Free Microsoft AB-731 Practice Exam with Questions & Answers | Set: 2

Answer Area

Using incomplete or poor-quality data during generative AI model training can increase costs. Answer: Yes

AI models rely on training data to learn patterns and identify relationships to produce outputs. Answer: Yes

Generative AI models trained on non-representative datasets can produce inaccurate or unbalanced results. Answer: Yes

Yes — Poor-quality or incomplete training data increases cost because it drives more iterations: additional data cleaning, relabeling, re-training, and re-evaluation to reach acceptable performance. It can also increase operational costs after deployment if the model produces low-quality outputs that require human rework, escalations, or incident handling. In practice, data quality debt becomes model cost debt.

Yes — Training data is the primary mechanism by which AI models learn statistical patterns and relationships. For generative models, the training corpus shapes language fluency, factual associations, style tendencies, and the kinds of content the model can produce. Without sufficient and appropriate training signals, outputs degrade.

Yes — If the training dataset is not representative of the real-world population or business context, the model can systematically underperform for certain groups, topics, or edge cases. This can manifest as biased language, missing perspectives, and uneven accuracy, producing “unbalanced” results. That is why Responsible AI practice emphasizes representative data, evaluation across slices, and continuous monitoring.

Answer Area

Retrieval Augmented Generation (RAG) architectures require that a large language model (LLM) be retrained on proprietary data. Answer: No

Retrieval-Augmented Generation (RAG) grounds a language model to produce more factual and context-relevant responses. Answer: Yes

Retrieval Augmented Generation (RAG) retrieves information from external knowledge sources at runtime instead of relying solely on the knowledge of a generative AI model. Answer: Yes

1) No — RAG does not require retraining or fine-tuning the base LLM on proprietary data. The defining idea of RAG is to keep the model as-is and instead supply it with relevant context retrieved from trusted sources at inference time. Fine-tuning can be optional for style or specialized behavior, but it is not a requirement for RAG.

2) Yes — RAG is a grounding approach. By retrieving authoritative passages (policies, manuals, product specs, internal knowledge bases) and injecting them into the prompt context, the model’s answer is constrained by evidence that is relevant to the user’s question. This improves factuality and domain relevance and helps reduce hallucinations.

3) Yes — RAG explicitly depends on runtime retrieval from external knowledge sources, such as indexed documents, databases, or enterprise repositories. The retrieval layer finds the best matching content for the query, and the generation layer uses that retrieved content to craft the response. This is why RAG is valuable when information changes frequently: you update the source documents/index rather than retraining the LLM.

Overall, RAG is best understood as an architecture pattern that combines search/retrieval + generation , improving accuracy and freshness without the cost and risk of retraining the underlying model each time the knowledge base changes.

By default, Microsoft 365 Copilot is grounded in your organization’s Microsoft 365 data through Microsoft Graph , and it respects the user’s existing permissions. For “find and summarize information across internal documents,” the most direct default document repositories in Microsoft 365 are SharePoint (team sites and shared libraries) and OneDrive (a user’s work files). That is why C (Microsoft SharePoint) and D (Microsoft OneDrive) are the correct selections. Microsoft explicitly describes Copilot as accessing organizational content via Microsoft Graph, including user documents and related work content.

The other options are not “by default” sources. A (on-premises file share) is not automatically part of Microsoft Graph unless you integrate/migrate content or use connectors to make it discoverable in Microsoft 365 experiences. B (custom CRM) similarly requires an integration approach (for example, Microsoft 365 Copilot connectors / Graph connectors) to index and expose that data for Copilot to use. E (Microsoft Sway) is not a primary default content source for Copilot’s document grounding and is not typically referenced as a core internal document repository compared to SharePoint/OneDrive.

So, for immediate, out-of-the-box internal document discovery and summarization within Microsoft 365, SharePoint + OneDrive are the default answer.

Answer Area

Allowing AI models to make autonomous decisions supports the Microsoft responsible AI principle of accountability. Answer: No

Regularly testing AI models for fairness and inclusiveness helps ensure they align with Microsoft’s Responsible AI principles. Answer: Yes

Protecting user data and limiting access to personal information supports the Microsoft responsible AI principles of privacy and security. Answer: Yes

Microsoft’s Responsible AI principles emphasize that people and organizations must remain accountable for AI systems and their outcomes. Accountability is strengthened by governance, human oversight, clear ownership, auditability, and processes to review and address issues—not by letting models make unchecked autonomous decisions. Therefore, statement 1 is No : increasing autonomy can actually increase risk unless paired with human-in-the-loop controls and clear escalation paths, because accountability requires clear responsibility for decisions and impacts.

Statement 2 is Yes because fairness and inclusiveness are explicitly supported through ongoing evaluation. Regular testing helps detect disparate impact, performance gaps across user groups, and unintended bias introduced by data drift or changes in usage patterns. It’s not a one-time activity; it’s continuous assurance that the system behaves appropriately as conditions change.

Statement 3 is Yes because privacy and security are directly supported by protecting personal/sensitive data, enforcing least privilege access, and implementing controls such as data loss prevention, encryption, access logging, and strong identity governance. Limiting access to personal information reduces exposure and supports compliance obligations while aligning with privacy-by-design and secure-by-design expectations for AI-enabled solutions.

create a Microsoft Word document.

Microsoft 365 Copilot is a productivity-focused AI capability embedded across Microsoft 365 apps such as Word, Excel, PowerPoint, Outlook, and Teams. A core, common use case is drafting and generating documents in Word from prompts and existing context. Therefore, “create a Microsoft Word document” is the best completion.

