AB-730 Sample Questions Answers

Comprehensive and Detailed 150 to 200 words of Explanation Microsoft AI Business professional documents:

This scenario is an example of overreliance. Microsoft’s AI guidance highlights that Copilot is an assistive tool that can accelerate analysis and drafting, but users remain responsible for validating outputs—especially for high-impact business decisions. Overreliance occurs when someone treats AI output as authoritative and acts on it without applying judgment, cross-checking sources, or validating against current conditions.

Here, the merchandiser uses Copilot to generate stocking recommendations from historical sales data, then places a large order without reviewing the suggestions or incorporating current market trends. Even if the historical data is accurate, demand can shift due to seasonality changes, competitor actions, pricing, supply constraints, macroeconomic factors, or new product launches. Copilot’s recommendations should be treated as a starting point for decision-making, not the final decision.

Option A (verification) is the opposite behavior—checking accuracy before acting. Option C (fabrication) would involve Copilot inventing facts; the prompt doesn’t indicate fictional data, only unvalidated reliance. Option D (prompt injection) involves malicious instructions embedded in content to manipulate the model, which is not described here.

Therefore, the best answer is overreliance.

Microsoft 365 Copilot is designed to be helpful by using work context—for example, the files you have access to, recent activity, meetings, emails, and SharePoint/OneDrive content—to suggest relevant prompts and help you start tasks faster. It also uses this context to augment your prompt before it is sent to the LLM. This is the grounding approach (often described as retrieval-augmented generation): Copilot retrieves relevant organizational content you’re permitted to access and adds it as supporting context so responses are accurate and business-relevant. However, Microsoft 365 Copilot does not use your organization’s contextual data to train the underlying foundation model. That separation is critical for enterprise privacy and compliance: your prompts, responses, and tenant data are used to generate the answer for your session and permissions, but are not used to improve or retrain the base LLM. This approach supports responsible AI, protects confidential business information, and ensures outputs respect access controls.

The instructions will apply to new chat conversations.

Answer: Yes

The instructions will apply to new conversations with the Researcher agent and the Analyst agent.

Answer: Yes

The instructions will apply to previous responses in existing conversation.

Answer: No

Custom instructions in Microsoft 365 Copilot are a persistent preference mechanism that influences how Copilot responds going forward. Once configured, they are applied when you start new interactions, helping Copilot maintain consistent tone, formatting, and behavioral preferences across future chats. Therefore, they apply to new chat conversations (Statement 1 = Yes).

Custom instructions also carry into new conversations you initiate with Copilot experiences and agents (such as Researcher and Analyst), because the instructions act as a user-level guidance layer that shapes responses regardless of which Copilot “mode” you start—provided those agents are being used in the same Copilot environment and are subject to your settings (Statement 2 = Yes).

However, custom instructions do not retroactively change content that was already generated. Existing conversation history and any prior responses remain unchanged; the instructions affect subsequent turns or new threads, not previously produced outputs (Statement 3 = No).

Microsoft 365 Copilot can be accessed via its dedicated web experience for enterprise users. The correct web entry point for Microsoft 365 Copilot is https://m365.cloud.microsoft , which provides authenticated access to Copilot features within the Microsoft 365 environment.

This URL routes users into the Microsoft 365 ecosystem where Copilot integrates with organizational data such as SharePoint, OneDrive, Teams, and Outlook. It ensures that users are authenticated through Microsoft Entra ID and that access controls are enforced according to tenant policies.

Option B refers to Copilot Studio, which is used to build and manage custom copilots and agents rather than access the Microsoft 365 Copilot chat experience. Option C (My Apps) is a general application launcher portal. Option D is an incorrect account management URL and does not provide Copilot access.

Therefore, to access Microsoft 365 Copilot from a web browser, the correct URL is https://m365.cloud.microsoft .

When creating an agent in the Microsoft 365 Copilot app using a template, administrators or authorized users can configure specific behaviors and knowledge sources for the agent. Therefore, it is correct that you can choose which knowledge sources the agent can use. This ensures proper grounding in approved Microsoft 365 data such as SharePoint sites, OneDrive folders, or other organizational repositories. Controlling knowledge sources supports responsible AI principles, including data security, relevance, and compliance.

Agents created within Microsoft 365 are designed primarily for internal organizational use. As a result, sharing the agent with users inside the organization is supported, enabling collaboration and productivity improvements across teams.

However, sharing the agent with external users is not supported by default. External sharing would introduce security and compliance risks, so Microsoft enforces tenant-level boundaries to protect enterprise data.

These capabilities reflect best practices in managing AI prompts and agents securely within enterprise environments.

