📘 Free AB-100 Sample Questions
Case study -
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam
time as you would like to complete each case study. However, there might be additional case studies or other
exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay
attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections
that follow this case study.
To answer the case study questions, you will need to reference information that is provided in the case. Case
studies and associated questions might contain exhibits or other resources that provide more information about
the scenario described in the case. Information provided in an individual question does not apply to the other
questions in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change
your answers before you move to the next exam section. After you leave this case study, you will NOT be able to
return to it.
To start the case study -
To display the first question in this case study, select the "Next" button. To the left of the question, a menu
provides links to information such as business requirements, the existing environment, and problem statements.
Please read through all this information before answering any questions. When you are ready to answer a question,
select the "Question" button to return to the question.
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.
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.
A
Correct Answer:
A.
Explanation:
the ALM Accelerator for Microsoft Power Platform.
ALM = Application Lifecycle Management
It manages the entire lifecycle of apps and copilots, including:
Development
Version control
Testing
Deployment
Updates
For conversational user experiences
Microsoft Power Platform Well-Architected framework.
What this framework does
Performance
Security
Reliability
The Power Platform Well-Architected Framework provides guidance on designing solutions with:
Operational excellence
User experience
Case study -
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam
time as you would like to complete each case study. However, there might be additional case studies or other
exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay
attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections
that follow this case study.
To answer the case study questions, you will need to reference information that is provided in the case. Case
studies and associated questions might contain exhibits or other resources that provide more information about
the scenario described in the case. Information provided in an individual question does not apply to the other
questions in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change
your answers before you move to the next exam section. After you leave this case study, you will NOT be able to
return to it.
To start the case study -
To display the first question in this case study, select the "Next" button. To the left of the question, a menu
provides links to information such as business requirements, the existing environment, and problem statements.
Please read through all this information before answering any questions. When you are ready to answer a question,
select the "Question" button to return to the question.
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.
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
Correct Answer:
A. Microsoft Cloud Adoption Framework for Azure
Explanation:
Why optionA –Microsoft Cloud Adoption Framework for Azure – is the correct choice
The Cloud Adoption Framework (CAF) provides a Microsoft-recommended end-to-end methodology for
moving on-premises workloads to Azure, covering assessment, solution design, migration, validation, and
operations.
It aligns with Fabrikam’s requirement to “follow Microsoft-recommended methodologies for infrastructure
migration to the cloud” and includes guidance on ROI calculation, security, and telemetry, which are
explicitly part of the migration objectives.
CAF’s migration planning workstreams map directly to the stated needs: consolidating data into a single
Dataverse source, establishing a unified authentication and security model, and ensuring audit-ready
telemetry for AI agents.
The framework also integrates with other Microsoft services (Azure Migrate, Azure Arc, Power Platform,
Dynamics365) needed for the downstream AI-agent and sales-automation components.
Why the other options are less suitable
lift-and-shift or the detailed migration checklist required by Fabrikam.
workloads to the cloud.
Success by Design (B) – This is a go-to-market and consumption model for Power Platform that focuses on
licensing and value realization, not a migration methodology. It does not address the low-level infrastructure
Microsoft Power Platform Center of Excellence (CoE) (C) – A CoE provides governance, best-practice
guidance, and community support for building and scaling low-code solutions, but it is not a migration
framework. It cannot replace the structured, Azure-centric migration process mandated for moving all
Power Platform Project Setup Wizard (D) – This wizard creates a new Power Platform project scaffolding
(dataverse, Power Apps, Power Automate templates). It is a development-level tool for prototyping solutions,
not a comprehensive migration framework that covers network, identity, security, and data-migration phases
required for the overall infrastructure transformation.
Conclusion
Only the Microsoft Cloud Adoption Framework for Azure supplies the full, Microsoft-endorsed migration
pathway that satisfies Fabrikam’s migration, security, ROI, and telemetry requirements, making it the optimal
choice for the infrastructure migration question.
