Microsoft AB-731 - AI Transformation Leader

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.

The correct answer is D. Retrieval Augmented Generation (RAG). A pretrained LLM does not automatically know frequently updated proprietary content unless that content is supplied to it during use or the model is retrained. RAG solves this by retrieving relevant, current information from internal documents, knowledge bases, or indexed repositories at runtime and adding that information to the model’s prompt context. This keeps responses grounded in the latest approved business content without changing the model weights. Fine-tuning adapts the model but is more expensive and does not automatically keep up with frequently changing knowledge. Content filtering is a safety control, not a freshness mechanism. Prompt engineering improves instructions, but by itself it does not retrieve current proprietary content.

uses reasoning capabilities to generate deep insights based on organizational data and the web.

The sentence is best completed by the option describing Researcher as a research-oriented reasoning agent that combines information from the web and your work data to produce deeper insights. Microsoft describes Researcher as an agent built into Microsoft 365 Copilot to tackle complex, multistep research and to help users gather, analyze, and summarize information from “the web, your work documents, or both,” producing a structured output that supports decision-making. That is exactly what the completion “uses reasoning capabilities to generate deep insights based on organizational data and the web” captures.

The other dropdown options are better matches for different tools/agents: “creates visual dashboards from structured data in Excel and Power BI” is more aligned to BI/reporting workflows; “generates a pivot table and performs time series forecasting” is spreadsheet/analytics functionality; and “performs complex, multi-step, data analysis and code execution tasks over arbitrary datasets” is the hallmark positioning of the Analyst agent (“virtual data scientist”) rather than Researcher. Researcher’s differentiator is deep research across both organizational context and the open web, while Analyst’s differentiator is data analysis and computation.

The correct selections are Yes, No, Yes. Microsoft 365 Copilot helps users create, rewrite, summarize, and analyze content in Microsoft 365 apps such as Outlook, Word, Excel, PowerPoint, and Teams. Therefore, it can help compose professional emails and summarize conversations. It can also summarize recent updates across business content such as documents, spreadsheets, and presentations when the user has access to that content. The second statement is false because Copilot is not generally described as autonomously updating business spreadsheets without user control. It can assist with analysis, formulas, summaries, and suggested changes, but autonomous modification of sales data would require governed user action, permissions, and potentially workflow controls. Copilot is an assistant, not an unrestricted autonomous spreadsheet operator.

The correct answer is data security. The principle of least privilege means users, apps, and services receive only the minimum access required to perform their work. Microsoft 365 Copilot respects existing Microsoft 365 permissions and does not grant users new access to content they are not already authorized to view. That behavior is a security control because it helps prevent unauthorized access to company information. Data classification is about labeling or categorizing information by sensitivity. Data compliance focuses on meeting policy, legal, or regulatory requirements. Data loss prevention helps prevent sensitive information from being shared inappropriately. Least privilege is primarily an access-control practice, so the best category is data security.

In Microsoft Copilot Studio, knowledge sources allow an agent to generate responses from configured content such as websites, files, SharePoint content, Dataverse, or other approved knowledge repositories. This reduces the need to manually create a separate scripted topic for every possible user question. Instead, the agent can use generative answers grounded in the configured knowledge source and respond dynamically based on the user’s request. Changing only the response format is too narrow and does not describe knowledge sources. Summarizing Teams meetings is more aligned with Microsoft 365 Copilot scenarios. Creating one scripted topic for every question is exactly what knowledge sources help avoid.

Answer Area

Microsoft 365 Copilot helps users create and analyze content in Microsoft 365 apps. Answer: Yes

Microsoft Copilot Studio can only be used to customize Microsoft 365 Copilot. Answer: No

Microsoft Security Copilot uses AI to assign sensitivity labels to documents. Answer: No

Yes — Microsoft 365 Copilot is built into Microsoft 365 apps (such as Word, Excel, PowerPoint, Outlook, and Teams) to help users draft, summarize, rewrite, and analyze work content. This includes creating documents and presentations, summarizing emails and meetings, and analyzing information in productivity workflows. That is its primary value proposition, so the statement is true.

No — Copilot Studio is not limited to customizing Microsoft 365 Copilot. It is used to build and manage agents (conversational experiences) and extend Copilot experiences by connecting to data and actions, creating custom topics/behaviors, and integrating business processes. While it can be used to extend Microsoft 365 Copilot (for example, via declarative agents and other extensibility paths), it is broader than “only customizing Microsoft 365 Copilot,” so the statement is false.

No — Assigning sensitivity labels to documents is primarily a Microsoft Purview Information Protection capability (manual labeling, default labeling, auto-labeling) rather than a core function of Microsoft Security Copilot. Security Copilot is focused on security operations (incident investigation, threat hunting, response guidance). Although AI can support security workflows, the specific act of assigning sensitivity labels to documents is not what Security Copilot is designed to do by default, making the statement false.

The correct answer is D. Microsoft Copilot Studio. The requirement is to create an AI assistant for a public customer support portal that can answer customer questions and initiate follow-up actions with minimal development effort. Microsoft Copilot Studio is designed for building custom agents using a low-code approach. It can connect to knowledge sources, provide generative answers, define conversation behavior, and trigger actions through connectors or workflows. Microsoft 365 Copilot Chat is intended for workplace productivity and organizational users, not public customer support portals. Microsoft Security Copilot is for security operations and incident investigation. Microsoft 365 Copilot connectors only make external data available to Copilot experiences; they do not by themselves create a public-facing customer support assistant.

Answer Area

Protect personal information and apply strong safeguards to keep data secure. Answer: Privacy and security

Make AI solutions understandable by explaining how and why decisions are made. Answer: Transparency

Design AI solutions that are accessible to people of all abilities and experiences. Answer: Inclusiveness

Involve human oversight in the control of AI solutions. Answer: Accountability

Microsoft’s Responsible AI principles provide a practical framework for building and deploying trustworthy AI systems.

Privacy and security is the principle focused on protecting personal information and ensuring strong safeguards—such as least privilege access, encryption, DLP controls, secure storage, and auditing—so data remains protected throughout collection, processing, and usage.

Transparency is about making AI systems understandable. This includes communicating when AI is being used, explaining system capabilities and limitations, and providing clarity on how outputs are produced (for example, what data sources are used, what assumptions apply, and why certain recommendations are generated). Transparency reduces confusion and helps users calibrate trust appropriately.

Inclusiveness ensures AI solutions are designed to benefit people of diverse abilities, backgrounds, and experiences. Practically, this includes accessibility (assistive technologies, readable outputs), inclusive UX design, and testing across diverse user groups so the solution does not exclude or disadvantage certain populations.

Accountability emphasizes that humans and organizations remain responsible for AI outcomes. Involving human oversight is a direct expression of accountability: setting governance, defining who owns decisions, establishing escalation paths, and ensuring there are controls for review, intervention, and correction when AI outputs are unsafe or incorrect.