Microsoft AB-731 Dumps

Enterprise AI adoption succeeds when it is cross-functional from the start . Option A is best practice because AI impacts legal risk, privacy, security, compliance, workforce processes, and business strategy—not just technology. Including leadership ensures alignment to priorities and funding; including business units ensures use cases and success metrics are real; including legal/compliance ensures responsible AI and regulatory obligations are addressed early. This prevents rework and reduces the chance of deploying solutions that are misaligned with policy or unacceptable risk.

Options B and C delay governance and business alignment, which often leads to “build first, govern later” failure modes—solutions that work technically but cannot be approved or scaled due to privacy/security gaps or unclear accountability. Option D over-optimizes for vendor selection without ensuring the organization has defined responsible AI requirements, target use cases, and operating model. Procurement is important, but it is not the primary driver of a successful adoption team. The most sustainable approach is a representative adoption team that integrates business, technical, and governance stakeholders from day one.

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.

The requirement has two key phrases: indexing information and knowledge mining by extracting insights from documents . The Microsoft service purpose-built for this is Azure AI Search (formerly Azure Cognitive Search), which provides a search index over your content and supports “AI enrichment” workflows to extract and structure insights from documents during indexing.

Azure AI Search can ingest content from common enterprise sources (files, blobs, databases), build searchable indexes, and enrich the indexed content using built-in skills or integrated AI capabilities—such as entity recognition, key phrase extraction, language detection, and OCR (depending on the pipeline). This is exactly what “knowledge mining” refers to: turning large volumes of unstructured documents into structured, searchable knowledge that applications and users can query.

The other choices are partial fits: Azure Vision focuses on image/video analysis, not general document indexing. Azure Document Intelligence is excellent for extracting fields/tables from forms and documents, but on its own it does not provide the full indexing/search and knowledge mining layer across a corpus. Microsoft Foundry is an overarching platform for building AI apps/agents; it can incorporate search, but the specific service that directly delivers indexing + knowledge mining is Azure AI Search .

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.

generative

The sentence describes an AI system that creates new, original content (for example, text, images, audio, code) by learning patterns from large datasets. That is the defining characteristic of generative AI , so “generative” is the correct completion.

To clarify the contrasts: predictive AI primarily uses historical data to forecast outcomes or estimate probabilities (for example, predicting next-quarter sales, predicting equipment failure, or classifying whether a transaction is fraudulent). It focuses on what is likely to happen or which category something belongs to , rather than producing novel content. Prescriptive AI goes a step further by recommending actions or decisions (for example, “increase inventory by X,” “route tickets to team Y,” “schedule maintenance next week”) often using optimization and business constraints.

Generative AI, by comparison, is focused on content synthesis . It identifies statistical patterns and relationships in training data and then generates new sequences that resemble the learned distribution while being responsive to prompts. In business use cases, that translates to drafting emails and documents, summarizing reports, generating meeting notes, creating product descriptions, producing marketing copy, and building chat-based assistants. While all three categories can “recognize patterns,” only generative AI is explicitly characterized by the ability to produce new and original content , which is what the question is testing.

Answer Area

A generative AI solution is well-suited to predict next-quarter sales trends. Answer: No

A generative AI solution can summarize lengthy policy documents. Answer: Yes

A generative AI solution can create product descriptions from product specifications. Answer: Yes

No — Predicting next-quarter sales trends is primarily a forecasting/predictive analytics problem. Microsoft differentiates predictive AI (forecasting outcomes from historical patterns) from generative AI (creating content like text, images, or code). While you can use LLMs to assist analysts (explain trends, draft narratives), the core forecasting model is typically traditional ML/time-series methods rather than generative AI as the main engine.

Yes — Summarization is a classic, high-value generative AI capability. Given a long policy, an LLM can compress it into executive summaries, key obligations, risks, and action items, often with formatting constraints (bullets, sections, “do/don’t” lists). Microsoft highlights summarization and analysis as common generative AI use cases in business contexts.

Yes — Generative AI is well-suited to transform structured inputs (features/specs) into natural-language outputs (product descriptions). This is straightforward “content generation,” where you control tone, length, and required fields (benefits, differentiators, disclaimers). Microsoft also points to generating product descriptions and similar marketing/customer-facing text as a practical generative AI scenario.

