannot be used for these purposes, as the systems depend on keyboard input. As a result, the sales
executives spend a lot of time using keyboards to search for data on several disparate systems and file servers, rather
than focusing on the customers. This affects the customer experience.
Fabrikam stakeholders are concerned that users will be hesitant to adopt AI. If the AI initiatives are NOT adopted, cost
savings will never be realized. Additionally, funding for future AI initiatives will depend on demonstrating an increase
in AI adoption month over month. As the AI agent initiative for the sales team will be the first for Fabrikam, the rapid
adoption of the agent is a high priority.
Planned Initiatives
General
Fabrikam management has prioritized AI-driven projects to improve efficiency, customer engagement, and responsible
AI adoption. The current application infrastructure is on-premises and must be migrated to the cloud to support the
adoption of these technologies.
Infrastructure Migration
Fabrikam plans to migrate from its current on-premises infrastructure to a completely cloud-based topology; this will
include user authentication, the security framework, and, primarily, the adoption of the services by end users.
All the data from the different systems will be consolidated into a single data source - a common data model that will
use a Microsoft Dataverse environment as a single source of truth (SSOT) for the sales team.
Sales Cycle Enablement
To achieve the company's objectives, Fabrikam intends to implement the following strategies to enhance the sales
cycle:
Use low-code development to create a single AI agent that has Dataverse as its core component.
Ensure that sales managers can access unanswered correspondence from prospects and intervene as appropriate.
Replace the previous proprietary software with Dynamics 365 Sales to track sales cycles and customer interactions.
Have the sales executives use Dynamics 365 Sales to track interactions for open opportunities and send follow-up
communications to prospects.
Have the sales executives use handsfree headsets to interact with an AI agent when they have questions about
internal policies or customer data.
Requirements
Infrastructure Migration
Fabrikam has identified the following infrastructure migration requirements:
Azure must be used for all future infrastructure workloads.
The company must follow Microsoft-recommended methodologies for infrastructure migration to the cloud.
Any created AI agents must have their return on investment (ROI) calculated to ensure that the solution will save the
company money.
Sales Cycle Enablement
Fabrikam has identified the following requirements for sales cycle enablement:
The final AI agent must follow Microsoft recommendations for a conversational user experience.
A designated checklist must be reviewed to ensure that the AI agent follows Microsoft deployment recommendations
for a compliant solution.
Detailed telemetry must be logged for the first created AI agent to help troubleshoot and optimize the agent during
the initial AI agent adoption process.
Unexpected AI agent actions must end in an escalation to a live representative. For example, a sales executive must
be rerouted to a representative if the agent cannot answer a question after two failed attempts.
The return on investment (ROI) of switching from the current process to the future process is required for stakeholder
sign off.
The sales team must use Dynamics 365 Sales to correspond with prospects more quickly and efficiently than
currently.
Sales managers must report on the adoption of the AI agent to key Fabrikam stakeholders on a monthly basis.
Any sensitive information, such as user IDs and names, shared via the AI agent must be tracked for future auditing.

Comprehensive and Detailed Explanation From Agentic AI Business Solutions Topics:
The correct answer is A. Microsoft Cloud Adoption Framework for Azure.
In this scenario, Fabrikam is moving from a fully on-premises environment to a completely cloud-based
topology, and the requirements explicitly state that:
Azure must be used for all future infrastructure workloads
the company must follow Microsoft-recommended methodologies for infrastructure migration to the cloud
That wording points directly to the Microsoft Cloud Adoption Framework for Azure.
The Cloud Adoption Framework is Microsoft's primary guidance for planning and executing enterprise cloud
migrations. It is not just a technical migration checklist; it is a full strategic framework that helps organizations
move workloads to Azure in a structured and governed way. It covers key areas such as:
migration strategy
readiness assessment
governance
identity and security planning
landing zones
operations management
organizational alignment
adoption planning
From an AI-powered business solutions perspective, this matters because AI solutions only succeed when the
underlying infrastructure is modernized correctly. Fabrikam's goals include cloud migration, Dataverse
consolidation, Dynamics 365 Sales adoption, and AI-first business operations. All of these depend on a strong
Azure-based cloud foundation. The Cloud Adoption Framework helps ensure that this transformation is done in
a way that is scalable, secure, and aligned to business outcomes.
Why the other options are incorrect:
B . Success by Design
This framework is mainly used for designing and implementing business applications in a way that improves
adoption, usability, and solution quality. It is highly relevant for conversational experiences, application rollout,
and ensuring users get value from solutions such as Dynamics 365 and Copilot-related implementations.
However, it is not the primary framework for infrastructure migration to Azure.
C . Microsoft Power Platform Center of Excellence (CoE)
The CoE is used to establish governance, monitoring, best practices, and enablement for Power Platform usage
across an organization. It helps manage makers, apps, flows, and adoption across Power Platform
environments. While it is useful after adoption begins, it is not the framework used to migrate enterprise
infrastructure to Azure.
D . Microsoft Power Platform Project Setup Wizard
This is more of a project setup and configuration aid for Power Platform implementations. It does not provide
enterprise-scale migration guidance for moving an organization's infrastructure from on-premises systems to
Azure.
Expert reasoning:
When a question mentions infrastructure migration, Azure, and Microsoft-recommended methodology, the best
match is almost always the Microsoft Cloud Adoption Framework for Azure. In Microsoft solution architecture
and AI business transformation scenarios, this framework is the standard answer for cloud migration planning
and execution.

