Yes, the Copilot Researcher Agent, once focused purely on gathering and summarising information, can now take action on your device through a capability called Computer Use. This provides secure interaction with both public and gated web content through a virtual computer which allows human and Copilot control. It requires a Microsoft 365 Copilot license, supports advanced content creation. It can be disabled by IT admins, but comes enabled by default.
This represents part of the next evolution of how we think about and use AI in the workplace and our personal lives.
What Is Computer Use?
This enhancement to Researcher should help users uncover deeper insights, take action, and generate richer reports grounded in both their work data and the web even with gated content that requires the user to take over the browser or to authenticate to content, accept CAPTAs and more.
Computer Use allows Copilot to go beyond simply telling you what it finds. It can now:
Open docs and web-pages directly and read, navigate web-sites and docs (including PDFs).
Navigate menus, click buttons, and move through dialogue boxes.
Execute tasks such as generating a charts, drafting an email, or applying formatting.
It does this in the context of a Microsoft hosted secure virtual PC and does not take over your personal device.
How This Differs from the Current Researcher Agent
The Researcher Agent as we’ve known it has been a powerful tool for finding and contextualising information. It queries internal and external sources, summarises results, and provides references. But until now, it stopped short of doing anything with that information other than the relatively limited for sting capability that it provides ready for your cut and paste skills.
This is where the new Computer Use tools come in by adding the following differences.
Researcher Agent (today): Finds, summarises, and presents knowledge.
Researcher Agent with Computer Use: Acts on that knowledge by operating applications and completing tasks, this mess it will be able to leverage the full power of desktops apps to make the output more polished. It can also access secured/gated resources by opening the website or resource in a virtual secure browser and passing control back to you to sign-in with your credentials to access such content.
This allows (as you can see in my example below), Researcher to actually browse the web, reason over the pages it finds and conduct research more efficiently than just using it’s LLMs and AI search mode. The result “should” be a much more fluid, accurate and representative piece of research.
Where Researcher was your simply your analyst, Reseacher with Computer Use becomes more of a full-assistant – able to take the next step and apply the insights directly into your workflow.
Why This makes a difference
This (and as it evolves) has the potential to make. A big difference in the way output is produced as it can leverage it’s research inside the core apps you would typically use when brining information together such as Word or Excel.
As such the implications are significant:
Reduced friction: Fewer clicks, fewer context switches, less manual effort.
Consistency: Routine tasks (like formatting reports or applying compliance templates) are executed the same way every time.
Accessibility: Natural language becomes the new interface, lowering barriers for all users.
Extends the range of access Researcher has which means users can now generate rich artifacts such as presentations, spreadsheets, and applications using advanced code generation.
This is really about amplifying the output and cutting out more steps, with Copilot handling more of the set the mechanics once the output is created.
Guardrails and Trust
Many will have yet more concerns about what AI can do and how much control it has.
Microsoft has built Computer Use with transparency and control in mind and bear in mind it is NOT talking over actual control of your device. As such:
It only acts when explicitly instructed (you need to enable computer use).
It shows you what it’s doing the whole time with total transparency
It respects organisational policies and permissions and can’t do anything or access anything you cannot already access.
Passes control back to you if its need you to sign-in to access secure or gates resources
You have control over what Researcher can access with regards web data and work data (based on your access rights naturally).
User credentials are never transfered to or from the sandbox environment, and all intermediate files are automatically deleted when sessions end. This ensures that this AI automation does not come at the cost of compliance or user trust. You are always in control.
The diagram below, depicts how it works.
Researcher Agent with Computer Mode – Secure data orchestration to Sandbox Environment. (c) Microsoft.
The future...
This is part of a broader trend: AI agents are evolving from passive Copilots to active collaborators. Workflows are becoming conversational, not procedural and the tools start to fade into the background, and outcomes come to the foreground.
For leaders, strategists, and IT professionals, the challenge now is to rethink processes, training, and measurement in a world where AI doesn’t just inform work it does it with and for us.
This latest addition of Computer Use to the Researcher Agent is a signal of what’s to come. The pace of change and evolution of these tools is rapid. The future of AI at work continues to punch boundaries and evolve from just finding and researching towards doing stuff for us….
Windows Insiders in the Dev and Beta channels can start testing a new Copilot search experience which is available through the Windows Search bar.
To get started go to Settings > Personalisation > Taskbar > Ask Copilot to enable the experience. You can also manage whether the Copilot app launches automatically at sign-in using the “Auto start on log in” toggle in the Copilot app settings.
This is an opt-in experience, but once enabled gives you one-click access to Copilot Vision and Voice, so you can use what ever interaction style works best for – text, voice, or guided support with Copilot Vision.
As you type, results appear and are updated instantly, making it easier than ever to find what you are looking for.
Let’s talk about one of my biggest pet peeves: the agenda-less meeting invite.
You know the type. A calendar ping lands in your inbox with a vague title like “Catch-up” or “Project Sync,” zero context, and no prep materials. You’re left guessing: Is this strategic? Tactical? A therapy session? Should I bring data, decisions, or just make a coffee, sit back and relax!?
In a world where time is our most precious resource, this kind of ambiguity isn’t just annoying – it’s inefficient. And now, there’s no excuse for it.
Copilot: Your Agenda Architect
Microsoft Copilot has quietly transformed how we prepare for meetings. It doesn’t just help – it proactively builds structure into your invites.
Copilot Agenda Assistant 🫡
Here’s how it works:
🧠 Context-aware agendas: When you create a meeting in Outlook, Copilot can draft an agenda based on the meeting title, attendees, and your input. It pulls from your Microsoft 365 work graph – emails, chats, previous meetings — to suggest relevant topics.
✍️ Editable and iterative: You’re not stuck with the first draft. You can tweak, refine, or ask Copilot to revise it until it reflects exactly what you need.
🔍 Pre-reads and prep prompts: Copilot now surfaces key insights directly in the meeting form. It can help you locate pre-reads, clarify the meeting’s intended outcome, and even suggest follow-up questions.
👥 Supports all meeting types: Whether it’s a 1:1, a team sync, or a cross-functional war room, Copilot’s meeting prep experience adapts accordingly.
Why This Matters.
We have a been sent meetings with nothing but a title. We’ve all sat through these types of meetings that felt like a waste of time. The truth is, most meetings aren’t inherently bad – they’re just underprepared. Even if someone has called you or IM’d you about it and sent a meeting a day later, a clear agenda is still important, sets expectations, aligns participants, and drives outcomes. It’s the difference between a productive sprint and a meandering chat.
Plus…. With AI tools like Facilitator which can help you manage the in meeting experience, agendas also help here too!
So next time you send a meeting invite, let Copilot help you do it properly. Because in 2025, “no agenda” isn’t just a faux pas — it’s a missed opportunity.
Microsoft is expanding its Copilot Frontier Programme with two powerful new agents. These are the App Builder and Workflows Agents.
These put “app creation” and automation directly into the hands of everyday users, with zero coding needed just an idea and an ask. These new agents are designed to further democratise innovation across every person in every organisations, making it possible to build “apps” and streamline processes using nothing more than natural language.
They are rolling out in the US now and will come to UK, Canada and the other regions over the next week or so.
I’ll add a demo to this blog soon!
What are the App Builder and Workflows Agents?
Firstly, these are new, in preview for Frontier (early adopters) and may change. They are not designed to replace Power Apps or Copilot Studio but more about adding value to info workers and non developers. Here is the new agents, which you can get by going to the main Copilot page, agents and get more agents.
App Builder: A no-code agent that enables anyone to design and deploy lightweight apps in minutes. It can generate a Microsoft Lists backend if needed and is grounded in Microsoft 365 content like Word, Excel, and Teams. These are not full blown apps that can hook into enterprise data or anything but create simple to use, functional and simple agents for things like data input, collection and look up.
Image (c) Microsoft
Workflows: An automation agent that turns everyday requests into flows across Outlook, Teams, SharePoint, Planner, and more – without needing Power Automate expertise. Again these are quite simple, but great for simple automation needs when you know what you want to do but don’t have time or want to learn / use Power Automate.
Image (c) Microsoft
Both these new agents are integrated into the Copilot Studio lite experience, ensuring they inherit Microsoft 365’s enterprise-grade security, compliance, and governance.
How Do They Work?
These agents work like other agents but are specific functional agents. They work by:
Using Natural Language Prompts: users can simply describe what they need. For example “Build me a dashboard to track campaign milestones” or “Send a Teams reminder every Friday at 3pm” – and Copilot translates that into a working app or automated flow.
Multi-turn Editing: Once the agent is created it can be modified, updated, refined with additional interactions without having to starting from scratch.
Ensuring Seamless Integration: Outputs are instantly shareable, just like a document link, and respect existing permissions and governance.
These agents lower the barrier to innovation and help spur on what is possible. Instead of relying on IT or developers, any employee can now build tools that fit their needs whether that’s a lightweight app for tracking, or a workflow that eliminates repetitive admin. Since they are built into Microsoft 365, they inherit the same security, compliance, and governance as the rest of the platform.
App Builder Use examples
Create a product launch dashboard to track milestones and assign tasks.
Build a calculator app for quick cost estimates, grounded in Excel data.
Generate interactive lists for project tracking, with Microsoft Lists as the backend.
Workflows agent use examples
Automate weekly Teams updates with deadlines pulled from Planner.
Set up email reminders for approval deadlines.
Manage calendar scheduling by automatically blocking time for recurring tasks.
Current Limitations
Frontier Programme Only: Currently limited to participants in the Copilot Frontier Programme and need to be “deployed by IT admin” initially
Language Support: Available in English only.
Controls: Access depends on Microsoft 365 app store settings and admin policies.
Scope: Aimed at designing lightweight apps and workflows; complex scenarios will still require Copilot Studio or Power Platform.
PerformanceThrottling: Heavy usage may trigger throttling.
Deploying the App Agent and Workflow Agent
These new agents are currently only available for organisations enrolled in the Copilot “Frontier Programme”.To access the agent, you need to go to the M365 Copilot app (or https://m365.cloud.microsoft/chat) and go to Agents. From there you should be able to see the new Agents as shown below.
NOTE: If you can’t see these new agents, you’ll need to chat to your friendly IT team as they may need to enable / deploy these agents whilst they are still in preview state. Again these are only available for organisations enrolled in the Copilot “Frontier Programme”.
Final Thoughts
The App Builder and Workflows agents represents another step forward in Microsoft’s vision of empowering everyone to innovate with AI.
Whilst these agents are far from a replacement for full-scale development or automation platforms, they provide a fast, accessible way to solve everyday problems. For organisations in the Copilot Frontier Programme, these agents are a glimpse into a future where building apps and automations is as easy as describing what you want.
In a live YouTube stream on 24th October, Microsoft unveiled a wave of new consumer features for Copilot (dubbed fall update) – headlined by the official debut of Mico, a new visual character (avatar) designed to give Copilot a voice (and face).
Mico has been in testing for a while, but from today it’s rolling out (USA first) by default in voice interactions. If you prefer the simpler “bouncing orb” interface, you’ll still have the option to switch it off.
The update today also unveiled updates to Copilot Voice including a feature called “real talk,” which is designed to allow Copilot to push back and challenge assumptions made by the humans interacting with it. This is a first on the market for AI chat. This is designed to ensure Copilot remains accurate rather than just trying to please it’s human counterpart.