References
Microsoft Cloud Adoption Framework (CAF) – Overview and migration guidance:
https://learn.microsoft.com/en-us/azure/architecture/cloud-adoption-framework/
CAF Migration best practices – Detailed steps for assessing, planning, and executing cloud migrations:
A company uses Microsoft Dynamics 365 Sales to manage leads that are stored in a Microsoft Dataverse table
named Lead and use non-standard terminology and custom columns.
You need to configure business terms in the Lead table so that Microsoft Copilot controls can summarize the leads
efficiently. The solution must minimize administrative effort.
How should you configure the business terms?
A
Combine all the fields into one custom field.
B
Map the field display names as business terms.
C
Add the schema names as business terms.
D
Create new business terms for each field.
Correct Answer:
B. Map the field display names as business terms.
Explanation:
Business terms in Dynamics365 must map to standard field names that Copilot can reference – by mapping
the display names of the custom columns to business terms, the platform creates readable, searchable labels
that Copilot’s summarisation engine recognizes without additional configuration.
OptionB (Map the field display names as business terms) directly achieves this mapping, requiring only a
one-time entry per term and no changes to the underlying schema. This minimizes admin effort while keeping
the terminology aligned with the data model that Copilot consumes.
different data points, and is not supported for business-term mapping.
References
OptionA (Combine all fields into one custom field) loses granularity, prevents Copilot from distinguishing
OptionC (Add the schema names as business terms) introduces technical, internal identifiers that are not
user-friendly; Copilot expects human-readable terms, so summarisation would be harder to understand and
maintain.
OptionD (Create new business terms for each field) duplicates effort and does not tie the terms to the actual
field metadata, leading to unsynchronised terminology and higher maintenance overhead.
Conclusion: Mapping display names (OptionB) aligns terminology with Copilot’s expectations, maximises
summarisation accuracy, and requires the least administrative overhead.
Configure business terms in Dynamics365 Sales: https://learn.microsoft.com/en-us/dynamics365/sales
enterprise/business-terms
How Copilot uses business terms for summarisation: https://learn.microsoft.com/en-us/dynamics365/sales
enterprise/copilot-summarisation-terms-guide
DRAG DROP -
You are designing two Microsoft Copilot Studio agents named Agent1 and Agent2. Each agent must meet the
following requirements:
Each agent must use a standard model.
Each agent must NOT use generative orchestration.
Agent1 must support simple and short phrases for a given topic.
Agent2 must integrate with Microsoft Dynamics 365 Contact Center voice channel.
You need to recommend language models for the agents.
What should you recommend for each agent? To answer, drag the appropriate language models to the correct
agents. Each language model 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.
A
Correct Answer:
A.
Explanation:
Agent1 – Natural Language Understanding (NLU)
What NLU is
Natural Language Understanding (NLU) is a capability that allows a system to:
Understand user intent
Extract entities
Process natural language inputs
Agent2 – Natural Language Understanding + (NLU+)
More advanced reasoning
Context awareness
NLU+ is an enhanced language model capability that extends NLU with additional intelligence such as:
Generative AI responses
Improved conversation handling
It can support:
Integration with knowledge sources
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
Correct Answer:
D. . a file upload
Explanation:
File upload is the supported knowledge-source type for in-app Copilot guidance in Dynamics365 Finance &
Operations.
It can be added directly from the Copilot studio without creating new “topics” in the agent’s navigation model.
The uploaded document (e.g., a PDF or Excel guide) is indexed locally and made available to the Copilot
engine, enabling it to retrieve context-relevant passages during user interaction.
This approach meets the requirement of adding a knowledge source while not altering the existing topic
structure.
“no new topics” constraint.
required for the scenario.
References
Why the other options are unsuitable
Microsoft Dataverse – Used for structured data storage and custom entity design, not for delivering ad-hoc
guidance content to the Copilot UI. Adding content here would require custom plugin development and would
not be consumed as a “knowledge source” by the in-app guidance engine.
A public website – External URLs are not ingestible by the Copilot knowledge-source service; they would
need a separate web-crawling or Search index, which adds unnecessary complexity and does not satisfy the
creating new topics is D. a file upload.
