Copilot Cowork Walkthrough

Hey everyone, in this video I want to talk about co-pilot co-work an awesome new capability that is exposed today as a separate agent available under

co-pilot. We can see it super quick

co-pilot. We can see it super quick here. I'm in a frontier tenant and I can

here. I'm in a frontier tenant and I can see under my agents I have this nice new co-work capability.

So what exactly is this? So if I think about co-pilot in general, we have a number of different capabilities. It's fantastic for

capabilities. It's fantastic for brainstorming, finding information, accomplishing a task, summarizing. I

have obviously the interactive. I can

have like a a chat experience both directly in copilot within all the different experiences. There's things

different experiences. There's things like analyst to help me as my own personal data expert. There's things like researcher

expert. There's things like researcher where I can go and do that very deep longer thinking understanding how to solve and get me all the information

about a certain thing. They're tuned for different types of tasks. And so now what we have as another type of agent is

fwork.

And this is for when I have very complicated requests potentially going across multiple systems, many many different steps required to solve it for

potentially a very very long time. Now,

straight away with the name co-pilot co-work, the question is going to be, is it just a skinned clawed co-work? Not at

all. This is Microsoft C-Pilot's own implementation of a co-work functionality, i.e. many tasks over a

functionality, i.e. many tasks over a long period to address a very complicated thing you want it to do. So

the way it's working is it has its own co-work agent runtime.

So it's a secure isolated sandbox where it does the things. This is the orchestrator of everything it's going to do. Now yes, this co-work agent runtime

do. Now yes, this co-work agent runtime obviously has to go and talk to a reasoning model, a large language model.

So it's going to go and for that reasoning talk to a large language model. The

specific large language model is likely going to change over time as models evolve, new ones come out, things improve. Now part of what has made

improve. Now part of what has made co-pilot co-work possible with this very longunning, very complicated set of task

is yes, Anthropic made a big leap. I

think it was November 2025 for complex reasoning. It's Opus 4.6 6 model made a

reasoning. It's Opus 4.6 6 model made a huge leap in the ability to reason for a very long time. I think days before it went off the rails.

So now what you can have is models have this agentic loop that can reason to complete the task. It can tell me what to do next once it's worked it out.

And so today at time of recording, the co-pilot co-work uses the anthropic model for its reasoning capabilities to create the plan

given the context and tools that are available and to work out what it should do.

Now, Copilot Co-work natively understands and leverages work IQ and that native grounding on work IQ.

So, think about yes all of the M365, Dynamics 365, etc., etc. knowledge, but then the context, the the things it has

learned about how data relates to other data, how people relate to data, how people relate to people, the rhythm of business, how work is done, the types of

activities, and then specific skills and tools. It is grounded on all of that

tools. It is grounded on all of that information.

And it's not just using the work IQ API piece by piece. It is also natively hooked into things like SharePoint

both from a data and API to do things, One Drive, but then things like Outlook, Teams,

um things like Fabric IQ and Dynamics 365. Five, it can use third party uh connectors, services, APIs and so

this is a big deal about this directly built on top of it. Other

solutions will use things like MCP APIs, maybe computer use to interact with client apps to do certain things to complete actions.

The copilot co-work is natively using the solutions. is going to be more

the solutions. is going to be more consistent, more reliable for any of those interactions.

So you hear an analogy sometimes it's built natively on all of this. So it's

got the full context rather than that per API call sipping through a straw. So

you get one query responded two at a time. So the time taken, you may not

time. So the time taken, you may not find all of the the perfect information you want. Now another big thing to

you want. Now another big thing to understand about copilot co-work it is running in the cloud.

It is not running locally on your machine consuming your local resources having access to everything on your local machine. It is purposefully a

local machine. It is purposefully a cloud agent and because it's running in the cloud it's therefore observable.

It's auditable. I can use perview on what it's doing. I get better compliance, better manageability.