The two correct answers balance practical decision-making factors. Option A correctly identifies that while the
organization's constraints (moderate maturity, limited expertise, six-month timeline) suggest leveraging
prebuilt solutions, the specific technical requirement—automating legacy system tasks without
APIs—necessitates the extensibility and Computer Use capabilities available in Copilot Studio. This reflects the
exam's emphasis on the 'build, buy, or extend' decision framework. Option C is correct because Computer Use
in Copilot Studio is specifically designed for this scenario: automating user interface interactions and web-
based task sequences in systems that lack API-first integration. Options B, D, and E represent poor decision-
making: option B ignores organizational constraints, option D overcomplicates the solution with unnecessary
custom modeling, and option E prioritizes technical sophistication over business outcomes and timeline
feasibility. The exam expects architects to balance capability, constraints, maturity, and time-to-value.
CASE STUDY 2
Overview
Contoso. Ltd is a high-tech manufacturing company that uses Microsoft Dynamics 365 Finance, Dynamics 365 Supply
Chain Management, and Dynamics 365 Commerce for its North American operations. The company designs and
develops innovative products that have many patents and proprietary technologies. The patents and engineering
designs are closely guarded secrets.
Contoso executives want to integrate and adopt Al solutions to help scale the company in preparation for an
anticipated period of rapid growth.
The company has multiple legal entities and Azure subscriptions that will be used in the adopted Al solutions.
AI Adoption
The following executives will have specific responsibilities in the overall Al adoption:
* Chief Technology Officer (CTO): Select one Dynamics 365 Finance, Dynamics 365 Supply Chain Management, or
Dynamics 365 Commerce prebuilt Al agent and one custom Microsoft Copilot Studio Al agent to prioritize and deploy
during the initial Al adoption phase.
* Chief Information Officer (CIO): Ensure that appropriate security labels are assigned to the data used by the Al
agents
* Chief Financial Officer (CFO): Analyze the return on investment (ROI) for the Al agents being deployed.
* Chief Information Security Officer (CISO): Discover and inventory Al resources for auditing.
* Chief Executive Officer (CEO): Ensure that all solutions adhere to industry-standard responsible Al practices.
All Al initiatives and agents will have a detailed business use case, a defined audience profile, and an estimated ROI
that will compare the cost savings of the current process against the estimated costs of using the new Al solutions.
The company's research and development (R&D) department already has a custom Model Context Protocol (MCP)
server that contains comprehensive product specifications and compliance data.
Prebuilt AI Agent
The CTO has NOT yet selected which prebuilt Al agent to use in Dynamics 365 Supply Chain Management The CTO
wants to view available agent templates to identify which agent will add the most business value.
Depending on which high-priority Al agents are identified, its agent capabilities must be previewed in a discovery
meeting with the relevant business operation stakeholders.
Custom AI Agent
Contoso has identified the following custom Al agent requirements:
* The custom Al agent will use data from Dynamics 365 Supply Chain Management to answer questions for the
manufacturing team as a low-code solution.
* The custom Al agent will be accessible from within Microsoft Teams.
* The custom Al agent must be designed to eventually connect to other agents that can be selected based on their
description.
* The topics used in the custom Al agent will be selected based NOT on a trigger phrase, but on a description of the
purpose of the query, to make the interactions more conversational
* The custom Al agent must be able to answer questions about product specifications by using existing technologies.
The product specifications are maintained by the R&D department.
* The custom Al agent must be integrated with and accessible from Dynamics 365 Supply Chain Management.
* The custom Al agent must be able to use Dynamics 365 Supply Chain Management business logic that is stored
outside of the application.
Analysis, Reporting, and Troubleshooting
Contoso has identified the following analysts, reporting, and troubleshooting requirements:
* The CISO will audit all the Al solutions monthly for compliance and security.
* The CFO will analyze all the Al solutions quarterly to compare the estimated ROI against actual measured efficiencies
and adoption. The CFO will use the Copilot Studio agent usage estimator to perform this analysis.
* The CISO wants to identify how much sensitive data was accessed for a given Al agent run and who accessed the
data. Too much sensitive data accessed by a single user might indicate a high security risk.
* The CTO wants to track user feedback on the quality of the Al agent responses during user interactions with the
agents. Consistently poor feedback will trigger an escalated reengineering discussion.
* The CEO wants a quarterly assessment of all the required metrics for their specific responsibilities. The tools used for
the assessments must be Microsoft-recommended and must verify reliability, interpretability, fairness, and
compliance.
* The CFO wants to identify how many interactions with the Al agents are abandoned on a given day as compared to
resolved conversations. Too many abandoned sessions might indicate that Copilot Studio credits are being used
inefficiently by end users.
Case study question

The CTO wants to view available prebuilt agent templates in Dynamics 365 Supply Chain Management to
decide which one should be prioritized for deployment. Agent management is the feature used to discover,
review, and manage available agent templates and capabilities for Dynamics 365 business applications.
Why this is correct:
It supports discovering available prebuilt agents
It helps evaluate which agent can deliver the most business value
It aligns with the requirement to preview and assess candidate agents during the selection phase
Why the other options are not correct:
B . Immersive Home is more of an experience surface, not the primary tool for selecting prebuilt agent
templates
C . Lifecycle Services (LCS) is used for environment and application lifecycle management, not for browsing
Dynamics 365 AI agent templates
D . Copilot Studio is primarily for building/customizing copilots and agents, not for selecting Dynamics 365
prebuilt Supply Chain Management agent templates