RESEARCH REPORT PART XI APR 2026 ARUP DIGITAL ADVISORY WORKFLOWS

The Edge
workflow, researched.

How the advisory team should use Copilot in Edge — to compress an afternoon of research into twenty minutes, interrogate PDFs without reading them cover-to-cover, and compose briefings from whatever's open in the browser. Six distinct Edge AI surfaces, six advisory workflows, and the one visual check that separates safe Arup work from unprotected data exposure.

The premise
Edge is where advisory research actually happens — industry reports, regulatory documents, client annual reports, competitor websites, YouTube briefings, news, procurement portals. Copilot in Edge turns the browser into a reading assistant that can absorb everything in your tabs and synthesise across it. Used with discipline, it compresses the core research loop from afternoons into minutes. Used without discipline, it quietly leaks client data into consumer Copilot. The green shield is the line between the two.
6 tools
Distinct Edge
AI surfaces
6
Use-case
workflows
~20 min
To scan 10 sources
properly
🛡
Green shield =
Enterprise Data Protection
01 / CORE SHIFT

Research at sidebar speed.

Before the features, the reframe. Web research has always been a slow, sequential process — read page, take notes, close tab, repeat. Copilot in Edge turns that into a parallel one. The browser reads with you. Whatever's in the tab becomes queryable.

Think about how an advisory consultant usually researches a new topic. Open search. Click through ten blue links. Read each carefully. Copy-paste excerpts into a Word doc. Keep twenty tabs open for days. Try to remember which page said what. Eventually write something synthesising it all, losing most of what you read along the way.

"The real value here isn't speed, it's selectivity. A research task rarely involves reading one source thoroughly — it involves scanning many sources and going deeper into the ones that matter. Copilot makes that dramatically faster."

Copilot in Edge doesn't replace reading — it restructures the sequence. Three specific shifts:

From reading to triaging

Old pattern: read every page that looked vaguely relevant, hoping something useful emerged. New pattern: open 10-12 tabs in parallel, sidebar-summarise each in 30 seconds, close the ones that aren't useful, deep-dive only the ones that are. The afternoon research session becomes a 20-minute session with better output because your reading time is spent on the sources that actually matter.

From static to conversational

Old pattern: the page is the interface. You read whatever the author put in whatever order. New pattern: the sidebar is the interface. Ask specifically what you want to know about the page — "what does this say about procurement frameworks for transport authorities?" — and get a targeted answer. You interrogate the page; you don't just receive it.

From one-tab to all-tabs

Old pattern: to compare three websites, you'd open them in sequence and take notes, then manually build a comparison. New pattern: with Copilot Mode, Copilot reads all your open tabs at once and produces a synthesised comparison. The browser becomes a research assistant that can read everything simultaneously — the closest thing to delegation in the Microsoft stack.

For Arup advisory work — where engagements routinely require reading regulatory documents, client annual reports, competitor websites, industry research, and government guidance — the compounding return is enormous. A consultant who builds these habits produces more-informed deliverables in a fraction of the time. The research time doesn't just shrink; the quality of what you actually know at the end of the session goes up.

The lowest-barrier Copilot in the stack
Most chapters in this playbook describe features you have to invoke deliberately — open Copilot in Word, turn on transcription in Teams, build a notebook. Edge is the opposite: every page you're on is already a Copilot surface. There's no workflow to set up. Open the sidebar, ask a question about whatever's in front of you. The only barrier is habit — remembering to ask. That makes it the easiest Copilot surface for the team to adopt, and the most wasteful one to ignore.
02 / THE SIX TOOLS

Six distinct Edge AI surfaces — all in the browser.

"Copilot in Edge" covers six related but distinct capabilities. Page summarise is the one everyone knows. The other five — PDF analysis, multi-tab reasoning, video summarise, Compose, and right-click Rewrite — are where the research workflow really lives.

