Domain 2 of 3 · Chapter 1 of 4

Writing Effective Prompts

The anatomy of a prompt: Goal, Context, Expectations, Source

Compare two prompts for the same task. "Write something about the launch" gives a generic paragraph. "Draft a three-bullet status update for my manager about the Contoso launch slipping a week, professional tone, based on Friday's status email" gives something you can almost send. The difference is not effort, it is structure.

Microsoft describes a prompt as up to four parts, and only the first is required (Learn about Copilot prompts[1]):

  • Goal is what you want Copilot to do: the verb and the deliverable ("draft a status update," "summarize," "compare"). A clear Goal is all that is strictly required to get a response.
  • Context is the background that narrows the Goal: who it is for, what situation it covers, what constraints apply ("for my manager," "the launch slipped a week").
  • Expectations set the tone, length, and format of the output ("three bullets," "professional," "a table"). This is where you control how the answer reads, not just what it says.
  • Source is the work content Copilot should ground on (a specific file, person, meeting, or email). Naming the Source is covered in the next section because it is the part that most changes the answer.

Think of these as dials, not a required form. You always set the Goal; you add Context, Expectations, and Source as the task needs them. A quick factual question ("what is our vacation policy?") needs only a Goal. A polished deliverable usually needs all four. The more of the right detail you put in, the less Copilot has to guess, and guessing is what produces the generic answer.

A promptset the dials you needGoalwhat to dorequiredContextbackground thatnarrows the goalExpectationstone, length,and formatSourcecontent to ground onoptional parts raise quality
Microsoft's four prompt parts: Goal is required; Context, Expectations, and Source are optional and raise quality.

Reference the right source with "/"

The Source is the part of a prompt that most changes the answer, so leaving it to chance is the most expensive shortcut. If you write a prompt and do not reference a specific file, person, or meeting, Copilot tries to determine the best source of data on its own, including across your work content (Refer to specific files and more[2]). Often it picks well; sometimes it grounds on the wrong document and produces a confident, wrong-sourced answer.

You ground on purpose by typing the forward slash. The feature is Context IQ (CIQ): type / in the prompt box and start typing the name of the item you want, then pick it from the suggestions. CIQ can reference people, Microsoft 365 files, meetings, and emails, ranked by how relevant and recent they are to you, but reaching those work items this way needs a paid Microsoft 365 Copilot license: do not assume the free Copilot Chat can "/"-reference your emails or meetings, because it cannot reach your work content on its own (more on this below). So "summarize /Q3 Launch Plan and list the open risks" grounds on that exact file instead of whatever Copilot would have guessed.

This is why the same Goal can give different answers: changing the Source changes what Copilot reads before it writes. Use it deliberately. When the task is about a known document, reference that document. When it is about what someone owns or said, reference the person or the meeting. Referencing the item is usually faster and cleaner than pasting its contents into the prompt, and it keeps the prompt short.

Two limits worth knowing for the exam. The license boundary above is one: with the paid Microsoft 365 Copilot license, "/" reaches people, meetings, emails, and files; the free, web-grounded Copilot Chat supports file references only. The second limit is that referencing only points Copilot at the source, it does not verify the answer for you, so still open the cited items and confirm.

Same goalnamed a source?NoYes, type "/"Copilot guesses the sourcemay ground on the wrong itemCIQ references the exact itemfile, person, meeting, or emaildifferent source, different answer
No source named means Copilot guesses; typing "/" (Context IQ) grounds on the exact file, person, meeting, or email.

Iterate, lean on the Gallery, and spot the exam pattern

A good prompt is rarely a one-shot. Microsoft's guidance is to expect back-and-forth conversation to get the results you want (Learn about Copilot prompts[1]). Refine with short follow-ups in the same conversation: "make it shorter," "more formal," "add the budget figures," "show me more." Each follow-up keeps the earlier context, so Copilot builds on the draft rather than starting over, which is both faster and more accurate than re-typing a longer prompt. Because answers can vary even for the same prompt, iterating is how you converge, not a sign you got the prompt wrong.

When you are unsure how to phrase a request, start from the Copilot Prompt Gallery, Microsoft's catalog of curated prompts, available inside Microsoft 365 Copilot and Copilot Chat (Prompt Gallery[3]). Pick a suggested prompt near your task and edit its Goal, Context, and Source to fit. Treat it as a template to adapt, not a button that produces a finished answer.

