Microsoft AB-100 Exam Questions

The requirements are classic Power Platform ALM requirements:

the custom connector must be deployed consistently across environments

it should be editable only in development

The correct design choice is to add the custom connector to Solution1.

Why B is correct:

Putting the custom connector inside the solution makes it part of the ALM package

It can then be exported and imported consistently across environments

In production, when deployed properly through managed solutions, it is not freely edited there, which supports the requirement that editing happens only in development

Why the other options are not correct:

A . Share the custom connector controls access, not ALM packaging and deployment consistency

C . Create the custom connector in the default solution is not the recommended ALM approach for controlled deployment

D . Add the custom connector to GitHub may help source control, but by itself it does not satisfy Power Platform deployment packaging across environments

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.'

Comprehensive and Detailed Explanation From Agentic AI Business Solutions Topics:

The correct answer is D. Centralize the product catalog data in Microsoft Dataverse and expose the data to both agents.

This scenario is about creating a consistent, reusable, governed product data source for multiple AI systems across:

Dynamics 365 Commerce

a Power Apps inventory management solution

multiple Copilot Studio agents

That requirement strongly points to Microsoft Dataverse as the shared business data platform.

Why D is correct

Dataverse is the best fit because it provides:

a centralized business data store

a consistent schema for product catalog records

native integration with Power Platform

strong compatibility with Dynamics 365

governed access and reuse across multiple AI systems

From an AI business solutions perspective, a product catalog is core enterprise reference data. It should not be fragmented across agents or scraped from documents. It should exist as a single source of truth that can serve multiple applications and copilots.

By centralizing the catalog in Dataverse, the company gains:

consistency across apps and agents

easier maintenance

better governance

cleaner analytics and grounding

less duplication and drift

This is exactly the kind of design pattern used for scalable agentic business solutions.

Why the other options are incorrect

A . Let each agent scrape product details from Microsoft SharePoint Online libraries

This is brittle, less structured, and not ideal for maintaining a consistent enterprise product catalog. SharePoint is not the best source of truth for structured operational catalog data.

B . Store the product catalog data in a separate custom table for each agent

This creates duplication, inconsistency, and governance problems. It directly conflicts with the requirement for a consistent source across multiple AI systems.

C . Configure prompts to pull product details from the PDFs of external vendors

PDFs are a weak source for central operational product master data. This would increase inconsistency and reduce reliability.

Expert reasoning

When a question asks for a shared, consistent business data source across:

Copilot Studio

Power Apps

Dynamics 365

the best answer is usually Microsoft Dataverse.

So the correct choice is:

Answe r: D

Comprehensive and Detailed Explanation From Agentic AI Business Solutions Topics:

The correct answer is B. Map the field display names as business terms.

In this scenario, the company is using Microsoft Dynamics 365 Sales with data stored in a Dataverse Lead table, but the table includes non-standard terminology and custom columns. The goal is to help Microsoft Copilot controls understand and summarize lead data efficiently, while also minimizing administrative effort.

This points directly to using the field display names as business terms.

Why this is the best choice:

Microsoft Copilot works best when the business meaning of data is clear and human-readable. In Dataverse, display names are already designed to represent the user-friendly business meaning of a field. They are what users see in the interface, and they typically align better with business language than technical names do.

By mapping field display names as business terms, you achieve two important outcomes:

Copilot can interpret the fields more naturally

Since display names reflect business-friendly terminology, Copilot can generate summaries that make sense in the context of sales operations.

Administrative effort stays low

The display names already exist. Reusing them avoids creating a large amount of extra metadata or manually defining separate business terms for every column.

From an AI-powered business solutions perspective, this is exactly the kind of configuration choice that improves semantic clarity while keeping the solution lightweight and maintainable. In enterprise AI adoption, the best design is often the one that improves model comprehension without adding unnecessary governance overhead.

Why the other options are incorrect:

A . Combine all the fields into one custom field

This is not a good design for Dataverse, Dynamics 365, or Copilot summarization. Combining everything into one field reduces structure, hurts maintainability, makes reporting harder, and weakens Copilot's ability to understand the meaning of specific attributes. Structured data is far more useful than a merged blob of text.

C . Add the schema names as business terms

Schema names are technical identifiers, not business-friendly labels. They are often formatted for developers and administrators rather than end users. Copilot summarization benefits from semantic clarity, and schema names usually do not provide that. They also do not minimize interpretation effort from a business AI perspective.

D . Create new business terms for each field

This might work technically, but it does not minimize administrative effort. The question explicitly asks for a solution that keeps administration low. If display names already represent the business meaning well enough, creating entirely new business terms for every field would be unnecessary overhead.

Expert reasoning:

In Microsoft AI business applications, especially with Dataverse + Dynamics 365 + Copilot, the system performs better when field metadata is aligned to business-readable language. The most efficient way to do that is usually to reuse display names, because they already express the intended meaning of the data and avoid extra manual configuration.

The requirement is to make sure the data ingested by the agent is clean and suitable for the intended use, which is producing monthly sentiment insights to guide product development and marketing.

The best answer is C. Identify and address biased data.

Why C is correct:

For sentiment analysis and reporting, biased data can distort conclusions and produce misleading recommendations

Data preparation should include checking for skew, unfair representation, missing segments, and other quality issues that affect downstream decisions

This aligns with responsible AI and sound analytics practice

Why the other options are not correct:

A . Ensure that the size of the database does not exceed 100 GB is unrelated to data quality or suitability

B . Translate the data into a single language might help in some implementations, but it is not universally required and is not the primary data-quality action here

D . Sort the database by customer last name has no relevance to model readiness or report quality