And again, because it is a cloud agent with all of these capabilities, but it is not talking directly to your local machine. There's no local device access.

machine. There's no local device access.

As it creates artifacts, it's going to actually go and save them into your one drive.

And so the things it creates become additional knowledge. it will get the

additional knowledge. it will get the proper labels and we can see this. So if

I jump over for a second and I just go and look at my one drive folder and I'll look at my documents. I'll see

co-work session folders for where I have done work. So there's my sessions and these

work. So there's my sessions and these are the different interactions I have had with it. If I select one of these folders, I see any data about inputs. I

can see the outputs and there's a number of different files here based on things and work I have had co-work do for me

and we're going to come back to that.

Now, it does have the same concepts like skills and plugins with anthropics co-work. So the nice thing here is it

co-work. So the nice thing here is it will be able to use those skills and plugins from the other platform within co-pilot co-work.

Now one of the things I think to really understand this is to see it in action to see it doing some really long reasoning multi-step work how it breaks

a problem down into various steps. So

what I have prepared is a folder and now you'll understand why I'm wearing like a superhero type t-shirt.

I have a villain incident report folder with a series of 20 different incidents involving super villains. Just open one

of these up. And it talks about what happened, where it happened, when it happened, sort of a description,

injuries, damage, how it broke down in terms of exactly what happened, current status. So there's an incident report.

status. So there's an incident report.

says 20 of these instant reports I have created. And what I want to do,

created. And what I want to do, as is pretty obvious, I'm going to get co-work across all those instant reports. So,

I'm going to ask it for a word document and a PowerPoint presentation, diving into everything, looking for

certain patterns. So, let's go and look

certain patterns. So, let's go and look at our cowork. So, we're going to start a brand new session and I'm going to ask

it about all of those different villain reports. Now, I'm not going to type all

reports. Now, I'm not going to type all this in. I'm going to paste it. I've

this in. I'm going to paste it. I've

prepared this prompt already.

And what we can see is I'm asking it, I'm telling it, hey, they're in my one drive folder.

So create an executive overview word doc and a PowerPoint presentation. Analyze

it for correlations. Look for patterns across geoclustering, severity by villain, uh trends, tone should be authorative, top five priority villain

ranking, recommended resources allocation by region, etc. So I'm going to just tell it to stop

go and work on this particular ask. So

now it's thinking and you can see straight away it starts to break down what it thinks it should be doing, the types of tasks it's going to create over

here a little window so I can see everything it's going to go and work on.

But you'll notice for a second I still have a prompt. It's thinking. It's doing

a prompt. It's thinking. It's doing

things but it's not offline to me. So I'm going to actually give it another instruction.

And I've decided actually what would be really cool as well is I would like an interactive web app that shows all this in a HTML file. So

I'm going to cue this up. So I'm now sending it that additional and it accepted it straight away. So it's still working on the other task, but now I've

added to what I asked it to do. I can

work with it. I can interrupt it. Maybe

I could ask it to, hey, go and schedule a meeting once this is done with Bruce and Clark to discuss all of the things you're going to find. So, this is just going to go off and it's going to carry

on. It's going to think for probably

on. It's going to think for probably many, many minutes. So, I'm going to cheat. I'm actually going to stop this

cheat. I'm actually going to stop this because if I go to tasks, as you would expect, I did this earlier on today.

Now when I look at this tasks view firstly these are all the ones that I've done before you can see I basically ran exactly the same request uh earlier on this morning

but I can also view it in a board view.

So the ones that are currently in progress ones that have completed one of the first things I ever tried with it was a financial analysis and I

could see again the full progress of everything it did. There's the output folder of the deliverables it created for me and I could go and see all of the

work it did. It took half an hour to do a financial sort of deep dive report for me. Massive numbers of steps and

me. Massive numbers of steps and investigations and information here, but let's focus on the same thing you just

saw me ask it to do.