Core featureSidebar · Ctrl+Shift+.Every page
1 · Page summarise & Q&A
Click the Copilot icon in the top-right or press Ctrl+Shift+. to open the sidebar. Type "Summarise this page" for a default structured overview, or ask a specific question — "What does this say about procurement constraints?", "What are the author's three main recommendations?", "Is this source primary or secondary?" — and get a targeted answer. Citations link back to specific sections of the page. Works on articles, reports, blog posts, government guidance, news sites. First use requires permission — Edge asks if Copilot can access page content. If your org has disabled page-context access, the sidebar works but answers aren't grounded in the page. For prompts that don't need page content (like "help me plan a trip"), the URL, page title, and history are the only things shared.
Best prompts
  • "Summarise this page"
  • "What does this say about [specific topic]?"
  • "What are the key conclusions or recommendations?"
  • "Who is the author and what's their expertise?"
  • "Is this a primary source or does it cite elsewhere?"
  • "What's the single most useful thing on this page?"
Doesn't work on
  • Pages behind logins you're not signed into
  • Paywalled content the browser can't render
  • Very image-heavy pages (text extraction dominates)
  • Pages actively blocked by Purview DLP policy
  • Local files unless opened in Edge
PowerfulDrag PDF into EdgeQ&A like a page
2 · PDF question-answering
Drag any PDF from your desktop, downloads folder, or a SharePoint link into an Edge tab. Edge opens PDFs natively — no Adobe Reader, no extra software. Once the PDF is open, the Copilot sidebar works identically to how it works on web pages. Ask it anything about the document. Critically, for long PDFs (50+ pages) — regulatory documents, technical standards, annual reports, government reviews — narrow, targeted questions produce dramatically better output than broad ones. Don't ask "summarise this 200-page document"; ask "what does section 4 say about compliance obligations for local authorities?" Get the specific answer, then navigate to that section manually to verify.
Perfect for
  • Industry standards (ISO 19650, PAS 2080, BS EN)
  • Regulatory guidance from government bodies
  • Client annual reports (for sector context)
  • Long procurement documents
  • Technical specifications
  • Commissioned research reports
The narrow-question rule
  • Orient first — 3-4 top-level sections?
  • Then narrow — "what does it say about X?"
  • Ask for implications — "what does this mean for [context]?"
  • Check gaps — "what does this NOT tell me?"
  • Always cite the section before relying on it
Copilot ModeOpt-inMulti-tab
3 · Multi-tab reasoning
Enable Copilot Mode via Settings → AI innovations → Copilot Mode (or aka.ms/copilot-mode). Once enabled and after you grant permission, Copilot can access the content of all your open tabs at once. Open four competitor websites and ask "compare these four in a table with columns for target market, core services, pricing, and delivery model" — get a synthesised comparison rather than four separate summaries. Works for: competitive scans, framework comparisons, cross-referencing multiple sources on the same question, assembling itinerary-like outputs from multiple inputs. Visual indicators appear whenever Copilot accesses page content so you always know when multi-tab analysis is happening. You can disable Copilot Mode at any time.
Strongest use cases at Arup
  • Competitive landscape research
  • Comparing regulatory frameworks across jurisdictions
  • Cross-referencing industry reports on the same topic
  • Synthesising multiple client-published sources
  • Building option-comparison tables for proposals
How it works under the hood
  • Extracts text chunks from each open tab
  • Ranks chunks by relevance to your prompt
  • Feeds the highest-value slices to the LLM
  • Returns synthesised output with implicit citations
  • Visual indicators show when tabs are being accessed
Video summariseYouTube + transcriptedSaves hours
4 · Video summarise
Open any video with an available transcript in Edge. YouTube works out of the box. Most major news sites and many conference platforms expose transcripts Copilot can read. Open the sidebar, ask "Summarise this video" or "What are the three main points the speaker makes?" or "Does this video discuss X?" and get an answer derived from the transcript. For video content where the speaker meanders, the information density per minute is often low — Copilot extracts the signal and leaves the filler. Particularly useful for: industry conference recordings, analyst briefing videos, client executives' media appearances, explainer videos on new frameworks. Does not work on videos without accessible transcripts — pure visual content, silent demos, or sites that block transcript extraction.
Especially useful for
  • 60-minute conference keynotes
  • Analyst briefings and industry webinars
  • Client executive media appearances
  • Explainer videos on complex frameworks
  • Training videos for self-paced upskilling
Best question patterns
  • "Three main points the speaker makes?"
  • "Does this video discuss [specific topic]?"
  • "What does the speaker say about [framework]?"
  • "Quote any specific recommendations verbatim"
  • "Is there Q&A — and what was asked?"
Output featureCompose tabTone + format + length
5 · Compose in the sidebar
In the Copilot sidebar, switch from the Chat tab to the Compose tab. Set three controls: Tone (Professional, Casual, Enthusiastic, Informational), Format (paragraph, email, ideas, blog post), Length (short, medium, long). Type a brief instruction — "brief overview of regulatory approach to X" or "three-paragraph email summarising the procurement landscape for Y" — and Copilot generates text using the context of what you've been researching in the session. That continuity matters: the output is grounded in the pages you just read, not generic content from general knowledge. Copy the output, paste into Word or email, polish. For knowledge workers who regularly turn research into written deliverables — which is most of advisory — Compose closes the gap between gathering information and using it.
Ready outputs
  • Briefing note (Professional, paragraph, medium)
  • Stakeholder update (Professional, email, short)
  • Section of a proposal (Professional, paragraph, long)
  • Internal knowledge share (Informational, ideas, medium)
  • Competitive scan summary (Professional, paragraph, medium)
Good hygiene
  • Read a few pages properly before using Compose — it inherits session context
  • Review every claim — Compose can extrapolate beyond sources
  • Treat output as a first draft, not the final version
  • Never paste Compose output into a client deliverable unreviewed
In-place editingRight-clickAny text field
6 · Right-click Rewrite for any field
Select any editable text in any web-based field, right-click → CopilotRewrite. Adjust tone, format, or length just like in Compose. Works in every browser-based compose box: LinkedIn posts, internal portals, web-based email clients, JIRA tickets, SharePoint comments, Confluence pages, procurement portal responses, online forms, third-party chat apps. Replaces the round-trip of copy-to-Word, rewrite-with-Copilot-in-Word, paste-back that most consultants do today. Saves small increments of time thirty times a day — adds up. Particularly valuable for LinkedIn drafting, where advisory consultants often need to share professionally-toned content without fully switching to a writing tool.
Use it on
  • LinkedIn posts before publishing
  • Web-based email replies
  • JIRA / DevOps / Monday comments
  • Confluence or Notion pages
  • Procurement portal responses
  • Browser-based chat platforms
Discipline
  • Never auto-accept — always read before replacing
  • Don't rewrite something you haven't yet drafted
  • Respect the platform's voice — don't over-formalise casual channels
  • For long-form content, switch to Word Copilot instead
Two things Copilot in Edge genuinely cannot do
First: it cannot read what isn't there. Pages behind logins, paywalled content, certain document types, or pages blocked by organisational DLP — Copilot returns vague or generic answers because it doesn't actually have page content. If a summary feels generic, check whether Copilot has page access. Second: summaries compress nuance by design. For anything with legal, financial, or compliance implications, a Copilot summary is a starting point, not a substitute for reading the primary source. Copilot will tell you the key points; it won't necessarily flag the important footnote buried in section 7 that changes the interpretation. Read properly the ones that matter.
03 / THE GREEN SHIELD