Azure AI Search – Although capable of semantic search, it introduces an external indexing pipeline and topic
creation steps (e.g., defining index schema, mapping fields). This exceeds the minimal, out-of-the-box solution
Conclusion – The only option that directly satisfies the requirement of adding a knowledge source without
Add a knowledge source to Copilot in Dynamics365 –https://learn.microsoft.com/en
us/dynamics365/customer-engagement/copilot/knowledge-source
Upload and manage files as knowledge sources –https://learn.microsoft.com/en-us/dynamics365/customer
engagement/copilot/upload-files
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
Correct Answer:
B. Microsoft Power Platform connectors
Explanation:
Correct choice –Microsoft Power Platform connectors
Power Platform connectors provide a standardized, bi-directional integration layer that enables Azure-hosted
logic (e.g., Azure Functions, Azure Logic Apps, Azure API Management) to be exposed as a connector. This
allows Microsoft365Copilot to call external services directly, leveraging the connector’s authentication,
schema mapping, and invocation capabilities. The integration is managed through the Power Platform
connector catalog, supports custom OpenAPI definitions, and can be securely shared across tenant
boundaries, making it the recommended mechanism for exposing Azure services to Copilot.
Why optionA (Microsoft Copilot Studio skills) is less suitable
Copilot Studio skills are primarily used for building conversational agents within Copilot Studio and are not
designed to expose arbitrary Azure APIs to Microsoft365Copilot. Skills operate within the confines of the
Consequently, they cannot serve as a robust integration point for external Azure logic.
Why optionC (custom engine agents) is less suitable
compliance risks.
References
studio environment and lack the necessary connector infrastructure for secure, governed, cross-service calls.
Custom engine agents refer to bespoke AI engine implementations that run outside the Microsoft 365
ecosystem. They do not provide a native, supported bridge to Microsoft365Copilot and generally require
custom middleware that must be manually provisioned, monitored, and maintained. This approach bypasses
the standardized connector model, resulting in higher operational overhead, limited governance, and potential
Power Platform connectors documentation: https://learn.microsoft.com/en-us/power-platform/connectors/
Extend Copilot with custom connectors: https://learn.microsoft.com/en-us/copilot-extensibility/connectors/
HOTSPOT -
You need to design a shared prompt library that will be used across multiple business units. The solution must
meet the following requirements:
Ensure consistent Al responses with reusable formats.
Support governance and version control.
Minimize administrative effort.
Minimize ongoing costs.
What should you recommend for each requirement? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
A
Correct Answer:
A.
Explanation:
Define standardized prompt templates.
Prompt templates ensure that AI models receive structured and consistent instructions.
Benefits include:
Consistent responses across teams
Reduced prompt variability
Easier maintenance and updates
Better response quality
Support governance and version control
Store prompts in a Git repository.
Version control
Change tracking
A Git repository supports governance by enabling:
Collaboration
Rollback to previous versions
Auditability
DRAG DROP -
A company has a Microsoft Foundry project that uses a single agent and a single prompt to complete a series of
tasks.
The agent encounters the following issues:
It frequently produces incomplete results.
It struggles with domain-specific reasoning.
Agent response times are remarkably slow.
You need to recommend a solution to improve the overall performance and accuracy of the agent.
What should you include in the recommendation? To answer, drag the appropriate actions to the correct
requirements. Each action 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.
A
Correct Answer:
A.
Explanation:
Move to a multi-agent architecture.
What performance means in AI systems
Performance refers to:
Speed of responses
Ability to handle complex workflows
Scalability for large workloads
Why a multi-agent architecture improves performance
A multi-agent architecture splits responsibilities across multiple specialized AI agents.
Add a grounding data source.
Grounding connects the AI model to reliable external data sources.
Instead of relying only on the model’s training data, the AI can reference:
Company documents
A financial services company uses Microsoft Dynamics 365 Finance.
Currently, the company's support staff manually reviews customer transaction histories to detect potential fraud
cases before escalating the cases.
