Evaluating spend and performance trends and determining ROI is a structured analytics task. In Microsoft 365 Copilot, the Analyst agent is designed for quantitative analysis workflows: it can interpret tables, analyze datasets, identify trends over time, calculate metrics (such as ROI), and present results clearly (often including charts or summarized insights). This makes it the best fit when your goal is to compare marketing channels and understand which ones are delivering the strongest return based on last year’s data.

Chat (Option B) can help you brainstorm questions or explain results, but it is not purpose-built for deep numeric analysis. The Researcher agent (Option C) is optimized for gathering and synthesizing information from sources and producing research-style outputs, not performing ROI calculations on internal performance data. A notebook (Option D) is useful for organizing files and keeping shared reference material across related conversations, but it does not itself perform the analysis—you would still need an analysis-capable agent.

Therefore, the best choice to evaluate spending and performance trends and calculate ROI is the Analyst agent .

Microsoft’s approach to transparency for AI-generated media relies on provenance signals rather than cosmetic indicators. File names and descriptions can be edited easily and are not reliable evidence of how an image was created. Watermarks may appear in some contexts, but they are not consistently applied across all AI image-generation workflows and can sometimes be removed or lost through copying, screenshotting, or file conversion.

Microsoft supports the use of content credentials to help users verify whether digital content was created or modified with AI. Content credentials are part of a provenance standard (often associated with C2PA) that can embed tamper-evident metadata into media files. When present, these credentials can show information about the tool or process used to generate or edit the image, providing a verifiable chain of origin.

Therefore, the most dependable way to verify whether the images were AI-generated is to check for content credentials (option C), since they are designed specifically to provide authenticity and provenance information for AI-created or AI-edited content.

Use the Analyst agent for Prompt 1 because it is optimized for structured data work: consolidating worksheets, performing calculations, sentiment breakdowns by category (product line), and producing visualizations. These tasks align with analysis-style workflows where quantitative processing and charting are required.

Use the Researcher agent for Prompt 2 because it is designed to synthesize information from multiple sources, including SharePoint content plus web grounding , and to produce a well-structured brief with citations . Researcher is best when you need evidence-backed insights, reputable sourcing, and an organized narrative with risks and gaps.

Use Chat for Prompt 3 because the goal is drafting a refined executive email based on an attached document with tone control and communication standards. Chat excels at business writing, rewriting, tone adjustment, and producing polished communications without needing the deeper research workflow or heavy data analytics specialization.

In Microsoft 365 experiences, the standard way to invoke or reference people and specific resources in-context is by using the @mention pattern. Microsoft 365 Copilot extends this familiar interaction model to agents: when you want to switch to, invoke, or direct a question to a specific agent from within an existing Copilot conversation, you use @ followed by the agent’s name. This makes the agent selection explicit and reduces ambiguity about which assistant or capability you want to use for the next turn.

The other syntaxes listed are commonly associated with different systems: square brackets are not used for agent invocation, hashtags are typically used for topics/tags, and slash commands are used in some chat applications for command execution—but they are not the standard method for calling a Copilot agent in Microsoft 365 Copilot Chat.

Therefore, to chat with an agent named Agent1 during an open Copilot conversation, you should enter @Agent1 .

Microsoft Purview is the correct choice because it is Microsoft’s unified compliance and data governance solution that helps organizations apply and enforce policies across Microsoft 365 content— including Copilot-related interactions where those interactions are captured in services such as Microsoft 365 audit, eDiscovery, and Purview compliance experiences. Purview supports capabilities such as data loss prevention (DLP) , retention , eDiscovery , audit , and sensitivity labeling so organizations can manage and govern data and AI-assisted content in line with regulatory and internal requirements. In contrast, Microsoft Entra ID focuses on identity and access management, Intune focuses on device and application management, and Defender for Cloud focuses on cloud security posture management. Governance policies for Copilot-generated conversations and associated compliance controls align most directly with Purview , which is designed to manage information protection and compliance across the Microsoft 365 environment.

Temporary chat in Microsoft 365 Copilot is designed for privacy-focused, non-persistent interactions. When a user initiates a temporary chat session, the conversation is not saved to Copilot chat history and is not retained for future reference within the standard conversation history interface.

Once the session ends or a new chat begins, the prompts and responses from that temporary session are deleted immediately. They are not moved to OneDrive, stored in a notebook, or retained for a delayed deletion period.

This feature supports secure and confidential usage scenarios where users may want to explore ideas, draft sensitive content, or test prompts without creating a stored record in their activity history.

From a generative AI governance perspective, this reflects Microsoft’s design principle of providing configurable persistence levels, balancing productivity with enterprise security, compliance, and user privacy controls.

According to Microsoft AI Business Professional guidance for Microsoft 365 Copilot, grounding a response means ensuring the AI generates output based on specific, authoritative content rather than relying on generalized training data. When working with enterprise documents such as proposals, grounding is achieved by explicitly referencing the source material within the prompt.

Option C is correct because referencing the proposal content directs Copilot to use that specific document as the primary context for generating the response. Microsoft documentation emphasizes that effective prompts should include clear context and explicit references to relevant files, meetings, emails, or documents stored in Microsoft 365. This reduces hallucinations and ensures factual alignment with organizational data.

Option A is incorrect because relying on training data increases the risk of inaccurate or fabricated information. Options B and D improve prompt clarity but do not guarantee grounding in the proposal itself.

Therefore, explicitly referencing the proposal content is the most reliable and best practice method for ensuring grounded, accurate responses in Microsoft 365 Copilot.

Custom instructions allow users to define persistent preferences for tone, style, and response behavior across conversations. Microsoft documentation explains that Custom instructions help tailor Copilot responses to professional roles, communication styles, and domain expectations.

For a medical researcher requiring consistently professional, field-appropriate responses, configuring Custom instructions in Settings ensures that Copilot maintains the desired tone and terminology in future interactions.

Attaching examples influences only a single conversation. Saving prompts to the Prompt Gallery aids reuse but does not enforce tone globally. Copilot Memory stores factual preferences but is not intended for style configuration.

Therefore, the best and most comprehensive approach is to configure Custom instructions in Settings.

In Microsoft 365 Copilot, the Copilot Prompt Gallery is used to store and reuse prompts that have been created and tested. To save a prompt into the gallery, Copilot must first have the prompt as an executed interaction so it can be captured as a reusable prompt (often alongside the context and intended outcome). Microsoft guidance for prompt management emphasizes validating prompts by running them and reviewing the output, then saving the prompt for reuse once it produces the desired results.

Option D is therefore the correct first step: run the prompt . After execution, you can save it to the Prompt Gallery so it becomes easily discoverable and reusable for future project reports or for sharing within your organization (subject to policy).

Creating a notebook is useful for organizing reference materials across related conversations, but it is not required to publish a prompt to the gallery. Adding an agent is for creating specialized assistants with knowledge and capabilities, not for saving a single prompt. Creating a page is used to refine and collaborate on generated content, not to make a prompt available in the gallery.

Therefore, the first action is to run the prompt .