Enterprise Data Protection, and why it matters.

The single most important visual check in this whole chapter. Copilot in Edge has two modes — consumer and enterprise — and they look almost identical. One is safe for Arup work. The other quietly isn't. The only difference visible to you is the green shield icon at the top of the sidebar.

🛡 Green shield = Enterprise Data Protection

When you open the Copilot sidebar in Edge, look for the green shield icon at the top of the pane. That icon means you're signed in with your Microsoft Entra work account and Enterprise Data Protection (EDP) is active.

EDP means: prompts and responses are not used to train foundation models. Content is handled under your organisation's compliance policies. Enterprise-grade security protections apply to anything you ask Copilot about.

No green shield means you're in consumer mode — the same privacy regime as using free Copilot Chat on a personal account. Treat it the same way you'd treat ChatGPT on a personal laptop: useful for generic queries, not safe for anything Arup-confidential.

What creates the green shield

The green shield appears when all three of the following are true:

  • You are signed into Edge with a work profile (not a personal Microsoft account)
  • The profile uses a Microsoft Entra ID from your organisation (your Arup account)
  • Your organisation has Copilot in Edge enabled by policy for that account

If any of those isn't met, you're in consumer mode. Signing into Edge with a personal Microsoft account — even on an Arup laptop — does not give you EDP. You have to use your work profile specifically.

The most common failure mode

The most common mistake: consultants who use Edge for personal browsing slip into personal profile for a search, then forget to switch back before asking Copilot about work-related content. The shield is gone and they don't notice. Check the shield every time you ask Copilot anything about Arup, clients, or any sensitive material. If no shield, switch to work profile first; or don't use Copilot at all for that query.

Purview DLP — the other quiet protection

In addition to EDP, Arup's Microsoft Purview Data Loss Prevention policies apply to Copilot in Edge on work profile. If a page is subject to DLP (sensitive client extranet, restricted SharePoint, confidential document portal), Copilot won't be able to summarise it — DLP blocks the access. This is working as designed, even when it's inconvenient. Don't treat DLP blocks as a problem to work around; they're a signal that the content isn't appropriate for Copilot processing anyway.

The "I didn't think it mattered" failure
Every six months at most large professional-services firms, there's an incident where a consultant uses a personal Copilot/ChatGPT with client-confidential material, often unwittingly. The content gets logged. Eventually somebody senior finds out. The consequences range from embarrassing to career-limiting depending on severity. The green shield is the whole defence against that scenario in Edge. Check it deliberately, every session. Not because IT said so — because your career is worth a two-second glance.
04 / PREREQUISITES

Profile, consent, privacy toggles.

Edge Copilot has lower prerequisites than most chapters in this playbook — but the ones it has are structural. Five minutes of setup on day one saves the team from the preventable mistakes.