The other options are not appropriate for Microsoft 365 Copilot’s scope. “Monitor network traffic and alerts in real time” is a security/operations function more aligned to security monitoring tools and, in Microsoft’s product set, closer to Microsoft Security Copilot or dedicated SIEM/SOAR platforms (for example, Microsoft Sentinel). “Modify administrative permissions for SharePoint files” is an admin/governance action that is intentionally protected by role-based access control and is not something end-user Copilot features are meant to perform as a default capability. “Create a list in Microsoft SharePoint” is closer, because Copilot can assist in generating content and can work within Microsoft 365 collaboration contexts; however, the most universally accurate and directly supported capability among the options is creating/drafting a Word document, which is a primary Copilot scenario in Word.

In short, Microsoft 365 Copilot is designed to help users create, summarize, rewrite, and transform content within Microsoft 365 apps, and document creation in Word is a canonical example of that value.

A pretrained generative AI model is trained initially on a large, broad, and diverse dataset so it learns general language (or multimodal) patterns and capabilities. Fine-tuning then takes that pretrained base and performs additional training on a smaller, task- or domain-specific dataset to specialize behavior—improving performance for a particular use case, tone, style, or domain knowledge representation. That is exactly what option C states, making it the correct answer.

Option A is incorrect because both pretraining and fine-tuning may use labeled or unlabeled data depending on the technique; the distinction is not “labeled vs. unlabeled.” Option B is incorrect because a pretrained model is not “faster to train” due to fewer parameters; pretraining is typically the most compute-intensive phase precisely because it’s done at large scale, while fine-tuning is smaller but still trains the same model architecture. Option D is reversed: the pretrained model is the general-purpose foundation, while the fine-tuned model is the specialized variant for a specific task or dataset.

Grounding is an AI solution pattern used to improve response quality by ensuring the model’s output is based on trusted, relevant information provided at inference time , rather than relying only on what the model “remembers” from training. Therefore, C is correct : grounding anchors responses in specific data sources .

In practical deployments, grounding commonly uses retrieval (often called Retrieval Augmented Generation, or RAG) where the system first finds relevant content from approved sources—such as internal policy documents, product documentation, knowledge bases, or databases—and then includes that content in the prompt context sent to the model. Microsoft’s guidance describes grounding data as information supplied at inference time to help responses become more accurate and relevant because the model is guided by authoritative, up-to-date content that may not have been part of original training.

The other options do not define grounding. A relates to inclusion practices and diversity considerations, which are important for responsible AI but are not what grounding means. B describes transparency/explainability concepts. D relates to model evaluation/communication of limitations. Grounding is specifically about tying outputs to known sources , which reduces hallucinations and improves business trust in the generated responses.

Azure AI Search provides an indexing and retrieval layer that makes large, distributed document collections searchable in a consistent way. The key benefit in an information discovery scenario is that it can index content from many sources and then retrieve relevant documents/passages using rich query capabilities, including natural language-style queries and semantic ranking. That directly aligns with B .

This retrieval capability is foundational for RAG architectures: the system uses Azure AI Search to find the best matching content, then supplies those results to a generative model so the answer is grounded in organizational knowledge. That improves relevance and reduces hallucinations because the model is guided by retrieved evidence.

Option A is the opposite of what you want—Search is used precisely to reference existing data. C is more aligned to workflow automation platforms (Logic Apps/Power Automate) and document processing services. D describes fine-tuning, which is a different approach; Azure AI Search improves discovery and grounding through retrieval, not by changing model weights.

Microsoft Foundry is positioned as a unified platform experience for building, optimizing, and governing AI applications and agents. Microsoft explicitly emphasizes “fleetwide security and governance” and the ability to build and manage AI in a unified environment, which directly supports statement 1 being Yes : it is designed to help organizations build and operate generative AI solutions with centralized governance controls (for example, environment setup, data isolation, access control, and operational management).

For statement 2, Foundry supports scaling as demand increases . Microsoft documentation for Foundry-related model usage notes that as usage grows, Foundry can automatically increase quotas by moving users to higher tiers (and allows requesting additional quota). This is a concrete scalability mechanism tied to increased workload demand, so the statement is Yes .

For statement 3, Foundry is not limited to text-only generative AI. Microsoft provides “Azure Vision in Foundry Tools,” which delivers computer vision capabilities such as analyzing images, reading text (OCR), and other image-processing features. That means Foundry can be used for image recognition/computer vision workloads, so the statement is Yes .

The requirement is specific: users must build and use declarative agents that can access work data (tenant data / organizational context). Microsoft’s licensing guidance for Copilot extensibility ties use of declarative agents to having the appropriate Copilot entitlement that enables tenant grounding and organizational data access. In Microsoft’s cost and licensing considerations for declarative agents, Microsoft states that to use a declarative agent, users must have a Microsoft 365 Copilot add-on license (or an equivalent Copilot Chat add-on path tied to eligible licensing). Therefore, among the provided options, the best recommendation is A.

Option B (Copilot Studio user license) is primarily about authoring/building agents in Copilot Studio, but it is not, by itself, the licensing prerequisite that grants end users the right to use those agents with full Microsoft 365 Copilot capabilities and work-data grounding inside the Microsoft 365 Copilot environment. Publishing/building can be separate from the end-user entitlement to use the agent with organizational context.

Option C (Copilot Chat pay-as-you-go) can enable usage-based access to declarative agents in some configurations, but the question asks for the best license recommendation for users who need work-data access through declarative agents. The Microsoft 365 Copilot add-on is the straightforward, fully supported entitlement for that scenario.