First Clippy & Cortana, now Mico
It’s impossible not to draw comparisons here. Clippy – now more than 30 years old – is still remembered (fondly or otherwise) as Microsoft’s first attempt at a digital assistant with personality which lived inside Office. Then we had Cortana, which launched with Windows 10 (and for a short time was poised to compete with Amazon Alexa and even had its own “inkoke” speakers. Cortana promised much but never really landed with consumers users, eventually being retired from Windows 10 and 11 just a couple of years back!
Copilot of course has been around for a couple of years now, in a consumer based version and also an enterprise version known as Microsoft 365 Copilot. Copilot has also had a “voice” for a while but now with Mica it is getting a lot more natural and is also betting a face too, after a few months of testing with Insiders.
Does AI need a voice and a face?
So why is Mico is becoming the face of Copilot? The way it is explained and was showcased today promised a different approach to what we have seen before. There is some physc behind it too in that humans are far more. Likely to engage with something artificial if it appears to us in a way we can be familiar and where expressions can come across in voice voice tone and facial expression.
Mica is about giving Copilot an Identity…
Of course Copilot is true AI (very different to the earlier assistants that were were more trigger based).
Back in July, Microsoft AI CEO Mustafa Suleyman hinted that Copilot would evolve into something with a “permanent identity… a presence… a room that it lives in… and it will age.” Mico is the first visible step in that direction.
One of the other things that starts to bring these assistants more to life is memory. Memory allows Copilot to recall facts about us, what we do, where we work and our preferences to how it responds. It can then adapts and that makes it more contextual, more personal, and (hopefully) more useful and that’s where the Mico face (which will also adapt) comes in….
This optional visual presence listens, reacts, and even changes colors to reflect your interactions, making voice conversations feel more natural. Mico shows support through animation and expressions, creating a friendly and engaging experience.
Microsoft
Mica is in essence the personality and personalisation that makes Copilot yours and not just “the same” as the other assistants!
Mica can chat to your friends too..
On of the other annoucements yesterday was group chat mode. Yes…
Called Copilot Groups, you can now invite your friends, family etc to join a Copilot chat too. This means you can be planning a trip then invite others to join the chat with Mica in this mix too. All chatting together with Mica about your trip..
Copilot Group Chat
You can take any chat and share it via a link, email, what’s app, Insta, Snapchat.
To conclude
These new things are not just about features, they are about about brand and identity. Microsoft wants Copilot to feel like a companion, not just a AI chatbot.
Mica is a bold move in an attempt to really make Copilot more human and personal. Copilot is very capable and AI is advancing quickly. The main challenge Microsoft faces is the same as they always do… Getting Copilot / Mica into the hands of consumers and to drive adoption and awareness
Enterprise / commercial users know Copilot but many consumers, teenagers and adults not in tech don’t… They flock to ChatGPT when they could get far far far more value with Copilot.. They just don’t know it!
Q&A
I heard Mico can look like Clippy? It can, tap Mico repeatedly and you’ll unlock a nostalgic surprise – Clippy, the iconic (and occasionally cheeky) paperclip assistant from Microsoft Office’s past, makes a cameo appearance.
What’s Copilot Group Chat all about? Copilot now supports real-time group chats with up to 32 participants. It can summarise conversations, suggest options and add up votes, split tasks and track decisions which is good for group chats or classroom work or projects with bigger groups.
What does “Real Talk” mode do? “Real Talk” is Copilot’s honesty engine. When enabled, it gently challenges misinformation or flawed assumptions during chats – especially useful in sensitive or personal discussions. It’s designed to keep conversations grounded, respectful, and genuinely helpful.
Agent Mode in Excel is a new “preview” feature Excel (online) for Microsoft Copilot Subscribers (Microsoft 365 Commercial, Personal, Family and Premium) that enables users to build and edit workbooks along side Copilot.
When you’re updating budgets, creating financial models, or analysing data, Agent Mode uses Excel’s most powerful tools like tables, charts, PivotTables, and formulas to help you get the job done. As part of Microsoft’s Frontier program, Agent Mode gives you early access to cutting-edge AI capabilities.
What I love most is you don’t needExcel skills at all (other than knowing how to enable this feature) which you need to do before you can use it!
The new “Agent Mode” transforms Copilot from a one-shot assistant into a collaborative AI partner capable of orchestrating multi-step tasks across your office apps.
Microsoft.
Agent Mode updates your workbook using Excel’s built-in features, so your content stays editable and synced with the latest changes. It works with you and you can see it’s reasoning thinking and what it’s doing in real time!
Enabling the Agent Mode in Excel
Currently, to use Agent Mode in Excel, you need to be using Excel on the Web (and must have a paid Copilot License). To use the agent, you then need to head to “Add-ins”, search form, and then add the “Excel Labs” as shown below.
Adding the “preview” for Excel Labs in Excel on the Web.
The first time you do then, you will be presented with the following message. I’d suggest you have a read and accept. You can then open the agent to get started! You will see there are two options for use – Agent Mode and an Advanced Formula Environment.
Using Agent Mode in Excel
Select the Excel Labs button
In the Excel Labs task pane, choose Agent mode.
Start working with the Agent to create your project.
An example, Microsoft provide is to “Build a loan calculator that computes monthly payments based on user inputs for loan amount, annual interest rate, and term in years. Generate a schedule showing month, payment, principal, interest, and remaining balance. Present the results in a clear, formatted table“. You can see this in the prompt to the left (you can cut and paste this if you like!).
Watch Agent Mode in Excel in action.
I have built a video to showcase the example above which you can watch at your leisure. You’ll see how I work with it, tweak the calculator and add more functionality as I go… This to be mirrors how most people work. Build, check, reflect, enhance…
Excel Agent in action
How is Agent Mode Different to Copilot Chat in Excel?
Agent Mode is really designed to work for more complex, multi-step tasks such as reshaping data, merging sheets, or creating reports with multiple elements. For simpler, one-step tasks like adding a chart or PivotTable, talking about data, help with formulas etc can be quicker.
Because of the way Agent Mode works, it also takes a little longer to provide an initial response and refine it, particularly for more complex requests. But… It’s leaps ahead of what you can do in Copilot Chat alone..
Remember, for more conversational assistance or tasks that don’t make lots of modifications to your workbook, Copilot Chat is a much more suitable option.
Agent Mode in Excel: Availablility and Limitations
Availability: At time of writing (October 2025), Agent Mode in Excel is available on Excel for the web via the Excel Labs add-in in English. Support for other platforms, and additional languages will be included in the future.
It’s still AI.. You need to work with, but what I love is you can now build quite complex models, calculators or calculations with no code, no formatting experience, no charting skills…
It is still in preview, expect it to get perfected.
This week was Microsoft’s third annual OneDrive digital event (October 8th, 2025), where their key message was that OneDrive is much much more than “just” file storage.
Whether you are looking at this as a consumer or information workers, the theme this year was “Intelligence in every click, inspiration in every memory” .
Yes OneDrive is getting a true AI overhaul the event was about showcasing what is coming (soon) revealing and demoing how Copilot and AI are being woven into the very fabric of OneDrive, transforming it into both a personal and professional productivity and imaging hub.
Perhaps the biggest thing for at the event was the Hero Link… Read on!
The 3rd Annual OneDrive Event
The virtual event itself was led by many familiar with the keynote from Jeff Teper (President, Microsoft 365 Collaboration Apps & Platforms) and Jason Moore (VP of OneDrive Product Management).
The core event was 25-minuts long and included an hour ish live AMA (Ask Microsoft Anything) with the OneDrive engineers and product lead.
Copilot is being deeply embedded across OneDrive consumer and OneDrive for Business and we will see Copilot now natively integrated into OneDrive across web, desktop (coming soon), and mobile. This includes:
Core OneDrive changes and innovation from everywhere.
Natural language file search: you can ask direct from OneDrive “show me the Q3 financials with margin analysis” and Copilot surfaces the right file instantly.
File summarisation and insights: With a single click or prompt, Copilot can summarise long documents, extract key points, and even suggest next steps.
Actionable collaboration: Instead of static files, OneDrive becomes more of a springboard into actionable steps. It can can draft responses, prep presentations, or analyse data directly from the file context in OneDrive.
Smarter Photos Experiencefor all
Smarter Photos Experience for personal users with huge updates to ‘rival‘ Google Photos especially around memories and search.
AI-powered photo organisation: new AI powered auto tagging, grouping, and contextual search. For example simply ask “show me photos from our Isle of Wight trip last summer”.
Memory highlights: Curated collections that feel more like a story than a folder, presented a blood and crisp new way with fluid animation and scrolling.
As I said, this is Microsoft’s answer to Google Photos, but with enhanced “enterprise-grade” compliance and privacy baked in.
OneDrive as a Hub for content.
OneDrive as a Hub for Work + Life The tagline here is about positioning OneDrive as the “always ready” hub for both professional and personal content.
Work content becomes more discoverable and actionable without having to switch context.
Personal content (like photos) becomes more meaningful and shareable and ups the standard for AI management and organisation.
Photos Agent: allows users to use Copilot to find all your best shots from anytime anywhere or anytime and Copilot will help find the best photos. Soon it will also help build albums too. It is coming soon to Microsoft 365 Copilot Windows and Web experience for Microsoft 365 Premium subscribers.
IT leaders retain control, with governance and compliance intact along with powerful new sharing controls known as the hero link.
The new Hero Link.
This for me was this big one. Microsoft say that after a decade of feedback and innovation, the biggest update to sharing in Microsoft 365 is here – the hero link!
Having seen this at MVP Summit last year at the early testing phases, I am uber excited by this.
This marks a major evolution in file sharing within Microsoft 365, designed to simplify and streamline collaboration.
Single, primary URL: identical to the address bar link, it governs access to shared content without multiple links. This means users can update permissions (e.g., expand access to their organisation) without needing to resend or regenerate links, significantly reducing the risk of “access denied” errors. It means you can change permissions without resharing links.
Copilot summaries when sharing: enhances this experience, ensuring recipients open files with immediate context. This update reflects over a decade of user feedback and aims to make sharing more predictable, secure, and efficient.
Simple for sharers and collaborators: With the hero link, content sharers distribute a single, permanent URL to all stakeholders, adjusting access levels as needed without worrying about outdated links. This not only improves continuity and reduces complexity but also supports seamless collaboration across teams, especially in dynamic environments where content and contributors frequently change.
New OneDrive Hero Link
Timeline and Availability
Many of the new features showcased are already in preview for Microsoft 365 Copilot users, with general availability expected in early 2026.
The new Photos experience updates will start rolling out to consumer (personal) OneDrive accounts over the next few months.
New OneDrive native app for Windows in preview now for Windows Insiders using Copilot Plus PCs.
My Take
Who would have thought a few years ago that OneDrive would have its own special annual event!
This year (the third year) it wasn’t just about new features it was about deepening the role of OneDrive as the connective fabric that binds Microsoft 365 together. Personally it think the focus was more on consumer to compete in the Google Photo Space with AI packaging features powered by Copilot (which ties in nicely with the new Microsoft 365 Premium SKUs for home, personal and family users.
For corporate IT, the message was for around OneDrive becoming the AI-first content hub (like they have done with SharePoint (after all it’s the same plafrom). With Copilot in OneDrive there are less clicks, it feels more native rather than an after thought and positions their AI in more places.