The five-point setup

1. Confirm the work profile. Open Edge. Click your profile icon (top-right). Make sure your Arup/Entra work profile is active — not "Personal" and not "Guest". If you see multiple profiles, pin the work profile as default. This single step ensures EDP applies.

2. Verify the green shield. Open the Copilot sidebar (Ctrl+Shift+.). Confirm the green shield icon at the top of the pane. If not, something is wrong with profile or policy — don't use Copilot for Arup work until fixed.

3. Grant page-context permission deliberately. On first use, Copilot asks whether it can access page content. For any page where you want page-grounded answers, grant it. You can revoke per-page if a specific page is sensitive. For the research workflows in this chapter, page-context permission is essential — without it, Copilot answers from general knowledge not from what you're reading.

4. Decide on Copilot Mode. Settings → AI innovations → Copilot Mode. Enabling it gives you multi-tab reasoning (Use Case 3) plus the revised New Tab Page layout. The multi-tab capability is genuinely useful for advisory research. The New Tab Page changes are cosmetic and some consultants dislike them — you can enable multi-tab without committing to the interface changes via the granular settings under AI innovations.

5. Review the privacy toggles. Under Edge sidebar → "…" menu → Settings → Privacy:

  • Context clues — controls whether Copilot can use the current webpage, browsing history, or preferences to respond. Keep on for research workflows; toggle off when browsing sensitive material you don't want referenced.
  • Personalization and memory — controls whether Copilot uses previous conversations, Bing/MSN activity, or inferred interests. Personal choice. For most advisory consultants, leaving on improves response quality over time; some prefer off for maximum separation between sessions.

Once these are set, you rarely touch them again. Five minutes up front, the whole team benefits for the rest of the year.

One habit to add to the daily routine
Before asking Copilot anything Arup-related in Edge, glance at the green shield. Build it into the same muscle memory as checking the lock icon on HTTPS sites. Two seconds per session; protects the team from the single most preventable Copilot-related data incident. Newer consultants especially benefit from making this explicit during their first week — it becomes automatic quickly if taught early, and very hard to retrofit if ignored.
05 / USE CASE 1

Scan ten sources in twenty minutes.

The core Edge Copilot workflow. The one that changes how research actually gets done. Open everything in parallel; sidebar-summarise each in 30 seconds; close the useless ones; deep-dive the useful ones. Afternoon becomes half an hour with better output.

~20 minLow effortPage summarise · multiple tabsDaily research
Triage first, read second
Use this when
Any research task where you'd otherwise open a series of sources in sequence. Typical scenarios: scoping a new engagement topic; assembling background for a proposal; researching a competitor or market; due diligence on a client organisation; understanding a regulatory change; building a landscape view of a new sector.
01
Search the topic; open 10-12 top results in tabs
02
Verify green shield, open sidebar
03
Tab by tab: sidebar summary + relevance check
04
Close the irrelevant tabs
05
Deep-dive the 3-4 that matter
# Use the same 3-part pattern on every tab: # 1. The 30-second screen Give me a three-sentence summary of this page. Specifically: what is it, what's the main argument or finding, and is it primary or secondary source? # 2. The relevance check Is this page genuinely relevant to [specific research question — e.g. "how UK local authorities are funding BIM adoption in their estates teams"]? If yes, tell me the two or three most useful things on this page. If not, say so and I'll close it. # 3. The deep-dive (only on the pages that matter) Walk me through this page more carefully. What specific claims does it make, what evidence does it cite, and where does it agree or disagree with [something from one of the other pages]?

The discipline that makes this work

The reason advisory consultants' research tends to sprawl is that they read every page in full because they're worried they'll miss something. The Copilot-assisted triage inverts that: the sidebar tells you in 30 seconds whether the page is worth reading, so you can afford to close the ones that aren't. The anxiety-reducing function of the sidebar matters as much as the time-saving function. You're not skimping — you're letting Copilot identify the signal so your reading time can focus there.

When the session is done

Once you've triaged the 10-12 tabs and deep-dived the 3-4 useful ones, switch to the Compose tab in the sidebar. Ask for a briefing note based on everything you've been reading — Compose inherits session context. See Use Case 5 for the pattern. The whole research-to-briefing loop fits in under 30 minutes.

The output-quality paradox
Consultants who try this for the first time often worry they're missing things. The counter-intuitive finding: triaged research produces better synthesis than sequential reading, not worse. Because you actually engage with the 3-4 sources that matter rather than superficially skimming all 10, your understanding of the important material is deeper. The output quality goes up even though total reading time went down. Trust the method for two weeks. You won't go back.
06 / USE CASE 2

Regulatory PDF deep-dive.

The advisory-team-specific workflow. Long regulatory documents, industry standards, government guidance — 100-300 page PDFs that used to mean an afternoon of reading. Drag into Edge, interrogate with narrow targeted questions, get what you need in minutes.

