Even when training data is already consistent and uniform, the first step in building a custom Azure Machine Learning model is still to prepare the training data. “Consistent” data reduces the amount of cleaning you may need, but preparation is broader than cleaning: you still must confirm the schema, validate data types, handle missing values (if any), ensure label quality (for supervised learning), select/engineer features, and split data into training/validation/test sets. Those actions determine whether training will be stable and whether evaluation metrics will be meaningful.

If you skip preparation and go directly to training (C), the model might learn from the wrong columns, inconsistent labels, or poorly partitioned data, producing misleading results. Evaluation (B) comes after training because you need a trained model to score and measure. Hyperparameter tuning (D) is an optimization activity that presupposes you already have a working training pipeline and a baseline model to improve. Deployment (E) is last, after you have validated performance and selected the model candidate.

Azure Machine Learning commonly operationalizes these steps through pipelines, where data preparation is a foundational stage that precedes training and evaluation (and can also be iterated as you refine features and quality).

Construction blueprints in PDFs often contain a mix of text, symbols, linework, and diagrams . The requirements include understanding both visual layout (where systems are located) and textual annotations , producing summaries, and answering Q & A. That combination requires a multimodal generative AI approach—models that can reason over images and text together. Therefore, A is best.

OCR alone (B) can extract printed text, but it won’t reliably interpret diagram geometry, symbols, or spatial relationships (e.g., “electrical riser is on the east core near gridline B-4”). Text completion (C) is too generic and doesn’t address image understanding. Document summarization (D) is only one requirement (summary) and still depends on first extracting/understanding both visual and textual elements.

A multimodal solution can ingest the PDF pages as images (or rendered page images) plus extracted text, then answer questions grounded in both modalities. In practice, you may combine OCR and layout extraction with a multimodal LLM so the model can reference drawing regions, legends, callouts, and system diagrams to produce accurate explanations and field extractions.

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.

Preventing generative AI from accessing confidential or classified information is primarily a data access and classification control problem. The most effective broad solution is data governance (B) —the framework of policies and controls that ensures sensitive content is identified, classified, protected, and access is restricted using least privilege. Data governance includes information classification/sensitivity labels, access control reviews, secure sharing practices, data loss prevention (DLP), and auditing—controls that directly limit what data is available to the AI through permission trimming and policy enforcement.

An information barrier (A) policy is more specific: it’s intended to prevent communication and collaboration between defined user groups (often for regulatory/ethical walls). It does not comprehensively address document classification or restrict AI access to sensitive files across the tenant. A data retention policy (C) governs how long content is kept and when it’s deleted; it’s not a primary access-prevention mechanism. Communication monitoring (D) is a detection/oversight control; it can help identify risky activity, but it does not itself prevent access to confidential content by the AI.

Therefore, to prevent AI from surfacing confidential/classified data during summarization and analysis, you should recommend data governance as the primary control layer.

crafting clear instructions to guide generative AI solutions in generating context-appropriate content.

Prompt engineering is fundamentally about how you communicate intent to a generative AI model so it produces outputs that meet business expectations. The best completion is “crafting clear instructions to guide generative AI solutions in generating context-appropriate content” because it captures the practical, day-to-day discipline: shaping the input (prompt) with the right task framing, constraints, context, and output format.

In real deployments, prompt engineering includes specifying the role and objective (for example, “act as a customer support agent”), providing the necessary context (product details, policy excerpts, audience), adding explicit requirements (tone, length, must/must-not statements), and defining structured output (JSON fields, bullet sections, headings). It can also include adding examples (few-shot prompting), clarifying what to do when information is missing, and instructing the model to cite only provided sources or to ask follow-up questions. These techniques reduce ambiguity, improve consistency, and lower the risk of hallucinations or off-brand responses.

The other options are not accurate definitions. “Integrating AI-powered tools into business workflows” describes solution adoption/integration, not prompt engineering. “Identifying and fixing errors in AI-generated content” is review/editing or quality assurance. “Designing, developing, and training generative AI models” is model development/ML engineering. Prompt engineering operates without changing model weights ; it’s about steering model behavior through well-constructed instructions and context.

The correct selections are Yes, No, Yes. Prompt engineering is the practice of designing clear and effective inputs that guide a generative AI model toward relevant, accurate, and useful output. Guidelines, constraints, role instructions, tone requirements, and output-format rules are all common prompt-engineering techniques, so statement A is true. Statement B is false because examples are normally considered examples or few-shot demonstrations, not the instruction itself. The instruction tells the model what task to perform, while examples demonstrate the preferred pattern or output style. Statement C is true because context supplies the background information, source material, business scenario, audience, or constraints the model should use when generating the answer. Strong prompts usually combine instruction, context, constraints, and examples.