AI tools being used in the workplace is no longer a question of if but how and what. The question is what if you could allow this in a safe and controlled way without compromising security and compliance and without leaking copirate data.?
What is BYO-Copilot to Work?
Whether your organisation invests and has deployed AI tools for employees or not, your people are already experimenting or using daily AI tools to boost their productivity, search and get things done at home but also at work, often outside the guardrails of IT. This is bad for IT and organisational security and privacy of a few levels.
Free AI tools such as ChatGPT, Claude etc that are consumer products do not have the data protection in place that organisations need to ensure corporate data is not used to train the AI models.
When we use free tools, the user “is the product” and many employees (and some organisations) simply don’t know the risk of using unsanctioned AI tools especially when with corporate data.
Microsoft introduces “bring your own Copilot to work”
Microsoft’s latest announcement delivers a way to address (some of) these challenges by enabling a secure, and safe way employees who don’t have a Microsoft 365 Copilot license at work to use their personal Copilot from their personal Microsoft 365 subscriptions (Personal, Family, or Premium) directly at work and with work documents – with enterprise-grade dataprotections organisations demand and expect.
This “bring your own Copilot” (BYO-Copilot) model provides a safe way (if permitted) for individuals to use AI at work without compromising organisational security, while giving IT the levers to stay firmly in control.
So how does it work?
How does Bring Your Own Copilot Work?
It’s simple really..
Employees can sign into so Microsoft 365 apps with both work and personal accounts (similar to work and personal profiles in Edge).
All Copilot features from a the employees personal subscription can be used on work files – even if the employee’s work account doesn’t have a Copilot licence.
Microsoft’s Enterprise data protection remains intact since Copilot only works within the permissions of the user’s work identity so identity, data protection and governance remains in tact.
IT remains in control. Admins can enable or disable this capability via policy, and all Copilot interactions are auditable.
In short: BYO-Copilot provides a safe and secure way for employees to get access to Copilot, whilst IT keeps governance, and organisational data protected.
This provides a much better method than just saying no. This of course needs the user to be using Copilot and not other non Microsoft AI tools.
Empowering employees
From an employee’s perspective, the process is straightforward (they will of course need a personal Microsoft 365 subscription with Copilot) first.
Sign into their work Microsoft 365 apps with both business and personal accounts.
Open Word, Excel, or another Microsoft 365 app.
Use the account switcher to add your personal Microsoft 365 account alongside your work account.
Open a work file from Word, PowerPoint, Excel etc which could be a document stored in OneDrive for Business or SharePoint that they have access too.
Invoke Copilot and use it as they normally would – for example, ask it to summarise a document, draft a response, or analyse some excel data.
Copilot will of course only work with the content you can access through your work identity,but Microsoft will not use the data to train their models, learn or share anything with the wider Microsoft environment. Organisations remain protected by Microsoft’s Responsible AI and Enterprise Data Protection.
Limitations of BYO Copilot at work?
It is worth noting that this is not the full Microsoft 365 Copilot so their are limitations.
The employees personal Copilot subscription only works on the open document or explicitly referenced file.
Broader capabilities (like querying across multiple files or your organisational data) still require a corporate Microsoft 365 Copilot licence.
How can organisations enable or block BYO Copilot?
Microsoft has of course designed this capability with IT control at the centre and no need for additional tools or controls. Here are the key considerations:
Policy Control
A tenant-level setting called “Multiple account access to Copilot for work documents” determines whether personal Copilot can be used on work files.
IT can enable or disable this capability for all users or specific groups.
Identity and Permissions
Copilot always respects the user’s work account permissions and data, identity and compliance settings on your tenant.
The employees personal account provides the Copilot entitlement, but it does not gain access to organisational data. You still control this as always.
Data Protection
All interactions remain within the Microsoft 365 service boundary.
Prompts and responses are encrypted, governed by existing compliance commitments, and never used to train the underlying AI models or shared for advertising etc.
Auditing and Monitoring
Copilot actions are logged and auditable, just like other user activities and can be surfaced via SEIM, audit logs and the Copilot Control System.
Other settings such as retention policies and compliance tools (such as Purview and DLP) apply to Copilot interactions.
Governance of Web Access
If Copilot’s web search grounding is disabled in your tenant, that restriction still applies – even when using a personal subscription.
Why
For IT leaders, this is a pragmatic response to the reality of AI adoption. Employees want (and often demand) to use AI, and many already have personal subscriptions to Microsoft Copilot at home. Rather than pushing this activity into the shadows, Microsoft has created a safe and protected way for employees to use their own “Microsoft” AI tools that:
Empowers employees to use AI productively.
Keeps IT in control with clear policy levers.
Protects organisational data with enterprise-grade safeguards.
Ensures IT are in the know, providing IT teams the ability to safely allow shadow IT on their copirate environment.
Of course, IT should take the time to review their policies, communicate the boundaries, and decide whether to enable or restrict BYO-Copilot in their environment.
What about other AI Tools like ChatGPT personal and Perplexity?
No (well not yet anyway). Since Microsoft have control over the Copilot experience across commercial, enterprise and personal/family experiences this is something they can do whilst guaranteeing nothing compromises or impacts their existing security and data goverance.
Whilst this won’t stop a poorly configured and governed Microsoft 365 environment allowing third party apps and AI tools on their network, it provides a safe way to empower many more unlicensed Microsoft 365 Copilot users to bring their Copilot to work without organisational expense.
Organisations can then use existing controls to block scan and block the use of unsanctioned AI tools and give employees a viable “self funded” option to BYO Copilot AI to work.
What do you think of BYO Copilot?
Personally I think this is great. Unless your controls are strong, personal AI is already at coming to work, whether sanctioned or not.
With BYO-Copilot, at least IT can provide a way of safely allowing it with the right guardrails in place.
Of course it’s also a clever approach as it gets more people (potentially) paying for Copilot themselves and then convincing their work to buy them a Microsoft 365 Copilot license.
Microsoft Copilot development just doesn’t sleep… This time they have just announced “agent mode” which they claim could be game changer in the way we (humans) work with AI agents (Copilot). Called “Agent Mode” this latest update marks is not just about new features, but a significant shift in how we interact with Office apps through Copilot.
Agent Mode in Excel
What is Agent mode?
Agent Mode is Microsoft’s answer to the growing demand for intelligent, iterative workflows without needing to craft lengthy prompts. Agent Mode brings agentic reasoning into Excel and Word, (others will follow), allowing users to work along side Copilot through multi-step tasks ranging from data analysis to document creation – with a level of depth and refinement that feels like working alongside an expert.
“In the same way vibe coding has transformed software development, the latest reasoning models in Copilot unlock agentic productivity for Office artefacts.”
Sumit Chauhan |CVP |Microsoft Product Group
These are both application and context aware. As an example:
In Excel, Agent Mode “speaks spreadsheet” language. Whether you need to build financial models, loan calculators, resource calculators or budgets, Agent Mode in Excel means Copilot now understands the nuances of formulas, formatting, and validation. Rather than just generating outputs, it can evaluate your work, suggest fixes, and works with you until you get the result you need.
In Word, Agent Mode will be able to transform writing into a dialogue. Users can prompt, Copilot drafts, user can then asks clarifying questions, and Copilot will refines the content with native styling and formatting. Microsoft say this is vibe writing in action — fast, fluid, and focused.
Chat first creation…
Then, there is the new “Office Agent”, which will live inside Copilot chat. This is designed for when discussions start in a Copilot Chat, rather from within document or spreadsheet. In this context, the Office Agent will have the ability to create “proper” documents directly from your chat, using deep reasoning and live previews to guide the process and creation. These will be powered by Anthropic models and not OpenAI.
Financial Analysis Prompt: “Create a financial monthly close report for a bike shop business, including a breakdown of product lines across VTB, VTF, sequential, and year-over-year growth. Use standard financial formatting and best practices.”
Loan Calculator Prompt: “Build a loan calculator that computes monthly payments based on user inputs for loan amount, annual interest rate, and term in years. Generate a schedule showing month, payment, principal, interest, and remaining balance. Present the results in a clear, formatted table.”
Monthly Report Update Prompt: “Help me update this monthly report for September. Update the data table with the latest numbers from the /Sept Data Pull email. Summarise the key highlights including insights compared to last month’s /August monthly report.doc.”
In Word
Project Update Prompt: “Update the executive summary for clarity, bold all key findings, and insert a bulleted list of next steps based on the /Project update meeting. Make sure to add a conclusion“.
Document Style Prompt: “Can you clean up this document? Title case for section headers, branding updates per the ‘/Latest brand guidelines’ email, and italicize all external partner mentions. Feel free to ask if you need help identifying partners or guidelines.”
In Powerpoint (coming later)
Interestingly, Microsoft say that Copilot can now (finally) create good presentations in PowerPoint!
“PowerPoint is one of the most used tools for creating presentations, but over the last two years, AI (Copilot) has often fallen short when creating slides. Office Agent changes that. Office Agent creates tasteful, well-structured PowerPoint decks and well-researched Word documents. ”
Microsoft say that now… When you work with Copilot to create presentations you will get a totally transformed experience. It will
Clarify your intent
Conduct deep research
Produce high-quality content.
How to use “Agent Mode”
First thing first….. Not everyone can yet and it’s not available day one… OK now read on…
Currently, Agent Mode is available for organisations (and users) enrolled in the Frontier program for Microsoft 365 Copilot who have a Microsoft 365 Copilot license or that have Microsoft 365 Personal or Familywith a Copilot Pro license.
Agent Mode works in Excel on the web but will be coming soon to desktop. Word is also coming soon.
For Excel, you will also need to install the Excel Labsadd-in and choose “Agent Mode”.
Oddly, from what I have read, the Office Agent is only available for Copilot Pro subscribers on Microsoft 365 Personal or Family or Premium and not (yet) Microsoft 365 Commercial. It’s also limited to USA currently! 🙁
The responses and workflows you get back from AI is only as good as the content it can reason over or leverage. If your content (data) is not in good shape and healthy (relevant, up-to-date etc) then it “isn’t ready” meaning your experience of AI will be “sub optimal” at best.
This is where Microsoft’s upcoming SharePoint’s Knowledge Agentcomes it. It is designed to bridge that gap — enriching, organising, and structuring organisational content so Microsoft 365 Copilot and enterprise agents can drive real business impact, not just deliver answers.
SharePoint Knowledge Agents’ “role” is to help you turn fragmented content into structured, governed, AI‑ready knowledge – so your AI doesn’t just answer, it understands, compares, summarises, and automate by having optimally organised, labelled and meta data rich content at its virtual fingertips!
What is SharePoint knowledge agent ?
If your organisations’ SharePoint intranet is cluttered with old, irrelevant pages or files that simply are not labelled properly (inconsistent metadata), Search and AI tools like Copilot can’t easily find or understand the information your people need when they search. This limits the value you get from AI, because it can’t surface the best answers or automate tasks reliably.
The SharePoint Knowledge Agent is a Microsoft native, AI-driven capability in SharePoint that systematically improves content quality, discoverability, and governance, which are the foundations Copilot needs to reason well. SharePoint Knowledge agent adds intelligent metadata, builds useful views, aligns labels and policies, and even generates workflows from plain language.