~10-20 minLow effortPDF in Edge · sidebar Q&ARegulatory & standards
Interrogate the document, don't read it
Use this when
A PDF document has substantive content you need to understand but not necessarily memorise cover-to-cover. Typical scenarios: ISO 19650 for BIM compliance; NEC4 contract requirements; PAS 2080 for carbon management; government strategy documents (DfT, DLUHC, Treasury); client annual reports; local plan and local development frameworks; industry standards; regulator guidance.
01
Drag PDF into Edge — it opens natively
02
Open sidebar, verify green shield
03
Run the 4-stage question sequence
04
Verify any claim you'll act on against the source
05
Save key findings into OneNote or Copilot Notebook
# ORIENT — what's the document? What is this document? Who published it, when, and what's its scope? Give me the three or four top-level sections or chapters so I know how it's structured. # NARROW — what does it say about my specific question? Within this document, what does it say specifically about [specific topic — e.g. "BIM Level 2 compliance requirements for public sector transport infrastructure projects worth over £5m"]? Cite the specific pages or sections. Quote verbatim for any claims I might want to use directly. # IMPLICATIONS — what does this mean for my context? Based on this document, if we're advising a [specific client type — e.g. "UK metropolitan transport authority"] on [topic], what are the three most important implications? What's new or changed from previous guidance? What would signal compliance, and what would signal a gap? # GAP CHECK — what does this NOT tell me? What important questions does this document NOT answer? What would I need to find elsewhere to complete my understanding? Flag anywhere the document is vague, contradicts itself, or defers to other references.

Why the 4-stage sequence matters

Every stage does something the others don't:

  • Orient anchors your mental model — you now know the document's scope and structure, so every subsequent question sits in context.
  • Narrow produces the specific answer you actually came for. This is where the real value is.
  • Implications turns "what the document says" into "what it means for the engagement." Copilot does the inference; you validate.
  • Gap check is the most underused. Knowing what a document doesn't say is often more valuable than knowing what it does — it tells you where to look next.

Always verify before acting

For any claim you're going to rely on in a client deliverable or a commercial decision, navigate to the cited section manually and read it in full. Copilot's summaries are excellent starting points but compress nuance, and for regulatory or legal content, nuance is often the whole point. Treat Copilot as the research assistant that points you at the right paragraph; you're still the one who reads it carefully.

Save the useful findings

Findings that matter should move out of the ephemeral browser session and into something durable. Options:

  • Paste into OneNote — rough capture for your own reference
  • Add the PDF to a Copilot Notebook — if this document is engagement-relevant, it becomes part of the project brain (see Part X)
  • Drop key quotes into the engagement's Word brief — anything you'll cite formally
The deeper advisory-grade use
For senior consultants, the 4-stage sequence is more than a time-saver — it's a reliable method for interrogating unfamiliar subject matter quickly. New client sector? Start with their annual report via this pattern. New regulatory area? Start with the key guidance document. New framework the team needs to apply? Start with the authoritative standard. Orient → Narrow → Implications → Gap-check becomes a generalisable research pattern that works far beyond PDFs — the same sequence works on websites, research reports, and internal documents.
07 / USE CASE 3

Comparative research across tabs.

Edge's unique trick. Open three or four competitor websites, platform pages, or regulatory frameworks in separate tabs. With Copilot Mode on, ask for a synthesised comparison. Get a structured side-by-side rather than four separate summaries — and the table drops straight into a deck.

~5-10 minLow effortMulti-tab · Copilot ModeComparative analysis
Three tabs, one comparison table
Use this when
Multiple sources need to be synthesised against common criteria. Typical scenarios: competitor landscape (compare three consultancies on service focus, target market, delivery model); framework comparison (compare PAS 2080 with the equivalent standards in the US and EU); platform evaluation (compare Power BI, Tableau, Qlik for client recommendation); option analysis (three procurement routes side-by-side); jurisdiction comparison (UK vs. Australian vs. Canadian regulatory regimes).
01
Ensure Copilot Mode is enabled
02
Open the comparison targets — each in its own tab
03
Grant permission when Copilot asks to read tabs
04
Ask for the synthesised comparison
05
Verify any critical cells against the source
Compare the content in my currently open tabs. Produce a comparison table with rows for each [source type — e.g. "consultancy" or "framework" or "platform"] and columns for: - [Dimension 1 — e.g. "Target market"] - [Dimension 2 — e.g. "Core services"] - [Dimension 3 — e.g. "Pricing model or tier"] - [Dimension 4 — e.g. "Delivery approach"] - [Dimension 5 — e.g. "Notable differentiators"] For each cell, cite which tab (by site or title) the information comes from. After the table, add: - **Points of convergence** — where the sources agree - **Points of divergence** — where they differ, and which difference matters most - **Gaps** — anything I'd want to compare on that isn't clearly stated in any source

Three worked Arup comparison scenarios

1. Consultancy competitive scan. Five tabs — Arup, Mott MacDonald, Atkins, Jacobs, WSP. Prompt for comparison on advisory services focus, target client type, digital/BIM capability, sustainability positioning, notable recent engagements. Output drops into an internal competitive analysis deck.

