Practice Free AB-900 Microsoft 365 Copilot and Agent Administration Fundamentals Exam Questions Answers With Explanation

The correct answer is are NOT assigned a Microsoft 365 Copilot license. Microsoft’s official reporting guidance explains that the Copilot credits report is used to manage metered consumption costs for Microsoft 365 Copilot Chat. The purpose of this report is to show credit consumption tied to pay-as-you-go billing policies, including metrics such as total credits used and credits used per user, per agent, and per billing policy. Microsoft’s Copilot analytics documentation further defines these credit-related metrics around Copilot Chat users, which are users with a Microsoft 365 license but without a Microsoft 365 Copilot license who consume credits while using agents.

Because licensed Microsoft 365 Copilot users are generally covered by their Copilot entitlement for included agent usage, the credits report is intended to track the metered agent usage scenario for users who are not assigned a Microsoft 365 Copilot license and who interact with work-grounded agents in Microsoft 365 Copilot Chat. That is why this option correctly completes the sentence.

The correct answer is Microsoft Graph . Microsoft documents that Microsoft 365 Copilot accesses organizational content and context through Microsoft Graph . Microsoft Graph provides the user’s work context, including items such as emails, chats, meetings, files, contacts, and calendar data , along with relationship and activity signals that help Copilot ground and rank responses. Microsoft also explains that Copilot combines organizational content with the user’s working context, such as recent chat conversations, email exchanges on a topic, and the meeting the user is currently in. Those are exactly the kinds of signals described in the question, including collaboration history and document relevance.

The other options do not fit this sentence. Microsoft Copilot Studio is used to build and customize copilots and agents. Microsoft Purview is for compliance, governance, and data protection. Microsoft Viva Insights provides workplace analytics and insights, but it is not the core service described by Microsoft as supplying the contextual signals that ground Microsoft 365 Copilot responses. Therefore, the only option that correctly completes the sentence is Microsoft Graph .

The correct answer is A . Microsoft Learn defines Zero Trust as a security strategy built on the principles verify explicitly , use least privilege access , and assume breach . Microsoft also summarizes Zero Trust as a model that assumes breach and verifies every request , rather than trusting users, devices, or traffic simply because they originate from inside the corporate network. This is the key reason option A is correct. Under Zero Trust, every access request should be evaluated continuously using available signals such as identity, device state, location, service, and risk.

Option B is incorrect because improving user experience is not the defining principle of Zero Trust. Option C is incorrect because Zero Trust requires ongoing review and adjustment of permissions, especially through least privilege and risk-based access. Option D is incorrect because Zero Trust explicitly rejects implicit trust based on network location. Microsoft states that organizations should reduce reliance on the traditional idea that anything on the internal network is automatically safe or trustworthy.

The correct answer is Microsoft Defender XDR . Microsoft Learn defines Microsoft Defender XDR as a unified pre- and post-breach enterprise defense suite that natively coordinates detection, prevention, investigation, and response across endpoints, identities, email, and applications to provide integrated protection against sophisticated attacks. That wording matches the sentence in the question almost exactly, which makes this the clearly correct choice.

The other options do not fit that definition. Microsoft Entra Conditional Access is Microsoft’s Zero Trust policy engine used to evaluate signals and enforce access policies, not a cross-domain threat detection and response suite. Microsoft Entra ID Protection focuses on detecting and responding to identity risks such as risky sign-ins and risky users. Microsoft Purview is Microsoft’s portfolio for data governance, data security, and compliance. None of those products is described by Microsoft as coordinating detection, prevention, investigation, and response across endpoints, identities, email, and applications in the same integrated XDR manner. Therefore, the only answer that correctly completes the sentence is Microsoft Defender XDR .

The correct answer is C. the code interpreter capability . Microsoft Learn states that the code interpreter capability for Microsoft 365 Copilot declarative agents allows the agent to generate and execute Python code to analyze data and generate visualizations . Microsoft’s agent schema documentation explicitly describes Code Interpreter as a capability used to solve complex math problems, analyze data, and generate visualizations. That directly matches the requirement to create charts and visualizations from a Microsoft Excel workbook .

Microsoft documentation also explains that code interpreter supports working with Excel files and is used for scenarios such as data analysis , statistical computations , and generating charts . This makes it the correct configuration for an agent that must reason over workbook data and produce chart-based outputs. By contrast, the image generator capability is for creating images, not for analyzing workbook data. The Scrum Assistant and Customer Insights Assistant options are templates, not the specific technical capability required to read data and build charts from an Excel workbook.

The correct answer is C. the Microsoft 365 admin center . Microsoft Learn documents a specific Copilot image generation setting in the Microsoft 365 admin center under Copilot > Settings > Copilot actions > Copilot image generation . Microsoft states that when this scenario is allowed, users can ask Copilot to create, design, and edit images. When it is not allowed, Copilot does not generate images and instead responds with stock or brand images. This directly matches the requirement to prevent users from generating images by using Copilot.

The other options are incorrect because Microsoft does not document this control as being managed from Defender, Purview, or Entra for this scenario. Microsoft also separately notes that organizations can control access to Designer image generation through policy, but the admin experience for managing the Microsoft 365 Copilot scenario itself is explicitly surfaced in the Microsoft 365 admin center . Therefore, for an exam question focused on where an admin should go to disable image generation in Copilot, the best and documented answer is the Microsoft 365 admin center .

The correct answer is D. a sensitivity label policy . In Microsoft Purview, creating a sensitivity label by itself does not make it available to users. Microsoft Learn states that after you create sensitivity labels, you must publish them by creating a label policy so that users and groups can see and apply those labels in Microsoft 365 apps and services. Publishing controls which labels are available and to whom they are shown. This is why a sensitivity label policy is required to ensure that users can apply Label1 to files.

The other options do not meet the requirement. Auto-labeling policies apply labels automatically when content matches conditions, but they are not the primary mechanism for simply making a label available for user selection. A trainable classifier is used to identify content categories, not to publish a label. A retention label policy publishes retention labels for records and lifecycle purposes, which is different from sensitivity labeling for classification and protection. Therefore, the correct Microsoft-documented method to let users apply Label1 to files is to publish it using a sensitivity label policy .