--- id: copilot-giving-copilot-context lang: en track: copilot title: "Giving Copilot context" seoTitle: "Giving Copilot context: Graph and access" description: "Copilot is already grounded in your mail, files, chats and meetings through Microsoft Graph. Learn to point it at the right context and why oversharing matters." part: getting-started partTitle: "Getting started with Copilot" partOrder: 2 order: 5 level: Beginner durationMinutes: 5 outcome: "Point Copilot at the right context, at the right level, and understand why \"it already knows everything\" isn't entirely a good thing." summary: "Copilot is already grounded in your mail, files, chats and meetings via Microsoft Graph: a head start, but only as clean as your sharing permissions." draft: false updated: "2026-10-14" furtherReading: - title: "Understanding Copilot's personalization features" url: "https://support.microsoft.com/en-us/microsoft-365-copilot/customize-how-microsoft-365-copilot-responds-to-you" note: "How to set preferences that apply to every Copilot conversation." - title: "Provide custom instructions for your Microsoft 365 Copilot Notebook" url: "https://support.microsoft.com/en-us/Microsoft-365-Copilot/provide-custom-instructions-for-your-microsoft-365-copilot-notebook" note: "How to add custom instructions to a single Notebook." - title: "Personalize what Microsoft Copilot remembers" url: "https://support.microsoft.com/en-us/microsoft-365-copilot/personalize-what-microsoft-365-copilot-remembers" note: "How Copilot's Memory works and how to manage it." - title: "What information does Copilot use to answer my prompt?" url: "https://support.microsoft.com/en-us/microsoft-365-copilot/what-information-does-copilot-use-to-answer-my-prompt" note: "Which sources Copilot draws on when it answers you." keywords: - Copilot context - Microsoft Graph grounding - Copilot oversharing - Copilot permissions - Copilot custom instructions - Copilot Memory - Copilot prompt brief quiz: intro: "Five quick questions. Ace them all and the next lesson unlocks." passScore: 5 questions: - q: "What does Copilot already know when you open a fresh chat, without attaching anything?" options: - "Nothing, it starts from zero like Claude" - "Only the files you attach yourself" - "Every file in your organisation, whether or not you have access" - "Whatever it can access via Microsoft Graph: your mail, calendar, Teams chats, and files you have permission to see" answer: 3 explain: "Whatever it can access via Microsoft Graph: your mail, calendar, Teams chats, and files you have permission to see." - q: "Why can a broad Copilot question be a risk as well as a convenience?" options: - "Broad questions only search the web, never your files" - "It can surface old, loosely shared files or folders that were technically accessible but effectively forgotten" - "Copilot changes your sharing permissions when it searches" answer: 1 explain: "It can surface old, loosely shared files or folders that were technically accessible but effectively forgotten. Copilot didn't do anything wrong; it just removed the friction that kept those old permissions harmless." - q: "Which of these gives Copilot more targeted context instead of relying on a broad search?" options: - "Reference or attach a specific file, email or meeting, or use \"Add content\"" - "Ask a broader question so Copilot searches more widely" - "Rely on a tenant-wide search, since Copilot already sees everything" answer: 0 explain: "Reference or attach a specific file, email or meeting, or use \"Add content\" in Chat or a Page. A narrow question is both more accurate and safer." - q: "How does knowing what Copilot can see connect to the EU AI Act's Article 4 obligation?" options: - "It doesn't, because Article 4 doesn't apply yet to companies using tools like Copilot" - "It means checking what's shared across your tenant once, as a one-off IT project" - "Knowing what your AI can see before you rely on it is the practical, day-to-day version of the AI-literacy requirement" answer: 2 explain: "Knowing what your AI can see before you rely on it is the practical, day-to-day version of the AI-literacy requirement that already applies to every company using tools like Copilot." - q: "You keep repeating the same instruction across several chats inside one Copilot Notebook about a project. Where should that instruction go?" options: - "Into every message, retyped each time" - "Into that Copilot Notebook's custom instructions" - "Into a brand new chat for each question" - "Into \"Add content\" for each message" answer: 1 explain: "Into that Copilot Notebook's custom instructions, so it applies to every chat inside it instead of being retyped each time." pass: badge: "Perfect score" title: "You know what Copilot can see." body: "Full marks. You can point Copilot at the right context, at the right level, and you know why its head start is also a risk. That wraps up Getting started. Next up: why prompting makes the difference, the first lesson of Part 3." retry: "Check the marked answers and give it another go. You've got this." --- > **Level:** Beginner ยท **Reading time:** ~5 min > > **What you'll be able to do:** point Copilot at the right context, at the right level, and understand why "it already knows everything" isn't entirely a good thing. ## The starting point is different from Claude's If you've used Claude, you're used to a chat starting from nothing. It knows only what you type, attach, or explicitly connect. Copilot works the other way round: from the moment you open it, it's already grounded in Microsoft Graph, your Outlook mail, your calendar, your Teams chats, and any SharePoint or OneDrive files you have access to. Ask "what's on my plate this week" in Copilot and it can genuinely answer, pulling from your actual calendar and inbox, no attaching required. ## Why that's a head start, and a risk The upside is real: you often don't need to explain background Copilot can already see. The catch is that "can already see" means everything you technically have access to, including old, loosely shared files and folders nobody remembers granting access to. A broad question can surface content that was shared months or years ago and quietly forgotten, not because Copilot did anything wrong, but because it removed the friction that used to keep those old permissions harmless. This is the same point Rollo's AI Act material makes about Copilot's risk being "archaeological" rather than new: the exposure was already there, Copilot just makes it easy to find.