You need to recommend an automation solution for the review process. The solution must ensure that escalations
reach a human analyst for final decision making. What should you recommend?
A
Deploy an autonomous agent that closes non-fraud cases automatically.
B
Use Microsoft 365 Copilot in Word to automatically finalize fraud detection policies.
C
Configure a task agent to generate fraud risk scores for the human analyst to review.
D
Export the data to a data lake for analysis in Microsoft Power BI.
Correct Answer:
C. Configure a task agent to generate fraud risk scores for the human analyst to review.
Explanation:
Why optionC is the best choice
Task agents in Dynamics365Finance can ingest transaction data, apply fraud-detection models, and output a
risk score.
The generated score is presented to the human analyst for final review and escalation decision, satisfying the
requirement that “escalations reach a human analyst”.
This approach leverages built-in business process automation (e.g., PowerAutomate/Flow) to pre-filter
records, reducing manual effort while keeping a human in the decision loop.
traceability.
Why the other options are unsuitable
decision.
It integrates natively with Dynamics365Finance security roles and audit trails, ensuring compliance and
enforce human-in-the-loop escalation.
A. Deploy an autonomous agent that closes non-fraud cases automatically – This removes the human
analyst from the escalation path, violating the explicit requirement that a human must perform the final
B. Use Microsoft365Copilot in Word to automatically finalize fraud detection policies – Copilot is a
productivity assistant, not a workflow automation tool for risk scoring; it does not connect to Finance data or
D. Export the data to a data lake for analysis in Microsoft PowerBI – Moving data to PowerBI creates a
reporting layer but does not provide an automated escalation mechanism or guarantee that analysts receive
the information in a timely, decision-oriented format within the Finance environment.
References
Task agents and AI-driven business process automation in Dynamics365 Finance:
https://learn.microsoft.com/en-us/dynamics365/finance/audit-management/automated-risk-scoring
Human-in-the-loop escalation patterns with PowerAutomate: https://learn.microsoft.com/en-us/power
automate/automated-flows-human-in-the-loop
A company plans to deploy a Microsoft Copilot Studio agent that will analyze historical business data to predict
customer behavior.
The data is currently stored in an Azure SQL database, flat files, APIs, and logs.
You need to organize the data into a format that can be used as a knowledge source in Copilot Studio.
What should you include in the solution?
A
Azure AI Search
B
Azure Data Lake Storage
C
Azure Cosmos DB
D
Azure Translator in Foundry Tools
Correct Answer:
A. Azure AI Search
Explanation:
Azure AI Search is purpose-built for ingestion, indexing, and semantic search over heterogeneous data
sources—including structured relational tables, files, APIs, and logs—making it the ideal knowledge-store
layer for a Copilot Studio agent that must retrieve contextual business data in real time. Its built-in support
for relational connections, vector indexing, and AI-enhanced query pipelines enables low-latency retrieval of
historical business data needed for predictive modelling.
agent.
References
Azure Data Lake Storage offers massive, retained raw storage but lacks native indexing, full-text search, or query
optimization needed for efficient knowledge-source retrieval; it would require additional services (e.g., Synapse,
Event-Based Ingest) to make the data searchable.
Azure Cosmos DB provides globally replicated NoSQL data with low-latency reads, yet it is optimized for
transactional workloads rather than comprehensive document-level search and analytics; without integrated
search capabilities it would not satisfy the requirement for a unified knowledge source.
Azure Translator in Foundry Tools is focused on language translation and offers no data storage, indexing, or
retrieval features; therefore it cannot serve as a knowledge-source repository.
Conclusion – Azure AI Search directly addresses the need for scalable, indexed, and semantically searchable data
across multiple storage formats, aligning perfectly with the knowledge-source requirements of a Copilot Studio
Azure AI Search documentation: https://learn.microsoft.com/en-us/azure/search/
Copilot Studio knowledge-source integration guide: https://learn.microsoft.com/en-us/copilot
studio/knowledge-sources/
Questions: 1-10 out of 112
Continue Full Practice..
GET ALL 112 QUESTIONS