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 .

Answer Area

Prompt engineering changes how a generative AI model was trained. Answer: No

Prompt engineering focuses on designing clear, concise, and context-rich instructions. Answer: Yes

Effective prompt engineering involves maximizing the number of tokens used in each request. Answer: No

No — Prompt engineering does not modify model weights or retrain the model. It is an inference-time technique : you steer outputs by improving the instructions and context you send to the model. Changing how a model was trained would involve pretraining, fine-tuning, or other training methods—separate from prompt engineering.

Yes — The primary goal of prompt engineering is to reduce ambiguity and variability by providing clear instructions , the right context , and explicit output constraints . This often includes specifying role and task, providing necessary facts or grounding text, defining format (bullets, JSON, headings), and adding examples (few-shot) when helpful. Well-constructed prompts improve consistency, relevance, and usefulness of outputs.

No — Good prompt engineering does not mean “use as many tokens as possible.” In fact, using unnecessary tokens can increase cost and may degrade quality by adding noise. Effective prompts are typically as short as possible but as long as necessary : enough context to achieve accuracy and alignment, but not bloated. Token discipline matters because most pricing is token-based and long contexts can dilute attention over what’s most important.

For a proof of concept , the key requirements are low commitment , quick start , and the ability to scale up or down as you learn what real usage looks like. Azure OpenAI Standard On-Demand pricing is designed for exactly that: you pay per token consumed (input and output) on a pay-as-you-go basis, which makes it ideal when demand is uncertain or variable—typical in early pilots and PoCs.

By contrast, Provisioned (PTUs) is best when you have well-defined, predictable throughput and latency requirements —usually a more mature, production workload. PTUs involve reserving model processing capacity to achieve consistent performance and more predictable costs, which is usually premature for a PoC where actual traffic patterns are not yet known.

Batch API is optimized for asynchronous high-volume jobs with a target turnaround (for example, up to 24 hours) and discounted pricing. That’s great for offline processing, but it does not match an interactive “agent” PoC that typically needs near-real-time responses and iterative testing.

Microsoft 365 Copilot is a separate SaaS licensing model and is not the Azure OpenAI pricing model for building your own agent solution.

An AI champions program includes users who advocate for AI by learning, sharing, and identifying use cases. Champions are not primarily the infrastructure team, analytics team, or executive strategy group. Their value is adoption enablement. They help colleagues understand AI tools, share practical usage patterns, collect feedback, and discover department-specific opportunities where AI can improve productivity or decision-making. Strategy and governance are usually handled by leadership, AI councils, legal, risk, compliance, security, and technical stakeholders. Infrastructure is handled by IT and engineering teams. Champions sit closer to end users and help translate the AI strategy into practical daily usage. This makes them critical for scaling proficiency and adoption across the organization.

Azure Machine Learning delivers the most strategic value when an organization needs to build, train, evaluate, and operationalize predictive models that improve decisions at scale. Option A is a classic predictive analytics use case: forecasting demand using historical sales across product categories. This typically involves time-series forecasting, feature engineering (seasonality, promotions, macro signals), model training/validation, deployment, and continuous monitoring—exactly the lifecycle Azure Machine Learning is designed to support (ML pipelines, model management, deployment endpoints, and MLOps). Forecasting demand can materially improve inventory optimization, supply chain planning, and revenue outcomes, which is why it’s strategic.

B (digitizing paper processes) is more aligned to workflow automation and document processing (often Document Intelligence + Power Automate), not primarily Azure ML. C is sentiment analysis, which can be solved with prebuilt language services and doesn’t necessarily require custom ML training unless you need a highly specialized classifier. D (location-based personalization) is commonly rules-based or CRM/marketing automation; it may use AI, but it doesn’t inherently require building a custom ML model—unless you’re doing advanced propensity modeling.

Answer Area

Microsoft Foundry provides a unified platform for developers and data professionals to create custom end-to-end AI solutions. Answer: Yes

Microsoft Foundry provides a unified platform for low-code developers and business users to create custom end-to-end AI solutions. Answer: No

You need a Microsoft 365 Copilot license to access Microsoft Foundry services. Answer: No

Yes — Microsoft Foundry is positioned by Microsoft as a unified AI platform for building, deploying, and scaling AI apps and agents, with enterprise governance in a single environment. Microsoft explicitly describes Foundry as enabling developers (and, in broader descriptions, data professionals/enterprises) to build and operate AI solutions end-to-end, which aligns with the statement.