2. BIM framework comparison. Three tabs — UK ISO 19650, PAS 1192 legacy, and a client's own BIM standards document. Prompt for a comparison on common information management principles, differences in how they treat collaboration, evolution over time, and what's most relevant for a transport authority. Output becomes the briefing for the project team.

3. Power Platform vs alternatives. Four tabs — Microsoft Power Platform, ServiceNow, Salesforce, Mendix. Prompt for a comparison on target use cases, enterprise integration, low-code vs pro-code balance, pricing structure, and Arup-relevant deployment patterns. Output feeds a client platform-recommendation document.

Verify before publishing

Multi-tab comparisons look authoritative — which is both their strength and their risk. Always check any cell that makes a material difference in your recommendation against the original source. Copilot occasionally conflates content from adjacent tabs or imports plausible-sounding but incorrect information. For anything going to a client, spot-check at least one row per tab before the comparison leaves your desk.

Watch for the convincingly wrong cell
Multi-tab output is polished by default — clean tables, consistent formatting, professional tone. The polish can make incorrect content look authoritative. The specific failure mode to watch for: Copilot saying "Mott MacDonald specialises in X" when actually it's Jacobs that specialises in X, because two adjacent tabs had similar phrasing. The fix is simple and boring — verify any cell that changes the shape of your recommendation. Most are right; the occasional wrong one can derail an otherwise solid comparison.
08 / USE CASE 4

Video briefings in three minutes.

Conference keynotes, analyst briefings, industry explainers, client executives' media appearances — often 30-60 minutes of video that nobody has time for. If a transcript is available, Copilot reads it and summarises the whole thing in minutes. Information density finally matches your calendar.

~3 minZero effortVideo summariseYouTube + transcripted
Watch in three minutes what took an hour
Use this when
Someone shares a video you'd benefit from knowing about but don't have an hour to watch. Typical scenarios: "you should watch this keynote from ARM Summit"; a client's CEO gives a media interview you should be aware of before the next meeting; a competitor publishes an analyst briefing; an industry body releases a strategic update via video; YouTube has the best explainer of a new framework.
# 1. The orient What is this video? Who's speaking, what's the context (conference, interview, explainer), and what's the three-bullet summary of what they say? # 2. The specific Does the speaker address [specific topic — e.g. "the role of digital twins in infrastructure delivery"]? If yes, quote what they say about it specifically. If no, tell me what topics they do cover instead. # 3. The quotable Are there any specific claims, statistics, or quotable statements the speaker makes that would be useful for me to cite in a briefing or deck? Quote them verbatim and note approximately where in the video (early, middle, late) they appear. # 4. The Q&A (if applicable) Is there a Q&A section? If yes, what were the three most interesting questions asked, and how did the speaker respond?

What videos work and what doesn't

Copilot's video summarise feature reads the transcript — so anything with an available transcript works:

  • YouTube — most videos have auto-generated or uploaded transcripts
  • Major news sites — BBC, FT, Reuters video often has transcripts
  • Conference platforms — many expose transcripts (TED, most professional events)
  • Corporate video hubs — increasingly transcripted for accessibility

Pure visual content (silent demos, workflow recordings without narration) won't work. Nor will videos where the transcript has been deliberately blocked. If Copilot's summary feels vague, check whether the transcript is available — the video platform usually shows a "CC" or transcript option somewhere.

When Compose picks up the thread

After summarising a video, switch to the Compose tab and ask for a briefing note based on the video. The output inherits the context — so you get a prose summary of the video's content with the right framing. Useful for: internal knowledge-share posts, brief-the-team emails, pre-reads for meetings where the video's content is context.

The category advisory consultants underestimate
Advisory teams routinely underestimate how much useful content is now video-first rather than text-first. Keynotes, analyst briefings, CEO fireside chats, explainer videos — a growing share of substantive industry communication happens in video. The old default ("I don't have time for video") meant missing it. With Copilot's video summarise, the time cost of engaging with video drops to the same as reading a page. Start deliberately watching — or rather, summarising — one industry video a day via Edge. You'll surface context competitors who stick to articles-only are missing.
09 / USE CASE 5

Compose the briefing from research.

The payoff step. You've triaged the sources, summarised the PDFs, compared across tabs, absorbed the video. Don't lose it all to a blank Word doc — use Compose in the sidebar to produce the first draft while everything's still loaded in Copilot's session context.