SharePoint Knowledge Agent
Microsoft say that the result should be “cleaner, richer knowledge fabric” across your business that raises the “fidelity of AI answers”, reduces manual effort, and makes content immediately actionable.
Knowledge Agent is designed to solve this problem by:
Curating content intelligently (helping keep only what’s useful and relevant),
Automating site maintenance (removing or updating outdated pages and files),
Enabling natural-language workflow creation (letting users build processes just by describing what they want, in plain English).
All of this happens inside SharePoint, making your intranet/knowledge libraries smarter, cleaner, and ready for AI-powered productivity without leaving your SharePoint page. Once enabled by your admin (since it is in preview right now), content admins see a floating button in the bottom‑right corner of every SharePoint page which serves as your entry point into SharePoint’s Knowledge Agent.
TIP:
You will know that a site has the SharePoint knowledge agent enabled as you will see the little SharePoint icon on the bottom left of the screen.
What can SharePoint Knowledge Agent do?
The SharePoint Knowledge agent has several key uses:
Context for AI with auto metadata: Copilot can suggests new columns and tags, and then auto classifies files with more meaningful, auto-filled metadata. Copilot and Agents can reason over this data to better distinguish similar documents and deliver higher‑quality answers.
SharePoint Knowledge agent – adding suggested Columns and meta tags
Confident, compliant experiences: Keeps metadata clean and aligned to policy with smart suggestions, labeling, and admin controls.
an create optimised “AI” views: Generates views that sort, filter, and group documents by metadata (e.g., “policies expiring in 2026” or “contracts grouped by client”) so teams find what matters fast.
Plain‑language automation: The Knowledge agent can help with “simple” automation tasks too. For example, users can describe what they need (e.g., “When the document changes or is updated, send an email to the owner”), and the agent builds the workflow.
This is quite simple automation but no technical expertise is required. For more advanced users, this can (still) be done with Power Automate which provides much more control and capability. Worth noting that the automations done via the Knowledge agent “currently” relay on meta data contents only and not file contents.
Answers and insights in context: You can ask the Knowledge Agent quick questions about site content and get grounded answers that leverage this new metadata.
Dynamic, multi‑turn web creation: Helps “owners” build and master SharePoint pages with natural language prompts, templates, and intelligent section suggestions – turning web content creation and SharePoint pages into a guided, iterative experience.
Knowledge Agent helps improve Copilot and agents accuracy
Better grounding with richer signals: Copilot relies on context to reason well. Structured metadata gives it the disambiguation and granularity needed to separate look‑alike documents, trace policy lineage, and surface authoritative sources.
Higher signal‑to‑noise across the tenant: Clean metadata and policy alignment reduces clutter in retrieval, improving ranking, semantic matching, and prompt grounding. Your AI spends less time guessing and more time knowing.
Actionable content, not just answers: AI-generated views, file comparison, and audio summaries make content instantly usable helping people move from “find” to “decide” to “do” in one flow.
Enabling the SharePoint Knowledge Agent?
Availability: Knowledge Agent is now available in Public Preview via “tenant‑level opt‑in” for users with a Microsoft 365 Copilot license.It can be enabled at site level or across all sites. This is only via PowerShell today, but I expect a UI to come soon.
Common Questions
Do we need Microsoft 365 Copilot licenses? Yes – Users need a paid Microsoft 365 Copilot license to use this feature.
Is this only about metadata? No — this is about creating AI‑ready content end to end: intelligent metadata, compliant labeling, actionable views, guided page creation, and plain‑language automation.
How to I enable the Knowledge Agent? Microsoft have provided a guide and instructions on how to enable the agent via PowerShell. You can access this here: https://aka.ms/KnowledgeAgentOptIn
Will this reduce manual tagging? Yes — the agent suggests and autofills columns based on content and user input, cutting manual effort dramatically.
How does this improve Copilot answers? Cleaner, richer metadata gives Copilot the context to distinguish similar documents and ground responses to authoritative content.
Microsoft has started to broaden their AI horizons by adding their first (not Open AI) model into Copilot.
Microsoft are integrating Anthropic’s Claude models into Microsoft 365 Copilot which marks a significant pivot from their exclusive OpenAI-centric approach. Microsoft are also working on their models which we already see on Copilot Plus PCs which will at some point make their way to Copilot.
This move is more than just a new menu option or toggle, it is part of their strategic play to diversify AI capabilities and reduce dependency on a single vendor.
Claude Opus and Sonnet in Copilot.
Claude Opus 4.1 and Sonnet 4 are now available to commercial Frontier Copilot users, (Corporate early adoptors) offering, for the first time, alternatives to Open AI’s GPT models for agents in Copilot Studio and also for their Researcher Agent.
Copilot Studio Model Selector (preview)
It’s worth noting that enabling access does require admin approval. See later.
In the formal annoucement, Microsoft said that Anthropic’s models will unlock “more powerful experiences” for users.
Using Claude in Microsoft Researcher Agent – Via Copilot Chat.
Claude is not new to Copilot, but not new to Copilot AI. Claude is already available (along with other AI models) are already embedded in Visual Studio and Azure AI alongside Google’s AI and Elon Musk’s Grok. This is, however the first time Copilot launch that we have seen non-OpenAI models powering Copilot.
Why This Matters
Microsoft’s shift to leveraging different models reflects a broader trend. Microsoft’s message here is that Copilot is no longer about a single model or even vendor, bit more about orchestration, choice, and adaptability.
Different models have different areas of excellence and this sets the foundations for Microsoft to give flexibilityto tailor and tune AI experiences to specific business needs using the most appropriate model for the task.
It does, however, raise questions around governance, model performance, and cost. With multiple models in play, we don’t really know how the future of pricing will work if multi model is the future for Microsoft 365 Copilot.
Data Sovereignty and Multi-Model Concerns?
One question I’m already seeing is around Microsoft’s boundary of trust and responsibility, something Microsoft boast around with their Microsoft 365 portfolio.
While the flexibility of multi-model AI is compelling, the question is does it introduce new considerations around data residency and compliance when multi models are being used?
To address that, Microsoft has confirmed that these Claude models run within its Azure AI infrastructure, but states that are not Microsoft-owned. This means that when users “opt to” use Claude, their prompts and responses may be processed by Anthropic’s models hosted within Microsoft’s environment.
This means that when organisations choose to use Anthropic models, they are using these under Anthropic’s Commercial Terms of Service, not the consumer user terms.
For regulated industries or organisations with strict data governance policies, this is likely to raises a few red flags or at least questions that Microsoft will need to be able to answer.
Data Boundary Clarity: Is the data staying within Microsoft’s compliance boundary, or is it crossing into Anthropic’s operational domain? If so what does this mean for data compliance and security?
Model-Specific Logging: Are logs and telemetry handled differently across models? Can organisations audit usage per model? How is encrypted data handled?
Privacy and Consent: Are users aware when their data is being processed by a non-Microsoft model? Is consent granular enough? Will users understand even if Microsoft tell them?
Again, Microsoft has stated that Claude models are “fully integrated” into the Microsoft 365 compliance framework, but organisations will still want to (and should) validate this against their own risk posture – especially where sensitive or regulated data is involved.
Enabling Claude models in Copilot.
To enable the models, your Microsoft 365 Admin needs to head over to the Microsoft 365 Admin Centre and enable access to the other models. Instructions for this are shown in the link below.
This is a smart move I think. Microsoft is playing the long game — moving their eggs out of one basket and looking a different models that made most economic and performance sense and brining more choice to agent builders.
For those of us partners like us at Cisilion, advising clients on AI adoption, this reinforces the need to think modularly. When building agents, don’t just pick a model – pick a framework that allows you to evolve. Microsoft’s Copilot is becoming that framework and that should be good for business.
I do expect this is just the start. We know Microsoft’s relationship with OpenAI is “less properpous” that it once was. As such I do expect more models, more integrations, and more choice and I do think we will see Microsoft’s own models making their way to Copilot soon.
But with choice comes complexity. We need to ensure that governance, transparency, and user education keep pace with innovation. Again partners will need to help customers navigate this.
What do you think. Is this a good move for Microsoft and their customers?
Microsoft Copilot is adding with two new major updates (this time for the consumer experience) that bring it closer to the more personalised AI experience users have been asking and waiting for.
Copilot Memory Management
One of the biggest asks for the consumer version of Copilot has been its lack of persistent memory, something that ChatGPT and Microsoft 365 Copilot have both had for a little while.
Memory is one of the key features helps makes AI feel much more personal and it’s finally coming to the Copilot Consumer experience that you use via the Windows App, mobile app and at https://copilot.microsoft.com.
A new Manage Memory feature within the Copilot profile tab is now starting to roll out which allows users to tell Copilot to specifically “remember this.”
Copilot Memory
Right now, unlike the Microsoft 365 Copilot version, there is not a way to view or edit your saved memories, but there is an option, via Privacy settings, to delete them and essentially “start over”.
Copilot Memory Management in Copilot Consumer
Think of this as resetting your TV and having to add all your favourite apps and channels again!
Microsoft have confirmed however that full memory management interface is coming soon, similar to what Microsoft 365 Copilot and ChatGPT has. This will eventually allow users to add, edit
Personally, Memory Management will make a huge different to how we work with Copilot and helps ensure greater user control and transparency.
Third Party App Integration.
Microsoft is also expanding their Connectors Ecosystem, which is what is used to connect and integrate third-party services. Support for Microsoft apps and services such as OneDrive is already supported, but they are now testing with Insiders Google Drive integration.
Integration into OneDrive and *soon* Google Drive means users will be able to do such things as:
Ask Copilot to read files or folders from users OneDrive or Google Drive
Generate summaries, create reports and other content on your data stored in cloud drive
Access and leverage OneDrive and soon Google Drive data in workflows across the web, Windows 11 app and mobile.
This builds on the existing ChatGPT-style connectors framework and opens the door for broader integrations in future. Microsoft is not new to having extensive open API connection to their apps and services so watch out for more native connectors coming your way soon!
Great for Consumers
These updates signal Microsoft’s continued innovation in their AI services and commitment to make Copilot a more intelligent, connected, and user-centric assistant.
For professionals, students and general users alike, the ability to manage memory and connect to third party cloud services like Google Drive will unlock new productivity scenarios.
As someone who’s personally deeply invested and embedded in the Microsoft ecosystem, I see this as a positive move – but one that must be backed by clear user controls, privacy safeguards, and cross-platform consistency.
With all the new AI models in Microsoft Copilot along with the first party agents that serve spefici functions, it can be confusing to know which tool to use for the right task. Microsoft have two specific agents within the Microsoft 365 Copilot domain Researcher and Agent designed to carry outr specific functions. We also now have GPT-5 (now also baked into Copilot) which brings the new “smart” mode, allowing it to switvch between languiage models based on the task at hand.
In this blog, I aim to break down the three tiers of Copilot capability— GPT-5 Chat, GPT-5 Reasoning (also known as Smart mode), and Researcher and to look at the differences, similarities and what is best for what!
GPT-5 Chat: Fast, Friendly, and to the Point
Best for:
General Chat and Quick Q&A
Content Summarisation
Creative brainstorming
How it thinks: Chat mode is is your rapid-fire assistant. It delivers supoer quick responses to youur questions without deep analysis. This is ideal for when you need an answer or exmplanation, clarity on something and anything not requiring deep thinking, reasoning or complexity.