What the exam questions look like

These task bullets show up as short scenarios. A few patterns recur:

  • "Copilot gave a generic / wrong answer, what should the user do?" The right answer is almost always to add the missing Context or Source (reference the specific file with "/"), or to refine with a follow-up, not to switch tools or re-license. A weak prompt, not a broken product, is what the stem is testing.
  • "How does the user point Copilot at a specific document/person/meeting?" Type "/" and pick the item (Context IQ). Distractors offer pasting the whole file or hoping Copilot finds it; referencing is the cleaner, intended path.
  • "Where should a new user start to learn good prompts?" The Copilot Prompt Gallery. Distractors suggest external prompt sites or writing from a blank box.
  • "The first answer is close, what next?" Follow up in the same conversation to refine. Distractors restart with a brand-new prompt and lose the context.

The through-line: a good prompt is specific, names its source on purpose, and is refined in conversation. Most wrong answers ignore one of those three.

Write aspecific promptRead the answerGood enough?accurate and on-formatYesDoneNoFollow up in the same conversationshorter / more formal / add detail; context is kept
The refine loop: a follow-up in the same conversation keeps the earlier context, so you converge instead of restarting.

The four parts of a prompt

PartWhat it setsExample fragmentRequired?
GoalWhat you want Copilot to do"Draft a status update"Yes, always
ContextBackground that narrows the task"for my manager, the launch slipped a week"Optional, raises quality
ExpectationsTone, length, and format of the output"three bullets, professional tone"Optional, raises quality
SourceThe work content to ground on, via "/""based on /Launch status email"Optional, changes the answer

Decision tree

Know how to ask?have a clear goal in mindNoStart from Prompt Galleryadapt a curated promptYesNeed a specific source?a known file, person, meetingYesReference it: type "/" (CIQ)grounds on the exact itemNoAdd context + expectationstone, length, formatAnswer good enough?accurate and on-formatYesDoneverify cited sourcesNoFollow up in the same conversation to refineshorter / more formal / add detail; context is kept, do not restart
Cheat sheet

Sharp facts the exam loves — give these one last read before exam day.

Cheat sheet

Sharp facts the exam loves — scan these before test day.

A Copilot prompt has four parts: Goal, Context, Expectations, Source

Microsoft frames an effective prompt as up to four parts. Goal is what you want Copilot to do, Context is the background that narrows it, Expectations set the tone and format of the output, and Source is the work content to ground on. Goal answers "what," Context answers "for what situation," Expectations answers "in what shape," and Source answers "based on what." Adding the right parts is what turns a generic answer into a usable one.

12 questions test this
Only the Goal is required; the other three parts are optional quality boosts

All a prompt strictly needs is a clear Goal to get a response. Context, Expectations, and Source are optional and you add them as the task warrants: a quick factual question ("what is our vacation policy?") needs only a Goal, while a polished deliverable usually wants all four. They are dials to turn up, not a mandatory form to fill in.

Trap Assuming every prompt must spell out all four parts; over-specifying a simple lookup wastes effort, and a clear Goal alone is enough for it.

1 question tests this
Be specific, because a vague prompt gives a generic answer

Copilot narrows its answer against the detail you give, so naming the audience, the length, the tone, and the exact deliverable removes its guesswork. A vague prompt leaves nothing to narrow against and returns something generic you then have to rewrite. Specificity in the prompt is usually cheaper than editing the output afterward.

9 questions test this
Show an example of the style you want instead of describing it

When the format or voice matters, pasting one short example of the style you want teaches Copilot faster than a paragraph describing it. This is part of the Expectations: a concrete sample of the desired output shape is a clearer instruction than abstract adjectives. It is most useful when the format is hard to put into words.

Reference a specific file, person, or meeting by typing "/" in the prompt

To ground a prompt on exact work content, type the forward slash and start typing the item's name, then pick it from the suggestions. The feature is Context IQ (CIQ), and it can reference people, Microsoft 365 files, meetings, and emails, ranked by relevance and recency to you. So "summarize /Q3 Launch Plan" grounds on that file rather than whatever Copilot would have guessed.

Trap Pasting the whole file's text into the prompt instead; referencing it with "/" is cleaner, keeps the prompt short, and points Copilot at the live item.