~10 minLow effortCompose tab · session contextResearch → briefing
Compose inherits everything you just read
Use this when
A research session should produce a written output. Typical scenarios: competitive scan → internal brief; regulatory research → team update; sector research → client-facing briefing note; multi-source analysis → pre-read for a meeting; landscape scan → proposal section; industry update → LinkedIn post.
01
Complete the research (Use Cases 1-4)
02
Keep the relevant tabs open — they're still session context
03
Switch Chat → Compose in the sidebar
04
Set tone, format, length; type brief instruction
05
Review, polish in Word, send
# Compose settings: # Tone: Professional · Format: paragraph · Length: medium Based on the sources I've been researching in this session, produce a 400-word internal briefing note for the Arup advisory team. Structure: 1. **Context** — one short paragraph on why this topic matters now 2. **What we found** — three or four short paragraphs, each headed by a theme, synthesising across the sources 3. **Implications for our work** — one paragraph on what this means specifically for advisory engagements with [client type] 4. **Suggested next steps** — three bullets of what we might do next Professional tone throughout. Cite sources inline where you draw specific claims. Don't invent anything not in the sources — if there's a gap, say so.

Compose vs Word's own Copilot — when to use which

Both generate written content grounded in research. The difference:

  • Compose in Edge is for short outputs (email, briefing note, LinkedIn post, meeting pre-read) where the research context is still fresh in the browser. Quick round-trip; no app switching.
  • Copilot in Word (Part VII) is for longer, structured deliverables where you want Arup's template, proper heading styles, track-changes discipline, and the ability to reference up to 20 files via /filename syntax.

The handoff pattern: use Compose to get the first draft out while research is loaded; paste into Word; switch to Word Copilot for proper formatting, structure, and final polish. You get the speed of Compose's session-grounded output and the rigour of Word's template-aware editing.

The "session context" subtlety

Compose's output quality depends on what's actually in Copilot's session memory. If you've been asking questions in Chat about the research, that conversation is context for Compose. If you've closed the tabs, that context fades. Compose works best immediately after a research session — not the next day when the session is gone. If you need to compose from research done earlier, re-open the tabs and run a quick summary of each to re-seed the context, then Compose.

Closing the research-to-output loop
Most advisory research fails at the last step — consultants research for hours, then stare at a blank Word doc for another hour trying to start the write-up. The session-context Compose pattern collapses that gap. The first draft exists before you've switched apps. You're editing a draft, not facing a blank page. That's a different mental game — and a faster one. For junior consultants especially, this is the single highest-leverage habit to build on Edge.
10 / USE CASE 6

Right-click rewrite for any field.

The small feature used thirty times a day. Any editable text field in any web page — right-click, rewrite with Copilot. LinkedIn posts, web-based portals, third-party forms, in-browser chat, procurement responses. Eliminates the copy-to-Word round trip that most consultants still do.

~30 secVery low effortRight-click Copilot RewriteMany times daily
In-place rewrite, no app switch
Use this when
You're drafting text in any browser-based tool and want to sharpen it before publishing. Typical scenarios: LinkedIn post before pressing "Post"; web-based email reply; response in a web-based chat app (Slack-in-browser, Discord); comment on an internal portal (Confluence, Notion, SharePoint comments); procurement portal response; online form submission that needs professional language; JIRA/DevOps ticket comment.

The specific patterns that save the most time

LinkedIn drafting. Advisory consultants often want to share professional content on LinkedIn but don't want to fully switch to a writing tool for a 3-paragraph post. Draft rough in LinkedIn's compose box; select all; right-click → Copilot → Rewrite; adjust for "Professional tone, concise, confident voice." Review and post. Three-minute workflow replaces the 15-minute "draft in Word, polish, paste back" loop.

Procurement portal responses. Many public-sector procurement portals have character-limited free-text fields where the quality of writing matters enormously. Draft in the field; Rewrite for concision within the character limit; the output fits where your original didn't.

Web-based ticket comments. JIRA, Azure DevOps, Monday — any ticketing system where your comment will be read by multiple stakeholders. Quick Rewrite to turn "please look at this it's broken" into "this is blocked by [clear statement of issue]; could you advise on [specific question]?" Small improvement, multiplied across dozens of tickets a week.

In-browser email replies. For consultants using Outlook Web App or other browser-based email clients, the right-click Rewrite works identically to the Draft with Copilot discussed in Part VIII — but without needing to open the full Copilot pane.

Respect the platform's voice

One failure mode to avoid: over-formalising casual channels. If you're in a team Slack channel where the norm is "hey all, quick q" and you Rewrite every message into "Dear colleagues, I have a quick question," you sound tone-deaf. Match the rewrite to the context. Professional portals get professional tone; team chat stays informal.