Example prompt:
“Write a short social post abou the latest updates to [product].”
When to use it: When you want brevity, speed, and a touch of flair. Think elevator pitches, tweet-length summaries, or light creative riffs.
GPT-5 Reasoning: Structured Thinking for Strategic Tasks
Best for:
Logical analysis
Problem-solving
Multi-step planning such as building a travel itinery, project plan or talk track
How it thinks: This mode (which GPT-5 will switch too automatically if needed), rolls up its sleeves and gets analytical. It’s designed for tasks that require synthesis, deep exploratory analysis, structured responses and a more strategic (deep thinking) response.
Example prompt:
“Let’s walk through this problem together: I need to launch a new product with a limited budget and a small team to appeal to an already crowded market. What’s the best strategy?”
Use it when: You’re building timelines, weighing trade-offs, or need a coherent plan that holds up under scrutiny.
Copilot Researcher Agent: Deep Dives and Source-Backed Intelligence
Best for:
Comprehensive research and reports
Source comparison and opinioning
Insight generation
How it thinks: Researcher mode is a custom build agent from Microsoft specifically designed to work in a recursive, self evaluation and exhaustive approach. It pulls from multiple sources which it compares and contrats against one-another, compares methodologies, and identifies gaps. This is design for for thought leadership, academic-style or research style analysis, or strategic decision-making with different view points.
Example prompt:
“Find and summarise studies on the effects of remote work on productivity. Compare methodologies and results, looking at pro’s cons, impact on society, well-being, productivity and trends across different EU regions.”
Use it when: You need more than just an answer. You want to combine different view, present the otput in a particular way and when you need comprehenisive evidence, nuance, and a narrative that stands up to boardroom or peer review.
Which One When?
There is no definitiave answer to this, but based on my usage and infomration I have read in the field, guidance from OpenAI, Microsoft and others, this table provides a guide to which mode would work best in the scenaios below
Task Type
Use GPT-5 Chat
Use GPT-5 Reasoning
Use Researcher
Write a quick summary
✅
Build a strategic roadmap
✅
Compare academic studies
✅
Brainstorm creative ideas
✅
Solve a complex problem
✅
Generate source-backed insights
✅
AI isn’t a one-size-fits-all and not all use cases are the same. As AI models contine to become more context aware and with the ability to switch modes, there are still many times where knowing where to take your problem to is key – just like you know to talk to a specialist consultant vs a generalise at times.
Currently, to get the best from these AI models, the best result often lies in knowing when to switch gears—from conversational to analytical to research-grade depth. Whether you’re a CTO shaping strategy or a content creator chasing clarity, the right mode turns AI from assistant to partner to mentor.
Would you like this adapted into a SharePoint-friendly format or paired with a branded visual? I can also tailor it for internal enablement or customer-facing use.
Teams has a powerful new capability called the Facilitator Agent – a Copilot-driven meeting assistant designed to make collaboration smoother, smarter, and more productive. Think of it as a virtual chairperson that keeps your meeting on agenda, on-time and to point,whilst allowing participants to focus more on the meeting than taking notes.
Facilitator in Teams Rooms – Image (C) Microsoft.
Facilitator auto-drafts agendas, keeps people on track of the agenda and timings, provides rolling summaries, decisions, and action items all in a secure shared Loop page that everyone can co-author / edit across desktop, web, mobile, and even now in Teams Rooms direct from the room controls in Teams Rooms.
What is the Teams Facilitator Agent?
The Facilitator Agent is an AI-powered feature built into Microsoft Teams that works alongside Microsoft 365 Copilot (you need a Copilot license to activate it and interface to it). It acts as a shared assistant within your meetings and chats, providing:
Real-time AI-generated notes: Captures discussion points, decisions, and action items as the meeting unfolds.
Collaborative editing: All participants can view notes and Microsoft 365 Copilot licensed users can co-author notes live – this ensures accuracy and inclusivity.
Meeting moderation: Helps manage agendas, prompts for goals if none are set, and even nudges participants to wrap up discussions.
Time management: Includes a meeting clock and reminders to keep sessions on schedule.
Post-meeting recap: Provides a structured summary and tasks in the Recap tab, stored securely in Microsoft Loop in the meeting organisers’ OneDrive.
How is it Facilitator different from the old “AI Notes” feature?
Previously, Teams offered AI Notes as part of Intelligent Recap, which generated summaries after the meeting. While useful, it was a passive experience—participants couldn’t interact with or influence the notes in real time.
The Facilitator Agent replaces and enhances this by:
Working live during the meeting, not just after.
Real-time co-authoring of notes by both AI and humans as the meeting progresses.
Acting as an active participant, responding to @mentions and questions in chat.
Providing dynamic updates as discussions evolve, rather than static summaries.
Keeps a track of the meeting, who has spoken, actions and topic/agenda drift (in otherwords it politely nags you!)
What is Facilitator good at?
Facilitator can or could if trusted, replace the chair or act as a chair/co-chair in a meeting. In my personal experience I have foudn it to be really really good at:
Real-Time Note-Taking & Summarisation Capturing key discussion points, decisions, and action items during meetings, with live co-authoring – I love how it writes as the meeting prgresses and even corrects itself.
Meeting Moderation & Structure Detects if a meeting lacks an agenda and prompts participants to define goals. If a meeting has an agenda it attempts to chunk the meeting into sections and helps keep the meeting on topic and ontime.
Improved Collaboration Works in meetings and group chats, keeping everyone aligned—even late joiners. It allows people to talk to the agent too – by mentioning @facilitator if you need it to do something like set an action or recap a point.
Post-Meeting Recap & Accountability Generates structured summaries and suggested tasks in the Recap tab for people to go back to or generate an email follow from etc,.
Facilitator Agent – Current Limitations
I do love usig it – its been GA for a few weeks now, but there are few limitations which I hope/expect will “go away soon”. These include:
Not Available Everywhere: Facilitator currently doesn’t work in external, instant, or channel meetings; mobile users can view notes but not start Facilitator (yet)..
Compliance Gaps: Sensitivity labels don’t automatically apply to notes yet but this is in thge public roadmap.
Using Facilitator in Meetings
Turning it on: By Default, when you create a meeting via Teams, Facilitator is “off” and needs to be enabled by switching the toggle as illustrated below. It can also be enabled from “within” the meeting.
In Meeting Interaction: When the meeting starts, you are notified that Facilitator is running via an in-app notification. Note the meeting does not need to be recorded for this to be active. You also see this indicator under the notes section at the right of the meeting pane.
By the way, if you join a meeting where Facilitator is not active, you can enable it anytime from the menu under “…more”.
You still get a notification when Facilitator is running, and it will period chat to you in the meeting chat to keep you updated on the meeting.
Facilitator in Meeting
In Meeting – Meeting Notes and Actions Beng taken by Facilitator
Actions Generated by Facilitator
During the meeting (and afterwards, which you can find by going back to the meeting in your calendar), you can view and of course edit the notes, actions and also see any “related” content and “insights” that Facilitator has sufaced that it “thinks” might be relevant to the meeting dsicussion you have been in. These notes are captured in a Loop Space which is stored on the meeting organisers OneDrive and shared (automatically) with all meeting participants.
Post Meeting Notes, Actions and Insights.
Facilitator Agent Use Cases
I use this in most meetings but there are loads of use cases I see and hear about.
Daily stand-ups or project huddles to log progress and blockers
Customer calls and scoping meetings capturing commitments and next steps to eliminate follow-up churn
Project update or planning calls.
Facilitator Agent – What is Coming (Roadmap)
This is in preview and will be fully rolled out (GA) by September, and there are a few thinsg still nt he works which I expect will be out soon enough.
Editable Canvas for Chat Notes: AI notes in chats will move to an editable canvas backed by SharePoint Embedded.
Teams Rooms Integration: Facilitator will also (now in Preview) support ad-hoc and scheduled meetings in Teams Rooms, with QR code invites and speaker attribution.
Improved Compliance: Sensitivity label inheritance and enhanced governance via Microsoft Purview will be supported.
Q & A
Q: Is the Facilitator Agent just a rebrand of the previous AI notes feature? A: It builds on that toggle but expands into a full-blown agent. Beyond post-meeting summaries, Facilitator prompts agendas, generates live recaps, drives collaboration via Loop, and integrates with Teams Rooms by QR code.
Q: How does it differ from using Copilot in a Teams meeting? A: Copilot in a meeting is a private assistant—only you see its responses. Facilitator operates in the group context: prompts, highlights, and action items appear for everyone to view and edit in real time.
Q: What’s the added value over just recording and transcribing? A: Recording and transcription are passive: you consume them after the fact. Facilitator is proactive—drafting agendas, nudging for goals, surfacing decisions, and giving every attendee an editable canvas mid-meeting.
Q: Where does Intelligent Recap fit in? A: Intelligent Recap synthesizes speech and on-screen visuals after the meeting ends. Facilitator closes the loop instantly – keeping the conversation structured, accountable, and collaborative from start to finish.
Q: What are the alternatives to Facilitator Agent?
1. Native recording + transcription then manual or Copilot/ChatGPT note generation 2. Intelligent Recap for post-meeting slide and data context 3. Private Copilot chats for ad-hoc AI queries 4. Manual note-taking or shared OneNote pages 5. Third-party assistants like Otter.ai or Fireflies.ai
Q: Do I need a Copilot license to use the Facilitator Agent? A: Any user who initiates or edits AI-generated notes in meetings or chats must have a Microsoft 365 Copilot license. Unlicensed participants can view meeting AI notes but cannot start or edit them.
Q: What about in-person meetings? A: Coming soon – a new feature in the Teams mobile app will let you start a dedicated in-person meeting with Facilitator right from your phone. This will then kick off a recorded, transcribed session – again with real-time agendas, notes, and follow-up tasks. When you end the meeting, notes save automatically and a “in the past” calendar event is created—everything is surfaced in Recap. – This will requires a Copilot license and is due to be in preview Auguist/Sept – I’ve seen it but don’t have it yet myself!
We are in the middle of rapid shift – AI agents are no longer just reactive helpers waiting for a us to give them a prompt. Instead, they are becoming proactive, and autonomous , capable of initiating actions, orchestrating workflows, and making decisions across systems.
If you’ve already built governance models for low‑code platforms like Microsoft Power Platform, you’re not starting from zero. Those same principles – with a few smart extensions can help you govern the next generation of agents built in Copilot Studio.
What is Agent Governance? Agent governance encompasses the rules, policies, and oversight mechanisms that guide the behavior of AI agents – autonomous systems capable of performing tasks with minimal human intervention. This governance is crucial to ensure that these agents operate in a manner that is legally compliant, ethically responsible, and operationally safe!
Microsoft have shared new blue prints and guidance to help you get started with healthy goverance for Copilot Studio – which I have linked to and summarised below…
1. Lead with a Governance Mindset
Agents aren’t “just another app.” They’re digital labour – they (can) talk across systems and across roles and need managing just like humans. This means they they need:
Trackable identities — so you know exactly which agent did what, and when.
Scoped permissions — the principle of least privilege applies here too.
Continuous oversight — because autonomy without accountability is a risk.
Not every agent should have the same freedom. For example, a Q&A bot answering FAQs is low risk. An autonomous sales development agent drafting proposals is much higher stakes and an agent that takes a customer interaction and acts on it automonously is high risk.