This scenario is an example of fabrication, which is commonly referred to in generative AI contexts as a hallucination. Fabrication occurs when an AI system generates information that appears credible but is factually incorrect, invented, or unsupported by verifiable sources.

According to Microsoft AI Business Professional guidance, large language models predict text based on patterns learned during training. They do not “know” facts in the human sense. As a result, when asked to generate reports using web-based information, the model may produce plausible-sounding but fictional details if sufficient grounding or reliable sources are not provided.

Deepfake refers specifically to synthetic media such as manipulated images, audio, or video. Overreliance describes a human behavior risk where users trust AI outputs without verification. Prompt injection is a malicious technique designed to manipulate model behavior. Bias refers to systematic unfairness in outputs.

In this case, the presence of fictional information in the generated report directly aligns with fabrication, making option B the correct answer.

Comprehensive and Detailed 150 to 200 words of Explanation Microsoft AI Business professional documents:

Microsoft distinguishes Microsoft 365 Copilot (the full, licensed experience integrated across Microsoft 365 apps and Microsoft Graph) from Microsoft 365 Copilot Chat (the chat-first experience available more broadly). Some advanced capabilities—especially those tied to specialized agents and persistent work organization—are typically associated with the full Copilot license.

The Researcher agent is an advanced capability and is not consistently available in Copilot Chat across tenants because it is treated as a premium agent experience. Copilot Notebooks are also a structured organization feature used to group conversations and share reference materials; this is typically positioned as part of the full Microsoft 365 Copilot experience.

Copilot Pages, however, is the collaborative, editable canvas used to refine, organize, and share Copilot-generated content. Pages is designed to work alongside Copilot Chat so users can move from a chat response into an editable artifact for collaboration and reuse. This makes Pages the feature most commonly available in both the full Microsoft 365 Copilot and Microsoft 365 Copilot Chat experiences.

Therefore, the best answer is Copilot Pages.

Microsoft 365 Copilot includes a memory capability that allows it to retain user-provided preferences or details across interactions when explicitly instructed to remember them. These stored details are referred to as memories and are separate from standard conversation history.

If you previously asked Copilot to remember specific trip-related details, those details are stored as structured memory items. Simply deleting the conversation does not necessarily remove stored memory entries. Likewise, deleting activity history through the My Account portal removes conversation records but does not directly manage structured Copilot memories. Custom instructions define persistent behavioral preferences and are unrelated to trip-specific stored data.

To ensure Copilot no longer retains those trip details, you must delete the stored memories directly within Copilot. Microsoft documentation explains that users can view and manage saved memories and remove them individually to control what Copilot retains.

Therefore, the correct action to ensure Copilot forgets the trip details is to delete the memories.

When you use Microsoft 365 Copilot Chat without a Microsoft 365 Copilot license, Copilot Chat operates in a “general” mode rather than a Microsoft Graph-grounded work mode. In this configuration, Copilot does not have the entitlement to access and reason over your organization’s protected Microsoft 365 content (such as SharePoint sites, OneDrive files, Outlook mail, Teams messages, or other tenant resources). It also does not connect directly to your organization’s internal databases unless separate, explicitly configured integrations exist.

Instead, Copilot relies on three primary sources to generate a response: (1) the prompt context you provide in the current request (what you ask, plus any text you paste), (2) the conversation history within the current chat thread to maintain continuity, and (3) internet search data (when web grounding is available) to supplement general knowledge with up-to-date public information.

Therefore, the correct selections are C (prompt context), E (internet search data), and F (conversation history), while organizational Microsoft 365 data and Teams chat data are not used without the Copilot license.

a specific date range of activity

The Microsoft 365 My Account portal provides users with control over their Copilot activity history in alignment with enterprise privacy and compliance standards. When selecting Delete history, users can remove Copilot activity based on a defined time range rather than deleting only a single conversation or all activity universally.

This functionality reflects Microsoft’s commitment to transparency, user control, and responsible AI governance. Allowing deletion by date range enables organizations and individuals to manage data retention policies efficiently while maintaining compliance with regulatory frameworks such as GDPR and internal data governance policies.

The other options are incorrect because deleting a specific conversation or all conversations with a specific agent is not the primary method offered in the My Account activity deletion setting. Instead, deletion is structured around activity time periods.

This capability reinforces generative AI best practices: secure data management, lifecycle control of AI interactions, and user-directed privacy management within enterprise environments.

The Researcher agent in Microsoft 365 Copilot is designed to gather and synthesize information from web and organizational sources. To support transparency and trust, Copilot provides citations alongside generated content when external or referenced material is used.