Claude vs. Copilot: the starting pointTwo panels. Left, Claude: an empty box, starts from zero, knows only what you type or attach. Right, Copilot: a row of pills for mail, calendar, files and Teams, starts pre-grounded via Microsoft Graph, already sees mail, calendar, files, Teams. Illustrative -- what Copilot can see is only as clean as your organisation's sharing permissions.Claude vs. Copilot: the starting pointClaudeemptyStarts from zero.Knows only what you type or attach.CopilotMailCalFilesTeamsStarts pre-grounded via Microsoft Graph.Already sees mail, calendar, files,Teams.vsIllustrative. What Copilot can see is only as clean as your organisation's sharing permissions.
## Being deliberate about context anyway Even though Copilot starts pre-grounded, you can, and often should, point it at something specific rather than relying on a broad, tenant-wide search. - Reference a specific file, email, or meeting by name in your prompt, or attach it directly, the way you would in Claude. - Inside a document, Copilot grounds itself to that document by default: narrower and more predictable than a standalone chat question. - Use "Add content" in Copilot Chat or a Page to explicitly bring in a file or link rather than hoping Copilot finds the right one on its own. A narrowly scoped question is both more accurate (less noise to sift through) and safer (less chance of surfacing something that shouldn't have come up). ## Three places to point that deliberateness Once you're being deliberate, it helps to know Copilot has scoped levels of its own, the same idea as Claude's profile instructions, project instructions, and per-message context, just under different names. - **This message.** Attach a file, reference something by name, or use "Add content." Applies to the one chat you're in, right now. The narrow scoping from above. - **This Notebook.** A Copilot Notebook (the closest thing Copilot has to a Claude project) can carry its own custom instructions, set from the notebook's menu, that apply to every chat inside it and stay with the shared material the notebook holds. Share the notebook and colleagues can see and co-edit those instructions too. - **Everything.** In Settings, under Personalization, "Customize how Copilot responds to you" applies your preferences to every future conversation: your role, the format you like answers in, terms you'd rather it didn't have to be told twice. Copilot also keeps its own Memory of details from past conversations, separate from this setting but working alongside it. Widen the scope the same way you would in Claude: when you notice yourself repeating the same instruction chat after chat, that's the signal to move it up a level. ## Write a short brief anyway Being pre-grounded is not the same as being briefed. Copilot can see your calendar and inbox, but it still doesn't know your role, your priorities this quarter, or how you like an answer formatted, unless you tell it. The same short brief from Claude's own context lesson works here: a few lines on who you are, what you're usually trying to get done, who reads your work, and the tone and format you like. Drop it into "Customize how Copilot responds to you" if it should apply everywhere, or into a Notebook's custom instructions if it's specific to one piece of ongoing work. Either way, a few minutes spent writing it down beats letting Copilot guess from whatever it happens to find in your Graph data. Here's what that looks like in practice, short enough to write in a couple of minutes: *I'm an account manager for our top-tier clients. I mostly draft client-facing emails, prep for renewal calls, and summarise account history before a meeting. My manager and the client-facing team read my work, so keep the tone professional but not stiff. When I ask for a summary, default to bullet points with any deadline or dollar figure called out clearly, not buried in a paragraph.* That's four sentences, and it does real work: it tells Copilot your role, your recurring tasks, your audience, and a formatting preference, all things it otherwise has to guess at from whatever happens to sit in your Graph data that day. Drop something like it into Settings once, and every future conversation starts from that baseline instead of zero. Update it when your role changes, rather than leaving Copilot working from an outdated picture of what you do. ## The Article 4 connection Knowing what your AI can see before you rely on it isn't just good practice. It's the practical version of the EU AI Act's Article 4 AI-literacy obligation, which already applies to every organisation using tools like Copilot. For Copilot specifically, that means treating a periodic look at what's actually shared across your tenant as part of using the tool responsibly, not a one-off IT project. ## Where this goes next Good context and good prompting are two halves of the same skill, whichever tool you're using. Context tells Copilot who it's helping and what it can already assume; the prompt tells it what to do with that. The difference with Copilot is that a lot of the context arrives whether you ask for it or not, which makes the deliberate half of the skill, choosing what to narrow, what to brief, and what to double-check, more important, not less. ## Try it Ask Copilot a broad question ("what have I been working on this week?") and note where the information came from. Then ask a narrowly scoped version, naming a specific file, email thread, or meeting. Compare the accuracy and relevance of the two answers. If you have a Notebook, add one line of custom instructions to it and ask the same question again from inside it. ## Key terms [Microsoft Graph grounding](/glossary#grounding), [Add content](/glossary#add-content), [Copilot Notebooks](/glossary#copilot-notebooks), [Custom instructions](/glossary#custom-instructions), [Tenant permissions](/glossary#tenant-permissions), [Copilot](/glossary#copilot)