We must define tiers of autonomy and enforce them with technical guardrails.
2. Apply Your Low‑Code Lessons
If you’ve governed Power Platform, you already have your own playbook:
Managed environments to separate dev, test, and production.
Role‑based access control (RBAC) to manage who can create, deploy, and run agents.
Data Loss Prevention (DLP) policies to control what data agents can access or share.
Audit logs to track behaviour and support compliance.
These aren’t “nice to haves” — they’re essential for safe, scalable agent adoption. Extend your existing frameworks to cover new agent behaviours.
3. Drive Visibility, Cost Control, and Business Value
Governance isn’t just about control — it’s about clarity. Visibility and telemetry is really important becuase it tells us:
Who created the agent.
What data it touches.
How often it’s used.
The business outcomes it’s driving.
With that visibility, you can spot redundantagents, forecast costs, and focus investment where it delivers the most value. Tools like Copilot Studio analytics and Power Platform Admin Center make this possible — but only if you use them consistently.
4. Empower Innovation with Guardrails
The people closest to the work often have the best ideas for agents. Advice is to empower them to experiment — but within a zoned governance model:
Zone 1: Personal Productivity — safe sandboxes for individual experimentation.
Zone 2: Collaboration — team‑level development with stronger controls.
Zone 3: Enterprise Managed — production‑grade agents with full monitoring and lifecycle management.
This approach balances speed and safety, enabling innovation without compromising compliance.
5. Build Community, Training, and Experimentation into the Culture
Governance is as much cultural as it is technical and it’s the culteral and human aspects that typically impact and slow adoption.
A thriving Center of Excellence (CoE) should:
Host “Agent Show‑and‑Tell” sessions and hackathons.
Appoint champions in each department to mentor others.
Provide role‑based training for makers, admins, and business leaders.
Encourage responsible experimentation — and celebrate successes.
As with any transformational shift, when people feel supported and inspired and part of the journey, adoption accelerates and impact flourishes.
Why This Matters Now
According to Microsoft, over 230,000 organisations – including 90% of the Fortune 500, are already using Copilot Studio, and IDC projects there will be a staggering 1.3 billion AI agents by 2028.
This scale and exponential speed of adoption make governance a critical priority, not an afterthought or option!
The CIO’s role is shifting from enabling agents to governing them at scale — ensuring they’re secure, compliant, cost‑effective, and aligned with business goals. That’s not just a technical challenge; it’s a leadership opportunity.
Summary – the Key Steps
Extend your low‑code governance — apply your Power Platform controls to agents.
Define autonomy tiers — match oversight to risk.
Instrument for visibility — track usage, cost, and impact.
Microsoft has introduced the =COPILOT() function in Excel, embedding AI directly into spreadsheet cells. This formula turns natural-language prompts into structured outputs—no VBA, no complex formulas—so anyone can perform advanced analysis with a simple cell entry.
This essentially turns your prompts into Excel formulas direct from your excel cell!
Copilot() function in excel
This is in currently in public preview.
What It Is and How It Works
The COPILOT() function behaves like any native Excel formula. You type =COPILOT("andyourprompt", [range]) in a cell, and Excel sends the request to the Copilot service (powered by Bing and ChatGPT). The AI returns a grid-friendly result that recalculates automatically whenever your source data changes. You can even nest COPILOT() inside functions like IF or LAMBDA for more sophisticated logic.
Core Capabilities
Summarise, group, or categorise data using plain-English prompts
Perform sentiment analysis on text feedback
Extract and organise information from unstructured text (names, emails, URLs)
Generate dynamic lists, schedules, or qualitative ratings
Augment tables with symbols or simple markers for clearer storytelling
Key Use Cases
Automating data cleanup: standardise formats, remove duplicates, split columns.
Customer insights: turn free-text reviews into sentiment scores and themes.
Sort data and represent in different formats without having to learn how to create pivot tables.
Transforming data using formulas without having to write a formula.. Just natural language.
Prerequisites & Access
To use COPILOT() in Excel, you must meet the following requirements:
Microsoft 365 commercial Copilot license (not included in Personal/Family plans)
Microsoft Entra ID account and primary mailbox on Exchange Online.
Excel Beta Channel build 19212.20000 or later / macOS build 25081334 or later
Up to 100 function calls per 10 minutes (300 per hour); use array inputs to conserve quote.
Data stored in the active workbook (external sources not yet supported
How to access:
In Excel, go to File > Account > Office Insider and switch to the Beta Channel (Windows).
On Mac, open Help > Check for Updates in Microsoft AutoUpdate and choose the Beta release.
Sign in with your work/school account that has a Copilot license; use File > Account > Update License if needed
Restart Excel—=COPILOT() will now be available in any cell, or via the Home > Copilot pane.
Requirements and Limitations
Not optimised for heavy numeric or matrix computations
Outputs are dynamic—save critical results as values to prevent unintended changes
Only works with in-workbook data; live web or external data access is pending
Why It Matters
Excel remains the lingua franca of business data. By transforming the grid into an interactive AI canvas, COPILOT() tears down formula-syntax barriers, accelerates decision-making, and empowers every user—from analysts to frontline managers—to become data storytellers. Enablement leaders can shift focus from formula training to writing effective AI prompts and compelling narratives.
In short, it’s powerful for people that are not excel formula wizards!
It snuck in quietly, like all meaningful innovations do. I didn’t see a press release, or announcement – and just saw it “pop” up for me today with one small pop-up. Just one single word, Smart. And yet, beneath the understated label lies perhaps the most pivotal shift in the way generative AI models like Copilot and ChatGPT work since manual “model selectors” first became a thing.
This is, yes, you’ve guessed it GPT5!
Smarter Than Smart – the quiet revolution of reasoning
Copilot (i’m talking the consumerversion currently at copilot.microsoft.com) or via the Windows, IOS and Android app, currently has three modes of chat which you choose based on the discussion with Copilot you want to have. This is similar to how ChatGPT works also today.
Quick Response [for every day conversations]
Think Deeper [for more complex topics]
Deep Research [Detailed reports with references]
That is changing – Microsoft Copilot’s new ‘Smart’ mode doesn’t ask you to choose a conversation type anymore. Instead it now adapts for you – automatically and intuitively.
This means, that depending on your query, for example whether you’re scoping customer insights, untangling a tricky dependency in a network diagram, or storytelling your way through a general chat, summarisation of marketing ideas, ‘Smart’ mode calibrates itself to the conversation and task at hand.
In short – in this mode, Copilot will now decide what model it thinks it needs to help you. Copilot has auto reasoning — true adaptive, context-aware reasoning based on the ask.
What Makes This Mode Smart?
‘Smart’ mode is likely powered by OpenAI’s upcoming GPT-5, a model anticipated to merge the OpenAI o-series and GPT-series models into one unified framework.
What we’re seeing as these models evolve is:
An intuitive reasoning engine, not just predictive text- task “and” context aware
Self-calibrating depth, reducing cognitive load by using the right tool for the right job
Model abstraction, freeing users from having to pick the right tool for the job themselves
Microsoft hasn’t just added another dial. It’s looking to hide the dial entirely — and taught the model how to turn it for you (however as it’s in preview you do need to turn the auto mode on – for now at least).
Copilot’s Human Centric UX
As you can see above, instead of users needing to flip between “Think Deeper,” “Quick Response,” and “Deep Research,” (or not evening understanding what these mean and therefore ignoring it), Copilot’s Smart mode does what most tools never do: it assumes responsibility. That’s more than a UX shift — it’s a culture shift. This means no longer asking (non technical) users to understand what the different models the model hierarchy or decoding acronyms like o4-mini. Instead Copilot is getting cognitive delegation.
This means we will be able to “trust”Copilot to know when to dig deeper and when to skim the surface.
Examples: Tech Architects, Storytellers, and Strategists
The table below gives some examples of where Copilot Smart mode can make a big different in use:
Role
Before Smart Mode
With Smart Mode
Solution Architect
Manually toggling depth based on task complexity
Instant adjustment to scope and context
Content Creator/Marketing
Selecting modes based on tone and detail required
Natural flow from quip to deep dive
Enginner
Testing prompts for clarity vs depth
Getting both — with nuance — the first time
This isn’t just about being faster. It’s about being right-sized. Strategically aligned, creatively agile, and cognitively respectful.
What about control and “mode anxiety”?
We’ve all wrestled with prompt engineering, hoping we’re not asking too little or too much. Smart mode is Copilot whispering, “I’ve got you.” That’s a leap from assistant to partner — the kind we’ve spent decades trying to design into our workflows, team cultures, and tech stacks.
Copilot Smart Mode Preview?
This is in preview clearly – or was it rolled out silently. Anyway, if you have it, give it a try (I have it on desktop and web plus mobile). Let me know your thoughts.
It will be interesting to see if eventually the modes disappear and we just have an “auto” mode.
Copilot Memory is a new capability within Microsoft 365 Copilot (similar to what ChatGPT has) that allows Copilot to remember key facts about your preferences, working style, ongoing projects, and other things you want it to know about you. This enables it (think PA) to be able to tailor its responses over time. You can add and change this as needed so it evolves with you, reducing repetitive prompts, adapting to your style and speeding up your daily tasks.
Key Capabilities
Persistent Facts
Copilot picks up on explicit instructions like “Remember I prefer bullet points in my writing” or “Always use a formal tone in emails” and retains these details across sessions.
Custom Instructions
Beyond passive memory, you can proactively shape Copilot’s baseline behavior. Ask for brevity, wit, or a specific document style, and Copilot applies those instructions automatically in Word, Excel, Outlook, and other 365 apps.
Contextual Recall
Copilot integrates with Microsoft Graph and ContextIQ to ground conversations in your files, meetings, and chats, ensuring its outputs align with your latest work context.
How It Works
Explicit Memory Prompts
Copilot only stores information when you ask it to. This prevents unwarranted data collection and keeps your AI focused on what matters to you.
Memory Updated Signal
Whenever it logs a new fact, you’ll see a subtle “Memory updated” badge—confirmation that Copilot has learned something new about your preferences.
Privacy Controls
You can control its memory: You can view, edit, or delete entries in Copilot’s Settings pane and if you need to can wipe it’s memory and start fresh by simply toggle the Memory function off entirely.
Admin and Compliance Oversight
Organisations can disable Memory for specific users or tenant-wide, and all memory actions flow into Purview eDiscovery for audit and compliance purposes.
Timeline & Availability
Rollout date: July 2025 (staged)
Why Copilot Memory Matters
Efficiency Gains
This is really about efficiency and personalisation since you will no longer need to keep telling Copilot your preferred tone or formatting preferences. This speeds up document creation, email drafting, and data analysis.
Deep Personalisation
By remembering your recurring topics—Project Alpha, Python for data science, or icon-size images—Copilot provides responses that are more tailored to each user, not generic AI outputs.
Enhanced Adoption
For organisations, personalised AI interactions drive higher engagement and adoption of Copilot across teams, leading to greater ROI on AI investments.
Trust & Transparency
Visible memory updates and clear controls build user confidence in the AI, ensuring you always know what Copilot retains and why.
Enabling Copilot Memory
Memory is an option feature and can be enabled, modified and disabled as needed. To enable it, follow the instructions below.
Open Microsoft 365 Copilot and head to Settings › Account › Privacy.