19 questions test this
If you name no source, Copilot guesses the best one

When a prompt does not reference a specific file, person, or meeting, Copilot tries to determine the best source of data on its own, drawing on your work content. It often chooses well, but it can ground on the wrong document and produce a confident, wrong-sourced answer. Naming the Source removes that risk.

11 questions test this
The source you ground on changes the answer, so choose it on purpose

The same Goal grounded against different sources produces different answers, because the Source determines what Copilot reads before it writes. That makes selecting the right source part of writing the prompt, not an afterthought: reference the document when the task is about that document, and reference the person or meeting when it is about what they own or said.

27 questions test this
Using "/" to reference your work items needs a Microsoft 365 Copilot license

Referencing people, meetings, emails, and files with "/" through CIQ requires a Microsoft 365 Copilot license. The free, web-grounded Copilot Chat supports file references only and cannot reach your work content on its own. Knowing the tier tells you whether the slash can pull in work items automatically.

Trap Assuming the free Copilot Chat can reference your emails or meetings with "/"; without a Copilot license it grounds on the web and your supplied files, not your work content.

The Copilot Prompt Gallery is Microsoft's catalog of curated prompts, available inside Microsoft 365 Copilot and Copilot Chat and organized by scenario. It is the fastest way to learn the shape of a good prompt: open a suggested prompt close to your task, then edit its Goal, Context, and Source to fit. Treat it as a starting template to adapt.

Trap Running a Gallery prompt unchanged and expecting a finished answer; it is a template to adapt to your situation, not a one-click result.

Treat prompting as a conversation and refine with follow-ups

A first answer is a starting point, and Microsoft's guidance is to expect back-and-forth to get the result you want. Refine with short follow-ups like "make it shorter," "more formal," or "show me more" rather than re-typing the whole prompt. Stopping at the first response is the most common reason a prompt feels like it underdelivered.

5 questions test this
Follow-ups in the same conversation keep the earlier context

When you refine with a follow-up in the same conversation, Copilot keeps the context from the earlier turns and builds on the draft it already produced. Starting a brand-new prompt instead drops that context and makes Copilot begin from scratch, which is slower and loses what you had already shaped. Refine in place to converge.

Trap Opening a fresh prompt to tweak a near-good answer; that loses the conversation's context, so reword in the same thread instead.

2 questions test this
The same prompt can return different answers, so iterating is normal

Using the same prompt more than once can produce different responses, because the underlying model has built-in variability. That means variation is expected behavior, not a malfunction, and refining toward the answer you want is the intended workflow rather than a sign the prompt was wrong.

Referencing a source points Copilot at it, but does not verify the answer

Grounding on the right file with "/" improves the source, yet Copilot can still summarize it imperfectly, and a generative model can occasionally produce incorrect content. So review and verify the response, opening the cited items to confirm, rather than trusting a grounded answer blind. Referencing is about aiming, not proofreading.

1 question tests this
Ground on web data for public info and on your own files for internal facts

Choose the source by where the truth lives: current public information that your organization has not documented (competitor pricing, industry news, market-size figures, new-market regulations) must come from web content, while proprietary facts (your sales figures, internal budget, survey results) must come from your organization's files and emails. When a single answer needs both, scope each part to its correct source rather than grounding the whole thing on one.

Trap Grounding a request for confidential internal figures on web content, which returns only generic public data and never your tenant's numbers.

13 questions test this
Open an email thread and use Copilot in Outlook to ground on that conversation

To summarize or reply based on a long Outlook thread, open the thread and use Summary by Copilot or Draft with Copilot from within it. Copilot then grounds its output in the messages of that specific conversation, producing recaps and replies that reflect the full back-and-forth rather than your memory of it; a thread summary even includes numbered citations that jump to the matching message.

Trap Building a custom agent to handle a one-off thread summary, when Copilot in Outlook already grounds on the open conversation.

4 questions test this

Also tested in

References

  1. https://support.microsoft.com/en-us/topic/learn-about-copilot-prompts-f6c3b467-f07c-4db1-ae54-ffac96184dd5
  2. https://support.microsoft.com/en-us/microsoft-365-copilot/refer-to-specific-files-and-more-in-microsoft-365-copilot
  3. https://learn.microsoft.com/en-us/microsoft-365/copilot/copilot-prompt-gallery