No — While Foundry can streamline AI development workflows and may include experiences that reduce complexity, the statement specifically targets low-code developers and business users creating custom end-to-end AI solutions. In Microsoft’s ecosystem, that “low-code/business-user” agent/app-building lane is more directly associated with tools like Copilot Studio/Power Platform , whereas Foundry is primarily presented as the platform for developers and technical teams building and governing AI solutions. Therefore, as written, the statement is not the best characterization.

No — Access to Microsoft Foundry services is not gated by a Microsoft 365 Copilot license. Foundry is part of the Azure AI platform experience (formerly Azure AI Studio) and is accessed through Azure, using Azure subscription-based service consumption. Microsoft 365 Copilot licensing is for Microsoft 365 Copilot experiences, not a prerequisite to use Foundry services.

The correct selections are Yes, Yes, Yes. Lack of trust is a common AI adoption barrier because users and leaders may worry about security, privacy, hallucinations, inaccurate outputs, and unclear accountability. If people do not trust the system, they will avoid using it or over-escalate decisions outside the intended workflow. AI adoption also fails when organizations overlook high-quality data. Poor, outdated, incomplete, or poorly governed data weakens grounding, reduces output quality, and damages user confidence. Finally, adoption is strongest when business and compliance stakeholders are involved early. Business stakeholders ensure the solution solves real problems and delivers measurable value, while compliance, legal, risk, and privacy teams ensure the solution aligns with policy and regulatory obligations.

When a non-reasoning generative AI model produces inconsistent outputs, the most reliable improvement is to make the prompt more specific, constrained, and demonstrative of what “good” looks like.

A is correct because adding high-quality examples is a form of few-shot prompting. Examples act like “training wheels” at inference time: they show the model the desired structure, tone, level of detail, formatting rules, and boundaries. This reduces ambiguity and variance, especially for tasks like marketing copy, summaries, policy text, or customer replies. The more your examples resemble real target outputs (including edge cases), the more consistent the model’s completions become.

B is correct because adding context, relevant source material, and explicit expectations narrows the model’s degrees of freedom. Including the intended audience, purpose, constraints (length, voice, banned claims), and trusted reference content (approved facts, product specs, policy excerpts) helps the model stay aligned and reduces hallucinations and off-brand language. This is also where you specify acceptance criteria such as “must include 3 bullet points,” “use UK English,” or “cite only provided text.”

C is not best: technical jargon can confuse or bias output if it’s not aligned to the task; clarity beats jargon. D is not best: a single concise requirement is usually under-specified and often increases variability.

The correct answer is A. transparency. Transparency means users and stakeholders should understand when AI is being used, what the AI system can do, what its limitations are, and how important outputs or decisions were produced. In this scenario, applicants can request an explanation for why a loan application was denied. That explanation capability makes the AI-assisted decision more understandable and reviewable, which directly supports transparency. Fairness is related to avoiding unjust bias or discriminatory outcomes. Privacy and security focus on protecting personal and organizational data. Inclusiveness focuses on ensuring AI systems work for people with different abilities, backgrounds, and experiences. Because the scenario is specifically about explaining a decision, the best answer is transparency.

Answer Area

Retrieval Augmented Generation RAG requires model fine-tuning. Answer: No

Retrieval Augmented Generation RAG is helpful when you need a generative AI solution that can access current, verifiable information. Answer: Yes

Retrieval Augmented Generation RAG enables you to get more relevant responses based on your organization’s documents without retraining the base model. Answer: Yes

RAG is an architecture pattern that improves generative AI responses by retrieving relevant information from external knowledge sources (for example, a document index, database, or knowledge base) and injecting that information into the model’s prompt/context at runtime.

No — RAG does not inherently require fine-tuning. Fine-tuning changes the model weights. RAG, instead, keeps the base model as-is and augments it with retrieved context. Fine-tuning can be complementary (for style, domain tone, or specialized tasks), but it is not required for RAG to work.

