MICROSOFT-AB-730 Practice Questions

Microsoft 365 Agent Builder natively supports using Microsoft Teams data—including channels, group chats, and 1:1 chats—as a direct knowledge source to ground an agent. However, past Microsoft 365 Copilot interaction transcripts are not an officially supported data source; grounding is restricted to enterprise sources like SharePoint, Dataverse, web URLs, Graph Connectors, and Teams. Furthermore, image files such as JPG or PNG cannot be used. Copilot specifically parses text content for knowledge retrieval, explicitly restricting supported file uploads to standard document formats such as .docx, .pdf, .pptx, .xlsx, and .txt.

Microsoft Learn, Add knowledge sources to your declarative agent in Microsoft 365 Copilot (Article: microsoft-365-copilot/extensibility/agent-builder-add-knowledge), Section: "Microsoft Teams data".

Microsoft Learn, Agent Registry in the Microsoft 365 admin center (Article: microsoft-365/admin/manage/agent-registry), Section: "Supported file types and limits" (Confirming the exclusion of image formats).

Microsoft Learn, Knowledge sources summary - Microsoft Copilot Studio (Article: microsoft-copilot-studio/knowledge-copilot-studio), Section: "Supported knowledge sources" (Confirming the exclusion of Copilot conversations).

When a declarative agent, such as a custom "Researcher agent," is published and accessed from within the Microsoft 365 user interface, it is in a deployed state for end-user consumption. The Microsoft 365 client does not provide authoring controls to alter the agent's foundational behavior. You cannot change its base instructions, add new starter prompts, or delete existing suggested prompts directly from the M365 chat interface. To make any structural or behavioral modifications, the developer or administrator must return to the original authoring environment (e.g., Microsoft Copilot Studio), edit the configuration parameters there, and republish the agent.

Microsoft Learn Documentation: Overview of declarative agents for Microsoft 365 Copilot. Section: "Authoring and Publishing". This document specifies that the creation and modification of declarative agent configurations (instructions, prompts, knowledge) occur exclusively within Copilot Studio or via the Teams Toolkit, not the M365 client UI.

Microsoft Learn Documentation: Manage Microsoft Copilot Studio agents in Microsoft 365. Section: "Edit an existing agent". It dictates that to update an agent deployed to M365, makers must open the agent in Copilot Studio, make the necessary changes, and select "Publish" again.

Microsoft 365 Copilot can surface data from Teams chats by summarizing long threads, extracting key points, and finding specific historical information. It also seamlessly summarizes, drafts notes, and answers queries about Teams meetings by analyzing the live or recorded meeting transcript. However, Copilot operates as an interactive, prompt-driven assistant. It cannot autonomously trigger sequences like scheduling, drafting, and sending emails "based on certain conditions." Conditional, trigger-based workflow automation is a distinct capability belonging to Microsoft Power Automate.

Microsoft Learn: Welcome to Copilot in Microsoft Teams. Section: "Catch up on chats and channels." This confirms Copilot's ability to extract and surface data from chat histories.

Microsoft Learn: Get started with Copilot in Microsoft Teams meetings. Section: "Use Copilot during a meeting." This details the capability to answer questions and summarize meeting content via transcripts.

Microsoft Learn: Overview of Microsoft Power Automate. Section: "Automate repetitive tasks." This distinguishes conditional, automated workflows (like sending emails based on triggers) as a Power Automate feature, contrasting with Copilot's prompt-response architecture.

When users navigate to the Microsoft 365 My Account portal (under Settings & Privacy) and select the "Delete history" option for their Copilot activity, the system performs a bulk deletion. It removes the user's entire Microsoft 365 Copilot interaction history. Microsoft's privacy controls for this specific portal action do not currently allow for granular deletions, such as filtering by a specific date range, selecting a single conversation, or isolating interactions with a specific agent. Selecting this option clears all saved prompts and responses associated with that user's account.

Microsoft Support Documentation: "Delete your Microsoft 365 Copilot activity history." Section: How to delete your Copilot activity history. (Details the exact steps in the My Account portal and confirms it deletes the entire history).

Microsoft Learn: "Data, Privacy, and Security for Microsoft 365 Copilot" (Article ID: microsoft-365-copilot-privacy). Section: Copilot activity history. (Outlines user data retention and the privacy portal's bulk deletion capabilities).

 In Microsoft 365 Copilot, prompt scheduling has specific execution constraints to manage automated background workloads. First, the highest permitted frequency for a scheduled prompt is Once per day; more granular intervals like hourly executions are not natively supported. Second, there is a strict lifecycle limitation restricting the maximum number of times a scheduled prompt can run to 15 times. After the 15th execution, the scheduled task will automatically stop and cannot be extended. To continue the automated workflow, the user must manually duplicate or recreate the prompt schedule.

Microsoft Learn, Manage Scheduled Prompts for Microsoft 365 Copilot, Section: "What's the user experience for scheduled prompts?", Document ID: scheduled-prompts (October 2025).

Microsoft Learn, Microsoft 365 Environment for Scheduled Prompts, Section: "Lifecycle and operations", Document ID: scheduled-prompts-environment (October 2025).

Would you like me to clarify any other limitations related to the underlying Power Platform environment that provisions these scheduled Copilot workflows?

Microsoft 365 Copilot agents are designed to integrate with Microsoft 365 data sources and provide

flexible, natural-language-driven configuration. Agents can be connected to organizational data such

as SharePoint, OneDrive, and Exchange. Since shared mailboxes are part of Exchange Online and

accessible through Microsoft Graph (subject to permissions), agents can be configured to search

shared mailboxes, making Statement 1 correct.