So there's all the output. So we go back. I did exactly the same thing. I

back. I did exactly the same thing. I

asked it the same. Hey, 20 villain reports. I waited for one minute. Then I

reports. I waited for one minute. Then I

added on this idea of a self-contained HTML file.

And here you could see it did that same kind of thinking about what it should do, all of the details.

It went and retrieved the contents of the data. It tried different ways to get

the data. It tried different ways to get the data. It then did various query

the data. It then did various query graphs to get information from it.

It read the results.

You created scripts to do things, all of the data. Then it starts structuring what it wants to create, just really working out. It went through

the various incidents, all the different correlations, just a massive amount of work going on, all these different things over a fairly long period of

time. I think this maybe took 10 15

time. I think this maybe took 10 15 minutes in total to complete what ended up being as we scroll down.

So it's creating the word doc creating the presentation there's the word there's the powerpoint there's the actual application it

created until it delivered everything.

So it delivered my word doc my powerpoint and that HTML file that I asked it to create. And so there were

the outputs. So we can open up

the outputs. So we can open up there's the word doc.

So it gave me that full analysis really nicely presented very clear all the information I asked it for the prioritizations.

It created me the PowerPoint document again. Same nice formatting. You can go

again. Same nice formatting. You can go through very clearly, see all of the different clusterings of information, which is exactly what I

asked it to do. However,

the app didn't actually work. And so,

you see, there was a second prompt, and all I did was say, "The HTML map does not seem to work. Can you fix it, please?"

please?" and it then went away and once again reasoned for a certain amount of time, found some problems

and it fixed it.

So again, it is going through looked at the different issues that it may find and fixed all of the problems. So I then had the incident map app that it created

for me and you can see different options. I can run it over a certain

options. I can run it over a certain period of time.

It's going to show me the verities and I can just hit play and it starts over a time period showing me all of those instance on a nice little map

the amount of damage. So there was a increased clustering of them and so I get all 20 incidents. I can select one

to see the detail about it.

But it's just this fantastic. And again,

I can move the little slider and it created an app for me. One

prompt.

Hey, look at all those 20 different files. And then, oh, I added an

files. And then, oh, I added an additional ask into it. Say, hey, go and create me an app as well. while it was thinking on the first thing to generate

all of that content, the word, the PowerPoint, and my app. And when the app didn't work the first time, hey, I just asked it to fix it, and it was done. And

again, it's written into my one drive.

That was actually the folder I showed you earlier. And [snorts] if you're

you earlier. And [snorts] if you're curious, I used co-work to create the 20 incident reports. Again, I just gave it a single

reports. Again, I just gave it a single prompt.

I'm working on a co-work demo. I need 20 different incident reports for DC bad guys that have dollar damage, what happened and when. I'm going to use it to create Word doc and PowerPoint and a

fun web app. Can you create for me? And

it went and thought about it and that was the only prompt I gave and it went and created me the 20 documents that you see. It noticed it had a problem on one

see. It noticed it had a problem on one of them and it's saying, "Hey, there was a transient issue. You need to go and fix and rename that." So, I actually

used co-work for the prep that you saw to actually make it go and do all of this stuff.

So, really crazy powerful. As long as you give it some fairly decent instructions that can have many, many requirements,

it goes and works it all out for you.

That is the benefit here for that longer running more complex. This is what co-work does. Now as mentioned the model

co-work does. Now as mentioned the model is going to change over time. Today is

an anthropic model. They are a subprocessor which means they have the same global data privacy guard rails that Microsoft has internally for all of

your services and your data.

And that's it. I mean, I really just wanted to show it to you for the most part because I think seeing really makes it click the difference with what

co-work brings over existing kind of per task smaller duration interactions to just tell it, hey, I need this result

and it will go and work out how to do it. It really is a complete game changer

it. It really is a complete game changer compared to me doing one tiny piece at a time. So, I hope that helped. As always,

time. So, I hope that helped. As always,

till next video, take care.