Answer Area

Larger datasets can increase the cost of a generative AI solution that uses an Azure Machine Learning workspace. Answer: Yes

The cost of consuming Azure OpenAI models is primarily identified by the number of input and output tokens processed. Answer: Yes

The cost of custom generative AI solutions always remains the same regardless of the model version or capability used. Answer: No

Yes — In Azure Machine Learning, cost is driven by the resources you consume to store, process, and train. Larger datasets typically require more storage, more data transfer, and more compute time for preprocessing, training, evaluation, and experimentation. Even if you are not training foundation models, handling larger corpora can increase pipeline duration and the number/size of compute instances used, which increases overall cost.

Yes — For Azure OpenAI usage under Standard (on-demand), pricing is primarily tied to token-based consumption (input tokens + output tokens). The more context you send and the longer the generated responses, the more tokens you consume, and the higher the cost. This is why prompt optimization, response length controls, and grounding strategies matter for cost management.

No — Costs vary with model choice and capability. Different model families and versions have different price points, and larger/more capable models generally cost more per token or per unit of throughput. Additionally, architecture choices (RAG, vector search, caching), usage patterns, and throughput requirements can significantly change total cost—so it is never “always the same.”

Responsible AI is fundamentally about earning and maintaining trust while scaling AI across the enterprise. Option C is the best answer because responsible AI practices (fairness, reliability and safety, privacy and security, transparency, accountability, and inclusiveness) reduce reputational, legal, and operational risk and make adoption sustainable over time. When stakeholders trust that AI is governed, tested, and monitored, the organization can expand AI usage confidently across business units.

The other options are incorrect because they make absolute or counterproductive claims. A is false: responsible AI does not “guarantee” accuracy; it reduces risk and improves assurance, but no model can be guaranteed correct in all contexts. B is the opposite of reality: responsible AI increases the importance of data protection and governance; it does not reduce the need for them. D is also incorrect: responsible AI requires clear ownership and oversight, especially from leadership, because accountability is a core principle. In short, responsible AI matters because it builds stakeholder confidence and provides guardrails that support long-term, scalable, and compliant AI adoption—exactly what executives care about when investing in an AI portfolio.

Answer Area

A generative AI model guarantees factually accurate responses if the model is trained on a large dataset. Answer: No

Content filtering and responsible AI safeguards help a generative AI model generate safe and inoffensive content. Answer: Yes

A generative AI model always produces fair and unbiased results when the training data has been properly prepared and reviewed for fairness. Answer: No

No — A larger training dataset can improve coverage and fluency, but it does not guarantee factual accuracy. Generative models can still hallucinate, mix concepts, or produce plausible-but-incorrect statements because they generate likely text rather than verifying truth. This is why solution designs commonly add grounding/retrieval, validation, and human review for high-stakes outputs.

Yes — Content filtering and Responsible AI controls are specifically used to reduce harmful, unsafe, or policy-violating outputs . In practice, safeguards include input/output filters, safety classifiers, and governance controls that help enforce safety policies and minimize offensive content. These controls don’t make outputs “perfect,” but they materially reduce risk and are a standard part of production AI deployments.

No — Even with careful data preparation and fairness reviews, models can still produce biased outcomes due to residual bias in data, label/measurement issues, deployment context, and shifting real-world distributions. “Always fair and unbiased” is an absolute claim that is not achievable in real systems; fairness is managed through continuous evaluation, monitoring, and mitigations—not assumed as guaranteed.

For a user to access organizational data from a mobile device, the user needs a Microsoft 365 Copilot license. No

To reason over your organizational data by using Microsoft Graph, you need a Microsoft 365 Copilot license. Yes

To use the Analyst agent, you need a Microsoft 365 Copilot license. Yes

Top of Form

Bottom of Form

The key distinction here is between Copilot Chat capabilities available with a standard Microsoft 365 subscription and the full Microsoft 365 Copilot add-on that enables richer, in-context experiences grounded in organizational data.

Mobile access to organizational data does not inherently require a Microsoft 365 Copilot license. Microsoft’s Microsoft 365 Copilot app (and related mobile experiences) can provide Copilot Chat for work/school accounts with a Microsoft 365 license, so simply accessing organizational content on a mobile device is not the same as having the paid Copilot add-on. The statement claims a Copilot license is required just to access org data from mobile, which is too broad—there are mobile Microsoft 365 apps that access org data without the Copilot add-on.

Reasoning over organizational data via Microsoft Graph is a core value proposition of Microsoft 365 Copilot. Microsoft documents explain that Microsoft 365 Copilot connects LLMs to your organization’s content and context through Microsoft Graph and generates responses “anchored” in organizational data. That deeper integration is tied to the Microsoft 365 Copilot experience (an add-on license).

Analyst is a “reasoning agent” within Microsoft 365 Copilot and Microsoft states that users with a Microsoft 365 Copilot license can use Analyst (with defined usage limits). Therefore, the Analyst agent requires the Microsoft 365 Copilot license.