Yes — RAG is especially valuable when you need current and verifiable information because the retrieval layer can pull the latest approved content (updated policies, product specs, incident runbooks) and provide it to the model. This reduces hallucinations and makes answers traceable to known sources.

Yes — A major benefit of RAG is improved relevance to organizational documents without retraining. Instead of rebuilding the model whenever documents change, you update the underlying content store/index; the model then generates responses grounded in the retrieved passages, producing answers that align with your organization’s latest information and terminology.

Answer Area

To use Microsoft 365 Copilot Chat, you must have a Microsoft 365 Copilot license. Answer: No

Microsoft 365 Copilot Chat provides context-aware assistance in Microsoft 365 apps. Answer: Yes

Microsoft 365 Copilot Chat can only access information in open files and read emails. Answer: No

No — Microsoft documents and pricing guidance indicate that Copilot Chat is available for eligible Microsoft Entra ID users with a qualifying Microsoft 365 subscription , and that capabilities can vary depending on whether users also have the Microsoft 365 Copilot add-on . In other words, Copilot Chat isn’t universally “Copilot-license required” in all cases; the add-on impacts which premium work features are enabled, but the baseline chat experience can be available without assigning the add-on to every user.

Yes — Microsoft describes Copilot Chat as a side-by-side experience in select Microsoft 365 apps (for example Word, Excel, PowerPoint, OneNote, Outlook) that is aware of the user’s open content , enabling context-aware help such as summarizing, drafting, and Q & A based on what the user is working on.

No — The word only makes this statement inaccurate. Copilot Chat can be grounded in more than just open files and emails (for example, it can also be grounded in the web, and—depending on licensing and configuration—can use agents/connectors for broader scoped tasks). So limiting it strictly to “open files and read emails” is too restrictive compared to how Microsoft positions the feature set.

For scanned invoices, the requirement is structured field extraction (invoice number/ID, vendor, totals) from document images or PDFs at scale. The best fit is Azure Document Intelligence because it is purpose-built for document processing and provides prebuilt invoice models that combine OCR with layout/structure understanding to extract common invoice fields into a structured output. Microsoft’s invoice model is explicitly designed to analyze invoices (including scanned images) and return key fields and line items in structured form, which directly maps to this scenario.

Azure Vision (B) can perform OCR and basic image analysis, but OCR alone typically returns text without robust invoice-specific field interpretation (e.g., reliably identifying “Invoice ID” vs. “Order ID,” totals vs. subtotals, vendor vs. ship-to). Document Intelligence is optimized for advanced document structure extraction and is therefore the “best” single recommendation.

Azure AI Search (C) focuses on indexing and retrieval/knowledge mining across a corpus; it’s not the primary service for extracting invoice fields for downstream processing. Azure Machine Learning (D) could be used to build a custom model, but that adds cost and time compared with a prebuilt invoice extractor designed for this document type.

Generative AI’s defining capability is producing new content (text, images, code) in response to instructions—most commonly provided as natural language prompts. Option A best captures that general-purpose description for stakeholders: users ask questions or provide instructions, and the system generates responses or drafts content accordingly.

B is a specific application (translation) that generative AI can do, but it’s not the defining description. C describes predictive analytics/forecasting, which is a different AI category. D describes recommendation systems, typically driven by user behavior and ranking algorithms, which can be enhanced by AI but is not the core definition of generative AI.

Microsoft Foundry is positioned as a unified, enterprise-grade platform that helps organizations build, deploy, scale, and govern AI apps and agents—especially generative AI solutions that need to work with business context and internal data. That directly aligns with A : Foundry provides a scalable platform for developing and deploying generative AI solutions. Microsoft describes Foundry as an interoperable platform that makes it easier to build, deploy, and scale AI apps and agents, while also providing centralized security and governance features for organizations.

B is incorrect because Foundry does not remove model choice/configuration; in fact, it supports selecting among models and using tools/frameworks to build solutions. You still choose appropriate model(s), configure endpoints, and design grounding and safety controls.

C and D are not the best characterization of Foundry’s primary benefit. While Foundry offers “friendly interfaces,” Microsoft primarily positions it for developers, model builders, and enterprise AI operations —not as a low-code platform for business users (that role is more commonly filled by Copilot Studio/Power Platform).