Citations allow users to review the original sources that informed the generated report. This aligns with Microsoft’s Responsible AI commitment to transparency and verifiability. By selecting or reviewing citations, users can confirm that the information originates from credible and relevant references rather than unsupported model-generated text.

Instructions define how the agent behaves but do not validate source authenticity. Memory refers to conversational context retention and does not confirm source validity. Capabilities describe what the agent can do, not whether its output is grounded in legitimate sources.

Therefore, to verify that a report generated by the Researcher agent uses valid sources, you should review the citations.

Microsoft 365 Copilot integrates with Microsoft Search to help users discover relevant content across their organization’s Microsoft 365 data estate, including SharePoint, OneDrive, Teams, and Exchange. When the objective is to determine whether similar training plans already exist, the appropriate action is to perform a search across organizational content.

Using Search allows Copilot to query indexed enterprise documents and return files, plans, or related materials that the user has permission to access. This supports content reuse, avoids duplication of work, and aligns with Microsoft’s guidance on leveraging organizational knowledge efficiently.

Designer is focused on visual content creation, Apps provides access to Microsoft 365 applications, and Pages is used for creating and organizing content within Copilot. None of these options are intended for discovering existing documents across the tenant.

Therefore, to identify similar existing training plans within your organization, the correct tool to use in Copilot is Search.

==================================================

Comprehensive and Detailed 150 to 200 words of Explanation Microsoft AI Business professional documents:

To ensure cited information is accurate, Microsoft’s AI guidance emphasizes human verification of AI-generated outputs, especially when the content will be used in formal business documents. Even when Copilot grounds responses in SharePoint files, it can still misinterpret text, summarize imprecisely, or attribute a statement to the wrong section of a source. The most reliable way to confirm accuracy is to check each citation against the original SharePoint document and validate that the claim is supported exactly as written.

Option A is the best answer because manual verification is the definitive control for accuracy and accountability. Option B may help by asking Copilot to re-check or restate where information came from, but it is still an AI-generated confirmation and does not replace direct source validation. Options C and D can improve consistency and reuse of standards or references, but they do not guarantee citation correctness; they still depend on model interpretation.

Therefore, the best approach is to manually verify the citations in the generated proposal content.

Comprehensive and Detailed 150 to 200 words of Explanation Microsoft AI Business professional documents:

In Microsoft 365 Copilot, notebooks are designed to organize related work into a single, reusable workspace. A notebook can group multiple Copilot conversations and associate them with shared reference materials (for example, the same set of files, links, or notes). This directly addresses both requirements in the question: (1) making conversations easier to find by collecting them in one place, and (2) enabling those conversations to use the same reference sources for grounding and continuity.

An agent is best when you want a specialized Copilot experience with predefined instructions, capabilities, and (optionally) a configured knowledge source. However, an agent does not primarily function as a “container” to gather and organize multiple existing conversations.

A page is used to capture and edit output (such as a generated report) for collaboration, not to organize multiple conversations with shared references. An app is a broader product surface and does not solve the conversation organization requirement.

Therefore, the best solution is to use a notebook.

Microsoft 365 Copilot notebooks use the version of a file that was uploaded or attached at the time it was added to the notebook. When a document such as Process.docx is added from a local folder, Copilot references that uploaded snapshot of the file. If the file is later modified locally, the notebook does not automatically sync or refresh with the updated local version unless the updated file is re-uploaded.

Microsoft guidance on grounding and file references explains that Copilot works with the specific content stored in Microsoft 365 or the attached artifact within the notebook session. Since the updated version remains in the local folder and was not reattached, Copilot continues to use the originally added version.

Therefore, during subsequent chats in the notebook, Copilot references only the original uploaded version of Process.docx.

==================================================

The correct completion is “cannot modify the settings of” because built-in agents such as the Researcher agent in Microsoft 365 Copilot are system-defined experiences. These agents are designed and managed by Microsoft to ensure consistent functionality, security, compliance, and alignment with responsible AI standards.

While users can interact with Researcher, provide prompts, and refine outputs during conversations, they cannot directly modify the core system settings or configuration of the built-in agent from Microsoft 365. Administrative configuration and deeper customization are available when creating custom Copilot agents through approved development tools, but default Microsoft-provided agents have controlled configurations.

Options such as modifying agent instructions, adding prompts, or deleting suggested prompts imply direct structural customization of the built-in agent interface, which is not supported in the standard Microsoft 365 Copilot experience.

This reflects a key generative AI governance principle in enterprise environments: system-level controls remain centrally managed to maintain data protection, compliance, and responsible AI implementation across the organization.