Microsoft also enables natural language creation of agents, allowing users to describe what the

agent should do, its purpose, and behavior using conversational instructions rather than requiring

code. This simplifies agent creation and aligns with Copilot’s low-code/no-code approach, so

Statement 2 is correct.

However, agents cannot use other agents as knowledge sources. Knowledge sources are limited to

structured content such as files, sites, and data repositories. Agents operate independently rather

than being nested or chained as data sources, making Statement 3 incorrect.

Thus, the correct answers are Yes, Yes, No.

Statement 1 is No. Microsoft explicitly states that organizational tenant data (emails, chats, documents) and user prompts are not used to train or fine-tune the foundational Large Language Models (LLMs) used by Microsoft 365 Copilot.

Statement 2 is No. According to Microsoft documentation, Copilot in Outlook currently only functions within a user's primary mailbox. It does not support summarizing or interacting with shared, delegate, or archive mailboxes.

Statement 3 is Yes. Copilot strictly adheres to your organization's existing Microsoft 365 security, compliance, and privacy boundaries. It uses Microsoft Graph to access enterprise data, meaning it only surfaces information that the user already has explicit permission to view based on existing Role-Based Access Control (RBAC) and sharing settings.

Microsoft Learn. "Data, Privacy, and Security for Microsoft 365 Copilot." Microsoft 365 Enterprise Documentation. Section: "How Microsoft 365 Copilot uses your proprietary data" and "Security and compliance features". (Validates that tenant data is not used for model training and confirms the inheritance of M365 security frameworks). [Available via Microsoft Docs/Learn]

Microsoft Support. "Frequently asked questions about Copilot in Outlook." Microsoft 365 Copilot Documentation. Section: "What are the limitations of Copilot in Outlook?". (Explicitly states: "Currently, Copilot only supports your primary mailbox. It does not support shared, delegate, or archive mailboxes.") [Available via Microsoft Support]

Enterprise Data Protection (EDP) is the specific privacy and security commitment in Microsoft 365 Copilot that guarantees organizational data remains secure. When users access Copilot using their work or school accounts (Microsoft Entra ID), EDP ensures that user prompts, generated responses, and any business data accessed via Microsoft Graph remain strictly within the Microsoft 365 tenant's trust boundary. Crucially, EDP guarantees that this business data is never logged or used to train Microsoft's underlying foundation large language models (LLMs). While Zero Trust and Sensitivity Labels are important security features within the ecosystem, EDP is the exact framework explicitly responsible for preventing customer data from being used in AI model training.

Microsoft Learn: "Data, Privacy, and Security for Microsoft 365 Copilot" - Section: Enterprise data protection (EDP). Details how prompts, responses, and data accessed through Microsoft Graph are not used to train foundation LLMs. (https://learn.microsoft.com/en-us/microsoft-365-copilot/microsoft-365-copilot-privacy)

Microsoft Learn: "Enterprise data protection in Copilot for Microsoft 365 and Microsoft Copilot" - Section: How does EDP protect your data?. Confirms that customer data is protected and not used to train the AI foundation models. (https://learn.microsoft.com/en-us/copilot/enterprise-data-protection)

Copilot Pages is a collaborative canvas feature that allows users to work with AI-generated content and share it with others. This functionality is available in both Microsoft 365 Copilot (the full version integrated into Office apps) and Microsoft 365 Copilot Chat (the standalone chat experience). It serves as a persistent workspace where AI responses can be edited, expanded, and collaborated upon, making it a core feature accessible across both offerings.

A. The Researcher agent is an advanced capability available only in the full Microsoft 365 Copilot version, not in Copilot Chat.

C. Copilot Notebooks is not a standard feature name in Microsoft's official documentation for either version.

1. Microsoft Official Documentation: "Copilot Pages in Microsoft 365" - Microsoft 365 Admin Center Documentation

Section: Copilot Features Overview

November 2024

2. Microsoft Technical Documentation: "Microsoft 365 Copilot Architecture" - docs.microsoft.com/microsoft-365/copilot/architecture

Pages 12-15

3. Microsoft Licensing Guide: "Microsoft 365 Copilot vs Copilot Chat Features" - Microsoft Volume Licensing Service Center

Document ID: M365-COP-2024-v1.2

Pages 8-10

To ensure Microsoft 365 Copilot's response is based exclusively on a specific document, you must "ground" the prompt in that data source. The most effective method is to explicitly reference the file within the prompt. Using a forward slash (/) followed by the filename tells Copilot to use that document as the primary source of information for its answer, preventing it from relying on its general training data or making inferences. This directly focuses the AI on the provided content for accuracy.

A. This is the opposite of grounding. Relying on general training data can lead to inaccurate or irrelevant information not specific to the proposal.

B. Adding a goal is a good practice for prompt engineering but does not, by itself, ground the response in a specific document.

D. Defining the audience helps tailor the tone and complexity of the response but does not ensure the information is sourced from the proposal.

1. Microsoft Learn. (2024). The art and science of prompting with Microsoft Copilot for Microsoft 365. In "The Copilot prompt book

" Section: "Grounding

" Paragraph 1. "Grounding is how you can ensure that Copilot is using specific information... The easiest way to ground your prompt is to use the forward slash (/) command..."

2. Microsoft Learn. (2024). Microsoft Copilot for Microsoft 365—Prompts. In "Reference a file

" Paragraph 1. "You can reference a file in your prompt

and Copilot will use the content of that file to inform its response. You can reference a file by typing '/' and the name of the file."