Under Personalisation & memory, toggle Memory on or off.
Tell Copilot what to remember: “Remember I prefer bulleted lists,” or “Keep my summaries under 100 words.”
View, edit, or delete memories any time from the same settings pane.
Coming soon, Copilot in Teams will improve on its intelligent meeting recap feature by incorporating content shared on screen into the AI-generated summary. This will ensure that slides, dashboards, and other visuals shown by participants become part of the post-meeting recap, capturing unspoken insights and making your summaries more comprehensive.
Visual Insight for Deeper Recaps
Meeting transcripts are great for meetings but currently miss the context conveyed by visuals in screen sharing. With this update, Copilot and Recap in Teams will:
Analyse on-screen content during live screen sharing.
Extract key data points, figures, and text from slides or shared apps.
Seamlessly integrate those visual details into the AI-powered meeting summary.
By bridging voice and visuals, teams gains a unified recap that reflects both spoken dialogue and pivotal on-screen information, reducing the risk of overlooked action items.
How Intelligent Capture Works
For Copilot to reference shared screen content accurately, the following conditions apply:
The shared content must remain on screen for at least 10 seconds to allow Teams OCR time to process it.
Content needs to be clear and legible; overly crowded or small text may not be captured.
At launch, PowerPoint Live and Whiteboard screen shares aren’t supported for visual extraction.
These requirements help ensure Copilot’s OCR and contextual understanding produce reliable, actionable summaries.
Licensing and Platform Support
This feature requires a Microsoft 365 Copilot license and will roll out to:
Teams for Windows desktop
Teams for Mac desktop
Teams on the web
Teams on iOS and Android
Prereqs for Intelligent Recap
To unlock the full benefits of intelligent recap, admins need to configure:
Recording policies that allow meetings to be recorded and stored in the cloud.
Transcription settings to capture spoken content as text.
Copilot or Teams Premium licenses assigned to meeting organizers and participants.
Other Related Innovations
Microsoft continues to expand Copilot and adjacent AI features in Teams. Recent roadmap highlights include:
Interactive agents in meetings and 1:1 calls (Roadmap ID 490564), bringing custom and built-in Copilot agents directly into your Teams sessions for on-the-fly assistance.
Meeting protection via Prevent Screen Capture (ID 490561), which blocks unauthorised screenshots by blacking out the meeting window on desktop and mobile.
Enhanced audio summaries for calls, enabling Copilot to generate concise overviews even without full transcription.
Best Practices for use
Encourage meaningful screen shares: Use high-contrast slides and clear visuals to boost AI accuracy.
Maintain recording consistency: Standardize meeting settings to always enable recording and transcription.
Train your team on how to query Copilot post-meeting—e.g., asking for “action items from the product roadmap slides.”
Review AI-generated tasks promptly to assign ownership and follow through on deliverables.
Conclusion
Incorporating visuals into AI-powered recaps marks a significant leap forward for Copilot in Teams. Capturing both spoken and on-screen content ensures no detail goes unnoticed.
With the upcoming rollout of this feature under Roadmap ID 490052, Copilot will help teams stay aligned, save time on note-taking, and drive better outcomes from every meeting.
Microsoft 365 Copilot now includes two advanced AI agents – Researcher and Analyst that became generally available in this month ( June 2025). These agents use powerful reasoning models (based on OpenAI’s o3-mini and deep research models) to handle complex tasks beyond what the standard Copilot could do.
Researcher is a specialised agent for multi-stepresearch – it can securely comb through your work data (emails, files, meetings, etc.) and the web to gather information, ask clarifying questions, and produce well-structured summaries and insights. It’s ideal for tasks like market research, competitor analysis, or preparing for big meetings – work that used to take hours, now done in minutes with higher accuracy.
Analyst is a virtual data analyst/data scientist built into Copilot. It excels at advanced dataanalysis, working through messy spreadsheets or databases step-by-step using chain-of-thought reasoning and even running Python code when needed. From identifying sales trends to spotting anomalies in finance data, Analyst gives you in-depth answers and visuals that mirror human analytical thinking.
Compared to the standard Microsoft 365 Copilot, these agents go much further in reasoning and capabilities for these specific tasks. While the native Copilot mod helps draft documents or summarise content, Researcher and Analyst tackle complex reasoning tasks (deep research and data analysis) with a level of thoroughness and skill akin to an expert – essentially “like having a dedicated employee at your side ready to go, 24‑7,” according to Microsoft’s Jared Spataro. They are accessed through the Copilot interface (pinned in the Copilot app and via Copilot Chat) and come with a usage limit of 25 queries permonth per user due to their intensive workloads.
Analyst vs. Copilot for Finance:
Analyst is a general-purpose data analysis agent available to any Copilot user, whereas Microsoft 365 Copilot for Finance is a separate, role-based Copilot designed specifically for finance teams. Copilot for Finance connects to financial systems (like Dynamics 365 and SAP) and Microsoft 365 apps (Excel, Outlook) to automate finance workflows (reports, reconciliations, insights). Unlike the Analyst agent which works on data you provide, Copilot for Finance directly taps into live enterprise finance data for real-time insights. Importantly, Copilot for Finance is not limited to Dynamics 365 – it can integrate with various ERPs including Dynamics 365, SAP, etc via connectors though it is deeply optimized for Dynamics 365 Finance.
The Age of AI Specialists in Microsoft 365 Copilot
Microsoft 365 Copilot is evolving from a single assistant into a team of AI specialists. Earlier this year, Microsoft announced two first-of-their-kind “reasoning agents” for work: Researcher and Analyst. After a period in preview (through the Frontier program) for early adopters, these agents are now generally available to all users with a Microsoft 365 Copilot license as of June 2025. This marks a significant expansion of Copilot’s capabilities beyond its initial skill set.
The new Researcher and Analyst are advanced Copilot modes (agents) specialised for particular scenarios – complex research and data analysis. They join other Wave 2 Copilot features (like the new Agent Store, Copilot Search, Memory, Notebooks, and image generation) that Microsoft has been rolling out to enhance the Copilot experience. Jared Spataro, Microsoft’s CMO for AI at Work, describes these agents as delivering “advanced reasoning” and notes “it really is like having a dedicated employee at your side ready to go, 24-7.” In other words, Microsoft 365 Copilot is no longer just a helpful assistant within Office apps – it can now also act as an on-demand subject matter expert that tackles higher-order tasks.
From a technology standpoint, both agents leverage the latest AI models tailored for their specific domains. They use OpenAI’s powerful models (codenamed o3-mini for Analyst, and a deep research model for Researcher) combined with Microsoft’s orchestration, search, Responsible AI, and tool integrations. This means they don’t just generate quick answers; they actually reason through problems in multiple steps, consult various data sources, and produce more comprehensive results. This blog explores each agent in detail:
Microsoft 365 Researcher Agent
Researcher is the new Copilot agent that acts as a highly skilled research assistant. It’s designed to help you tackle complex, multi-step research projects right from your Microsoft 365 environment. Researcher brings together OpenAI’s “deep research model” with Microsoft 365 Copilot’s advanced orchestration and search. In practice, this means it can scour both your organisational data *and* external sources on the web to find the information you need, synthesize it, and present insights in a coherent way.
What can Microsoft 365 Researcher Agent do?
Microsoft describes Researcher as “an agent that can analyse vast amounts of information with secure, compliant access to your work data – your emails, meetings, files, chats, and more – and the web” to deliver expert insights on demand. In simpler terms, Researcher is great at doing all the digging for information, reading it and then summarising the findings for you. Some of its capabilities include:
Multisource Information Gathering: It can search through your files, emails, SharePoint, and external online / Web sources to collect relevant data and. For example, if you’re exploring a new market or analysing a topic, Researcher will pull from both internal documents and credible websites to gather material.
Smart Summaries: After collecting information, Researcher summarises what it finds in plain, easy-to-read language. You get a clear, tailored report instead of a dump of raw data. It will highlight key points, trends, and insights rather than making you sift through hundreds of pages or search results.
Trend and Insight Identification: Researcher uses its AI reasoning to spot patterns, trends, and opportunities in the information. It can draw connections and highlight things that might make a difference for your project or question. For instance, it might notice an emerging customer preference across feedback data or identify a common thread in market research reports.
Interactive Refinement: If your initial query is broad, Researcher often asks clarifying questions to narrow down the scope and ensure it’s on the right track. This interactive back-and-forth helps it deliver more relevant results. You can guide it by answering those questions or giving additional instructions, much like you would with a human researcher.
Citations and Source Transparency: When delivering its findings, Researcher provides well-sourced content. It can include citations or references for where information came from, so you can trust but verify the results. (This is crucial for workplace research, and you can ask it to only use authoritative sources for extra confidence, as in one example prompt Microsoft shared).
Use Cases for Microsoft 365 Researcher Agent
Researcher is great in situations where you need to quickly learn or compile knowledge on a topic or subject area but are not sure where to look. This could be for tasks like assessing the impact of the new Trump tariffs on business lines, preparing for vendor negotiations by gathering supplier intel, and collecting client research before sales pitches.
Researcher Agent Example
In a business context, imagine your sales / marketing team are looking for a fresh perspective on top technology investments organisations are making in the UK based on industry research which needs to be in a report. You could ask Researcher “What are the top technology investments and projects by “small to medium” and enterprise organisations in the UK. Use trusted market data from repuatble sources such as Gartner, IDC, Cisco, Microsoft, Canlays, CRN etc.”
What I love is how you see the deep thinking and reasoning Researcher is using to compile the information and generate your report. This is so much easier than manually searching the web and reading dozens of articles. Instead, Researcher gives you a report in just a few minutes.
Instead of manually having to search the web and read loads and loads of articles, Researcher gives you a report in under ten minutes. You can of course tweak the response by asking more questions or requesting adjustments to ensure it meets you needs. When the report is finished you’ll see how comprehensive and well formatted it is, allowing you to export to, add it to a collaborative Copilot Notebook or leave it as is.
Sample output from Researcher Agent.
Microsoft 365 Analyst Agent – Data Analyst
If Researcher is your content and knowledge scout, Analyst is your number-crunching, data-savvy AI team member. The Analyst agent is all about diving into data (often numerical or structured data) to extract insights, find patterns, and answer complex analytical questions. Microsoft describes Analyst as “thinking like askilled data scientist”, using an advanced reasoning approach to tackle data problems step-by-step https://www.microsoft.com/en-us/microsoft-365/blog/2025/06/02/researcher-and-analyst-are-now-generally-available-in-microsoft-365-copilot
What makes Microsoft 365 Copilot Analyst Agent special?
The Analyst agent runs on a finely-tuned AI reasoning model (post-trained on OpenAI’s o3-mini model specifically for analytical tasks). Unlike a standard chatbot that might try to answer a data question in one go (and often make mistakes), the Analyst agent uses a chain-of-thought process to break problems down and solve them iteratively. It can even generate and execute actual code (like Python) in the background to manipulate data, perform calculations, or generate charts. Throughout this, it adjusts to new complexities and can recover from errors autonomously – essentially debugging and refining its approach as it goes, much like a human analyst would. The end result is a thorough analysis with reasoning that is transparent to the user.