The core business concern in the scenario is data leakage —employees using consumer tools where corporate data could be pasted, stored, or processed outside the organization’s governance boundary. The key differentiator of Microsoft 365 Copilot is that it’s designed to work inside your Microsoft 365 tenant and to respect the organization’s existing security, compliance, identity, and data access controls. Therefore, D is the best answer: Copilot accesses internal work data (Microsoft Graph-connected content such as mail, files, chats, meetings) in accordance with existing Microsoft 365 policies and permissions —meaning it can only surface content the user is already allowed to access, and it operates under enterprise-grade controls (authentication, auditing, compliance boundaries, and admin governance).

Options B and C describe general generative AI capabilities that personal ChatGPT can also provide (brainstorming, drafting, rewriting). A can be done in multiple tools as well, and it is not the primary “enterprise value” difference tied to the stated risk. The scenario’s driver is governance: reducing the likelihood of proprietary data leaving controlled systems while still enabling productivity. Rolling out Copilot addresses that by providing “work-safe” AI anchored to organizational content and managed through the same tenant controls your company already uses.

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.

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).

This scenario is a clear violation of the fairness principle. Fairness in Microsoft’s Responsible AI framework is about ensuring AI systems do not create unjustified bias or discriminatory outcomes—especially when decisions affect people’s access to opportunities such as credit, employment, housing, or education. A rule or learned behavior that rejects all applicants over a certain age creates a systematic, categorical disadvantage for a protected demographic group and indicates a discriminatory decision boundary rather than an individualized assessment of creditworthiness.

Even if the model designers believed age correlates with risk, using a hard cutoff that rejects every applicant older than 60 is not an equitable approach. It suggests the model is either using age directly as a dominant feature or reflects biased training data/labels that encoded discriminatory outcomes. Fairness requires you to evaluate model outcomes across groups (for example, age brackets), measure disparate impact, and apply mitigations such as feature review (removing or constraining sensitive attributes), rebalancing training data, adjusting thresholds, or using fairness-aware training/evaluation methods. It also requires governance and review of high-stakes automated decisions.

The other principles are not the best match: transparency concerns explainability and user understanding, accountability concerns human oversight and ownership, and reliability and safety concerns consistent and safe operation. The core issue here is discriminatory treatment across an age group— fairness .

Answer Area

Microsoft Copilot in Outlook can automatically send follow-up replies to emails. Answer: No

Microsoft Copilot in Outlook can identify and surface tasks mentioned in your emails. Answer: Yes

Microsoft Copilot in Outlook can summarize long email threads and highlight action items and deadlines. Answer: Yes

1) No — Copilot in Outlook can draft email responses and help you take actions, but sending messages is not positioned as an automatic “follow-up reply” behavior. Microsoft describes capabilities such as “Draft with Copilot” (generating email drafts from prompts) and Copilot chat actions that update the mailbox, which implies user-directed execution rather than autonomous follow-up sending.

2) Yes — Copilot supports contextual help over your inbox and can help you “catch up” and understand what’s due, which includes surfacing action-oriented items from recent communications. This aligns with using Copilot to pull together summaries of email messages and identify what requires attention.

3) Yes — Microsoft explicitly documents email-thread summarization in Outlook: Copilot scans a conversation and produces a summary of key points. Microsoft also describes Copilot’s summarization capability as extracting key points from threads, which is commonly used to surface what matters most (including actions to take) when the thread is long.

model inaccuracy

The scenario describes a model producing plausible-sounding content that is factually wrong —a common generative AI failure mode often referred to as a “hallucination.” Since “hallucination” is not offered in the dropdown, the best matching choice is model inaccuracy because the core problem is that the model’s output is incorrect even though it appears confident and coherent.

The other options do not fit the definition of the behavior: data leakage is about sensitive information being exposed (for example, proprietary prompts, secrets, or personal data). Prompt injection is an attack technique where a user tries to override system instructions or cause unsafe actions. Overreliance describes a human/organizational risk —trusting the model too much—rather than the model’s intrinsic behavior of generating incorrect facts. Overreliance can be a consequence of this behavior, but it is not what the behavior itself is called.

In practice, you mitigate this kind of inaccuracy by grounding responses in trusted sources (for example, RAG), constraining prompts with explicit requirements, using verification steps (citations, cross-checking, tool-based validation), and adding human review for high-impact use cases.