Legit AB-900 Exam Download

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 selections are No, Yes, Yes . Statement 1 is No because Microsoft documents tenant controls for web search on or off , but not a general Microsoft 365 Copilot setting to block only selected websites for normal Copilot responses. Microsoft also says it doesn’t recommend or support managing Copilot through selective URL or domain blocking at the network level. Website allow/block lists shown in Microsoft documentation apply to Researcher with Computer Use virtual-device settings, not to standard Microsoft 365 Copilot web grounding overall.

Statement 2 is Yes because Microsoft provides the Allow web search in Copilot policy in Cloud Policy service and in the Microsoft 365 admin center, which can disable web search for Microsoft 365 Copilot and Copilot Chat.

Statement 3 is Yes because Microsoft states that admins can block Researcher and Analyst , and agent governance includes a Block action. Microsoft also notes that for Researcher and Analyst, user scoping isn’t edited through the usual panel; availability is managed by blocking the selected agent at the tenant level.

The correct answers are C and D . Microsoft Learn explains that agents created with Agent Builder in Microsoft 365 Copilot allow you to define specific instructions that extend Microsoft 365 Copilot for a business scenario. Microsoft also documents that you can add knowledge sources such as specific public websites and SharePoint content so the agent can reason over targeted information instead of relying only on the default chat experience. Those two capabilities directly match the needs in options C and D.

Option A is incorrect because grouping chats is a Copilot notebook scenario, not the reason to build an agent. Option B is incorrect in the context of creating an agent in the Microsoft 365 Copilot app . Agent Builder supports declarative agents with instructions, knowledge, and capabilities, but Microsoft Learn describes custom AI model control as part of custom engine agents built with tools such as Copilot Studio, SDKs, or Foundry, not as a standard Agent Builder feature in the Microsoft 365 Copilot app. Therefore, when the task is specifically to create an agent in the app, the valid reasons are custom instructions and reasoning over a specific website .

The correct answer is C because Microsoft explains that authorization is the process of determining whether an authenticated identity is allowed to access a resource . Microsoft Learn distinguishes authorization from authentication by stating that authentication proves who you are, while authorization decides what you can access or do after identity has been established. In Microsoft 365 and the Microsoft identity platform, authorization commonly involves permissions, scopes, roles, and consent that control access to data and services such as Microsoft Graph, Exchange, SharePoint, or Teams.

Option A is incorrect because it refers more to external identity validation or federation concepts, not authorization itself. Option B describes authentication , not authorization, since it is about verifying identity claims. Option D describes a control such as multifactor authentication or Conditional Access requirements, which can happen before access is granted, but that still is not the definition of authorization. Authorization begins after identity verification and focuses on whether the identity has the right permissions for the requested resource.