Here are some of the key capabilities of the Analyst agent:
Data Analysis Across Formats: Analyst can work with Excel spreadsheets, CSV/TSV files, databases, Power BI reports, and other structured datasources . It can even extract financial data from PDFs. It is possible to upload or point it to a dataset, even if the data is messy or hidden across multiple files. For example, if you have sales data split across a few different Excel sheets and files, you can use Analyst Agent to ingest them all. The agent can also clean up many of the typical issues found in spreadsheets such as wrong delimiters in a CSV, or values buried in an unexpected place before it starts to work. This means that your data does not need to be perfectly prepared beforehand .
Iterative Reasoning and Problem Solving: When you ask Analyst a question, it will hypothesise, test, and refine repeatedly. For instance, you might ask, “What insights can you find about our Q4 sales data, and why did some teams underperform?”. Here, Analyst might break this down into steps: first identifying overall sales by region, then noticing why one sales team is lower, then digging into possible factors (maybe inventory issues or lower marketing spend), then correlating that with other data. It takes as many steps as needed to arrive at a sound answer. This multi-step approach leads to more accurate and nuanced results than a one-shot response.
Code Generation and Execution: A standout feature – Analyst can write and run Python code behind the scenes to perform calculations or data transformations. If your data question requires a formula, statistical analysis, or creating a chart, Analyst will generate the code to do it. Even better, it shows you the code in real time as it works, so you have complete transparency into how it’s reaching its conclusion. You effectively have an AI that can program on the fly to solve your data problem. This is like having a data analyst who is also a programmer working for you instantly.
Insight Generation and Visualisation: Analyst doesn’t just provide text based results – it will also explain the “story” behind the numbers in plain language and can also create simple charts or graphs to illustrate key points. It could, for example, produce a trend line graph of sales over time or a bar chart of top-performing products if those help answer your question. It will highlight findings such as “Sales Team A had a 20% increase in Q4, outpacing their previous year results ,,,, ” By narrating and illustrating the data, it helps you quickly understand the business implications.
Actionable Recommendations: Analyst can often suggest next steps or recommendations based on the data patterns it finds. If it discovers, say, that a certain region’s sales are lagging due to low inventory, it might recommend increasing stock or marketing in that region. Or if a customer segment is showing poor engagement, it could suggest targeted outreach. These suggestions turn raw analysis into useful advice, bridging the gap from insight to action.
Microsoft 365 Analyst Agent Use Cases:
The Analyst agent is useful anywhere you have data and questions about that data. Some real-world examples Microsoft has noted include using Analyst to assess how different discount levels affected customer purchasing behavior to identify the top customers who aren’t fully utilising the products they bought, and to visualise product usage trends and customer sentiment for informing go-to-market.
Analyst Agent Example
In the example below, I took some Customer Support Tickets from an excel (see below).
Sample Customer Support Ticket Export
I then have asked the Analyst Agent to “review the support ticket and create me an exective summary of the tickets, pulling out trends and themes that my team should look at and how they might reduce future support call duration.”
The results below are the first run with data that represeted as I have asked.
How Do Researcher and Analysts Agents Compare to the Standard Microsoft 365 Copilot Experience?
With all the excitement around Researcher and Analyst, you might wonder how they differ from the core Microsoft 365 Copilot Chat experience that users have been trying out in apps like Word, Excel, Teams, and Outlook.
The key difference comes down to depth of reasoning and specialisation. The core Copilot Chat experience is like a well-rounded generalist – great at everyday productivity tasks, such as drafting an email, summarising a document or thread, writing in Word, generating a PowerPoint outline, or pulling insights from a single Excel worksheet. It uses a large language model (LLM) to understand your prompt and the context from the active document, then provides a response.
However, it typically gives a direct answer or action based on available content, without doing prolonged multi-step reasoning. For example, standard Copilot can summarise a document or create a draft from prompts, but if you ask it to perform a very complex analysis that requires digging through multiple files or doing calculations, it may hit its limits. Thats where these specialist agents differ:
Advanced Reasoning vs. Quick Responses: “Standard” Copilot Chat is designed for quick assistance within the flow of work (one-shot answers or short tasks). In contrast, Researcher and Analyst use advanced reasoning algorithms (chain-of-thought) that allow them to work through a problem in multiple steps). They will plan, execute sub-tasks (like searching sources and creating and executing code), and then refining its output. This means they can handle questions or tasks that the regular Copilot would either answer superficially or not manage at all.
Tool Use and Data Access: These specialist agents have access to a much broader set of information and models. Researcher can tap into web search and internal knowledge bases simultaneously, something standard Copilot doesn’t proactively do by itself. Analyst can use the equivalent of a built-in scripting engine (Python) to manipulate data. These abilities let the agents produce more accurate, data-backed results (for instance, Analyst can compute exact figures or generate a pivot table behind the scenes, rather than guessing).
Use Case Focus: Out of the box, Microsoft 365 Copilot has a breadth of capabilities across Word, Excel, PowerPoint, Outlook, Teams, etc., but each in a somewhat scoped way – e.g. helping write, summarise, or create within that app. It is “broad but shallow”. Researcher and Analyst are narrower but much deeper in their domains. If you don’t need multi-step research or advanced data analysis, you might not need to use them and the regular Microsoft 365 Copilot Chat or in app Copilot experience might suffice. But if you do have those needs, these agents provide a level of expertise that feels like a specialist joining your team.
For example, consider interpreting a complex financial report: Standard Copilot in Excel can summarise that report or maybe answer something about it if asked directly, but Analyst could take multiple financial files (ledgers, budgets, forecasts) and do a cross-file analysis, then produce a summary and suggest optimisations – a far more sophisticated outcome.
Interaction Model:Using Researcher/Analyst is a bit like launching a specific mode of Copilot meant for heavy tasks. They’re accessible via the Copilot app’s Agent Store or as pinned which is a different entry point than simply typing to Copilot in Word. This interface guides the user to ask bigger questions (“Help me investigate X” or “Analyse Y data for Z”) rather than the smaller in-app prompts. The agents also tend to show their working process (especially Analyst showing its code or reasoning steps), whereas standard Copilot just delivers the end answer in a friendly tone. This transparency is great for users who want to trust the results – you can literally see how Analyst arrived at an answer, step by step.
Analyst vs. Copilot for Finance – What’s the Difference?
With the introduction of the Analyst agent, you might also hear about Microsoft 365 Copilot for Finance – another AI offering that targets data and analytics, but specifically for finance professionals. It’s important to clarify how the Analyst agent and Copilot for Finance differ, because their names might seem related. In fact, they serve different needs:
Microsoft 365 Copilot for Finance (formerly introduced simply as “Copilot for Finance”, now in preview) is a role-based Copilot experience tailored for finance departments. This was announced in early 2024 as a way to “transform modern finance” by bringing generative AI into the daily workflows of finance teams. Unlike the Analyst agent – which any user with Copilot can use for various kinds of data analysis – Copilot for Finance is a separate add-on Copilot designed to integrate deeply with financial systems and processes. It essentially combines Microsoft 365 Copilot with a specialized finance agent and connectors to your financial data.
From what I have managed to assess these are the main differences between the Analyst agent and Microsoft 365 Copilot for Finance:
Aspect
Analyst Agent (Microsoft 365 Copilot )
Microsoft 365 Copilot for Finance
Purpose & Domain
General-purpose data analysis for any domain or department. Helps users analyse spreadsheets, databases, or other data to get insights.
Designed to work across certified and connected systems such as Microsoft 365 Dynamics, Salesforce and some others
Integration and Data
Works on provided or accessible data in Microsoft 365 (e.g. Excel files, CSVs, SharePoint data). No built-in direct connection to ERP systems – user typically uploads data or points to files for analysis
Connected to enterprise financial systems and data sources. Draws context from ERP systems (like D365 Finance & SAP) and the Microsoft Graph . Integrates in real-time with live finance data, assuming connectors are set up. Optimised for D365 Finance (seamless data access). Can connect other systems via custom or pre-built connectors).
Features and Skills
Uses chain-of-thought AI reasoning and Python code execution to perform analytics. Ideal for ad-hoc data analysis: e.g. combining sales data with customer data to find trends, identifying anomalies in operational data, generating charts from raw data. Acts as AI data analyst for any project.
Uses AI to streamline finance-specific processes and provide insights within finance workflows. For example, can automate variance analysis in Excel, perform reconciliations between systems, generate reports, summaries, and even draft emails for collections with relevant account info. Understands accounting principles and the company’s financial data.
User Experience
Accessed through the Copilot app as one of the agents (no special deployment beyond having Microsoft 365 Copilot license). The user asks questions or tasks in natural language and often provides the data files to analyze. The output is an interactive analysis in Copilot chat with optional visuals and code transparency.
Integrated into the tools finance teams use: primarily Excel, Outlook, and Teams in the context of finance work. For example, in Excel a finance user might invoke Copilot for Finance to run a budget vs. actual report or find anomalies in ledger data. In Outlook, it can summarise a customer’s account status from ERP data to help a collections officer. Works in flow of existing finance tasks, bringing AI where needed.
Availability & Pricing
Included as part of the Microsoft 365 Copilot (the Analyst agent is available to any user who has Copilot enabled). General Availability as of mid-2025. Usage is capped at 25 queries/month for heavy reasoning tasks.
Available as add-on to Copilot targeted at enterprises. Paid offering for organisations that use Microsoft 365 and want AI assistance in finance for supported systems like D365.
Dependencies on Microsoft Dynamics
Not dependent on Dynamics 365 – Analyst can analyse any data you give it. If your financial data is in Excel exports from SAP or Oracle, Analyst can still work with those exports, but it won’t directly pull from those systems on its own.
Deeply integrates with D365 Finance & Operations. Designed to plug into D365 modules so can act within that ecosystem (e.g., directly reading transaction data, posting results back). Through “connectors”, it can interface with other ERP or CRM systems too. Advantage is native use with D365 – without manual data exporting or integrations
To put it simply, the Analyst agent is like an AI data expert you can use for virtually any type of analysis by feeding it data, whereas Copilot for Finance is a comprehensive AI-powered solution built into Microsoft’s ecosystem to assist with a company’s financial operations in real-time. They might overlap in the sense that both can do things like variance analysis or finding trends in financial figures, but the context is different: Analyst would do it when you ask and give it the data (say, a couple of Excel files containing financial info), while Copilot for Finance would do it as part of your normal finance workflow, already knowing where the data is (in your ERP and Excel models) and proactively helping you in that domain.
Does Copilot for Finance only work with Dynamics 365?
No. Copilot for Finance is not limited to Dynamics 365, though that’s a primary integration. It brings together Microsoft 365 Copilot with a finance-focused agent that connects to your existing financial data sources including ERP systems like Dynamics 365 and SAP. So if your company runs SAP for finance, Copilot for Finance can use that data as well. Microsoft has built it to be flexible via connectors, because they know not everyone is on Dynamics. That said, organizations using Dynamics 365 Finance get a more seamless experience – Copilot for Finance can sit right inside the D365 Finance interface and offer insights without any data transfer.
In summary, Copilot for Finance is cross-platform in terms of data sources, but tightly integrated with Microsoft’s own finance solutions for maximum benefit. It’s an example of Microsoft creating role-specific Copilots (others being Copilot for Sales, Copilot for Service) that extend the core Copilot capabilities into specialised business functions.
Further Reading and Sources
As well my own experimentation, the following sources were also inferred and read when writing this blog. I did also use Copilot to help tweak the tone and flow.
