Practice Free AB-900 Exam Online Questions

Explanation:

To use Microsoft 365 Copilot Chat to reason over web data, you need a Microsoft 365 Copilot license. Answer. No

To use the Researcher agent in Microsoft 365 Copilot, you need a Microsoft 365 Copilot license. Answer. Yes

To add an agent in the Microsoft 365 Copilot app, you need a Microsoft 365 Copilot license.

Answer. No

The correct selections are No, Yes, No. Microsoft documents that Microsoft 365 Copilot Chat is available at no additional cost for eligible Entra account users with qualifying Microsoft 365 licenses, and that it includes secure AI chat grounded in the web. That means a separate Microsoft 365 Copilot add-on license is not required just to use Copilot Chat over web data.

Statement 2 is Yes because Microsoft states that Researcher is part of the core default experience for Microsoft 365 Copilot licensed users. In other words, access to the Researcher agent requires the Microsoft 365 Copilot license.

Statement 3 is No because Microsoft documents that users can access agents and create them in the Microsoft 365 Copilot app through Copilot Chat, and Microsoft 365 service descriptions state that web-grounded agents are available at no extra cost for commercial users with a qualifying Microsoft 365 license. A Copilot add-on license is required for certain advanced capabilities, but not simply to add an agent in the app in general.

Explanation:

The correct answer is Require multifactor authentication for administrative roles. In the exhibit, each recommendation shows its available Secure Score points. The listed values are 1/1 for Use least privileged administrative roles, 8/8 for Do not expire passwords, 0.73/8 for Enable policy to block legacy authentication, and 0/10 for Require multifactor authentication for administrative roles.

Because 10 points is the highest value among the options shown, resolving that recommendation would improve the Identity Secure Score the most.

Microsoft Learn explains that Identity Secure Score in Microsoft Entra is based on Microsoft security recommendations, and each recommendation contributes a specific number of points depending on its impact and implementation state. Recommendations related to administrator protection are especially important because privileged accounts are high-value attack targets. Microsoft also emphasizes multifactor authentication for admin roles as a core identity security best practice. Therefore, both from the screenshot and from Microsoft’s identity guidance, the recommendation with the greatest score improvement is Require multifactor authentication for administrative roles.

Explanation:

The correct answer is Connectors. Microsoft documents that Microsoft 365 Copilot connectors are used to bring external, line-of-business data into Microsoft 365 Copilot so users can search, reason over, and act on content from non-Microsoft systems. Microsoft also states that admins must enable and configure Copilot connectors in the Microsoft 365 admin center, and once configured, those connectors can be selected as knowledge sources for custom agents. This directly matches the requirement to let users use an external system as a knowledge source for custom Microsoft 365 Copilot agents.

This is why the hotspot in the Copilot area should be set to Connectors, not Overview, Agents, Search, Billing & usage, or Settings. Overview provides status information, Agents is for agent management, Search is for Microsoft Search experiences, and Billing & usage is for metering and consumption tracking. The specific admin feature that enables external enterprise data sources for agent grounding is Connectors. Microsoft further explains that configured connectors can expose external knowledge securely and respect source-level permissions when used in agent scenarios.

Explanation:

In Microsoft 365 Copilot, you should use the Researcher agent to perform multi-step reasoning over unstructured data.

The correct answer is the Researcher agent. Microsoft describes Researcher in Microsoft 365 Copilot as an agent for complex, multi-step research that can reason across information sources and synthesize findings into structured outputs. That aligns with the phrase multi-step reasoning in the question. Microsoft’s guidance also contrasts Researcher with Analyst, which is aimed more at data analysis and spreadsheet-oriented tasks.

The other options are less suitable. Chat is general-purpose and not the specialized tool Microsoft positions for deeper multi-step research workflows. A notebook is used to organize materials and chats, not as the main reasoning engine for this scenario. The Analyst agent is better suited to structured data analysis, trends, and calculations rather than broad reasoning over unstructured data such as documents, notes, and mixed content. Based on Microsoft’s product positioning, the best fit for multi-step reasoning over unstructured information is the Researcher agent.

Explanation:

time-bound role activation

The correct answer is time-bound role activation. Microsoft Learn explains that Microsoft Entra Privileged Identity Management (PIM) allows users to be made eligible for privileged roles and then activate those roles only when needed. Microsoft also states that once activated, the role is active for a preconfigured period of time, after which the privileged access expires automatically. This is the core just-in-time and time-limited access model that PIM is designed to provide. (learn.microsoft.com)

The other options do not match Microsoft’s definition of PIM. It is not primarily described as providing restricted access to Microsoft 365 services, the lifecycle management of users, or the management of enterprise applications. Those areas relate more closely to other Microsoft Entra and Microsoft 365 governance capabilities. Microsoft specifically positions PIM as a service to manage, control, and monitor access to important resources by using eligible assignments, approval workflows, MFA if required, and temporary role activation. Therefore, the phrase that correctly completes the sentence is time-bound role activation. (learn.microsoft.com)

Explanation:

provide control over how users can access cloud apps.

The correct answer is provide control over how users can access cloud apps. Microsoft Learn defines Microsoft Entra Conditional Access as the Zero Trust policy engine that uses if-then logic to make access decisions. Microsoft states that Conditional Access policies determine who can access resources, what resources they can access, and under what conditions. These policies can require actions such as multifactor authentication, compliant devices, or other controls before allowing access to applications and services like Microsoft 365. That means Conditional Access is specifically used to control how users access cloud apps.

The other options are incorrect. Conditional Access policies are not configured by using the Microsoft Defender portal; they are managed in the Microsoft Entra admin center. They are also not applied only to on-premises resources, because Microsoft documents Conditional Access primarily for cloud identities, cloud apps, and cloud-connected resources. Finally, Conditional Access does not require a Microsoft Exchange mailbox. It can be applied broadly across many Microsoft and third-party cloud applications integrated with Microsoft Entra.

Explanation:

The correct answer is accountability. Microsoft’s Responsible AI framework is built on six principles: fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability. Microsoft describes accountability as the principle that people who design and deploy AI systems must remain responsible for how those systems operate and for the impacts they create. A key part of that principle is ensuring there is human oversight so humans remain in control of decisions and system behavior.

The other options do not match the wording in the sentence as closely. Transparency focuses on helping people understand how AI systems work and why they produce certain outcomes. Privacy and security is about protecting data and securing systems. Reliability and safety is about dependable and safe operation. Inclusiveness is about designing AI that empowers and includes people broadly. The principle tied to oversight, responsibility, and keeping humans in control is accountability.