The compounding daily effect
Right-click Rewrite feels trivial per instance — 30 seconds here, a minute there. The compounding effect across a week is substantial: dozens of small in-browser texts that used to be rougher are now polished with zero app-switching cost. Over a month, this adds up to hundreds of better-written messages, comments, posts, and responses going out of your browser. Individual reader quality of each goes up slightly; collective external perception of your communication quality goes up a lot. Small feature; outsized returns.
11 / DECISION MATRIX

Which tool, when?

Six use cases, six tools, one table.

Your scenarioUse thisSurfaceTime
Quick summary of a web page or articleSidebar page summariseEdge sidebar~30 sec
10-12 sources on a new research topicParallel triage + deep-dive patternMultiple tabs~20 min
100+ page regulatory PDF4-stage PDF deep-divePDF in Edge~15 min
Compare 3-4 websites or frameworksMulti-tab Copilot ModeCopilot Mode~5 min
60-minute conference keynote on YouTubeVideo summariseEdge sidebar~3 min
Turn research into a 400-word briefing noteCompose tab with session contextCompose~5-10 min
LinkedIn post needs professional polishRight-click RewriteLinkedIn compose~30 sec
Procurement portal free-text responseRight-click Rewrite (for concision)Portal field~1 min
Find quotable claims in a long reportPDF deep-dive · verbatim quote promptPDF in Edge~2 min
Quick sense-check: is this page relevant?Sidebar · relevance check promptSingle tab~30 sec
Client annual report before a meetingPDF deep-dive + Compose briefPDF in Edge~20 min
Cross-reference multiple research sourcesMulti-tab comparison + verifyCopilot Mode~10 min
12 / DO'S & DON'TS

Common failures — and their fixes.

Patterns from training advisory teams on Copilot in Edge. Almost every bad outcome maps to one of these.

Do
  • Check the green shield every session. Two seconds; protects against the single most preventable data incident.
  • Open 10-12 tabs in parallel for research, triage with sidebar summaries, deep-dive only the 3-4 that matter.
  • Use the 4-stage PDF sequence — orient, narrow, implications, gap-check — on every substantive document.
  • Ask narrow, targeted questions of long PDFs. Broad prompts produce generic summaries; specific prompts produce usable output.
  • Enable Copilot Mode for the multi-tab reasoning capability. Worth the opt-in even if you dislike the New Tab Page changes.
  • Use Compose immediately after research — session context is live. The first draft exists before you've switched apps.
  • Right-click Rewrite in any browser field instead of copy-to-Word-and-back. Save small increments many times daily.
  • Verify any claim you'll act on against the source. Copilot summaries are starting points, not final words.
Don't
  • Use Copilot in Edge without a green shield for any Arup-related content. Consumer mode is not safe for work data.
  • Sign in with a personal Microsoft account to Edge on your work laptop and expect EDP. Work profile + Entra ID only.
  • Ask one broad prompt of a 300-page PDF. The output is too general to be useful. Narrow and target.
  • Trust a multi-tab comparison table without spot-checking. Polished output can be convincingly wrong on specific cells.
  • Treat a Copilot summary as a substitute for reading. For legal, financial, or compliance content, read the source.
  • Compose from a research session that's already ended. Session context has faded; the output will be generic.
  • Right-click-Rewrite everything. Over-formalising a casual team chat sounds tone-deaf; respect platform norms.
  • Forget that some pages are invisible to Copilot. Behind-login, paywalled, DLP-blocked. Generic answers = check for this.
The unifying mental model
Think of Copilot in Edge as three roles, not six features. Reading assistant — summarises pages, PDFs, videos so you engage with the signal not the noise (page summarise, PDF Q&A, video summarise). Research synthesiser — reads across tabs and produces comparisons (multi-tab Copilot Mode). In-browser writing assistant — turns research into briefings and polishes anything you type in a browser field (Compose, right-click Rewrite). Every specific feature fits one role. The discipline: check the green shield, match the role to the task, and remember that Copilot tells you the key points but won't flag the footnote in section 7 that changes the interpretation — for anything that matters, read the source.
Playbook implication
Edge is the lowest-barrier Copilot surface in the stack — every page you visit is already a Copilot surface, no setup required. For advisory teams who spend meaningful time in research, the compounding return is among the largest in this playbook. Teach the green-shield discipline first, because everything downstream depends on it. Then teach the parallel-tabs triage pattern — that's the single habit change that collapses afternoons into minutes.
Series Complete
Eleven reports. One playbook.
Part XI closes the research series. The Arup advisory team now has dedicated, full-depth workflow research for every major Microsoft 365 app used in the working day — from PowerPoint to Edge, including the agent layer and competitive landscape. Ready for integration into the playbook SPA.