Download "Data Agents & Copilot Studio: Better Together for Intelligent Business Experiences #microsoftfabric"
%3Aformat(webp)%2Fi.ytimg.com%252Fvi%252FZbVUl52Q-hQ%252Fmaxresdefault.jpg&w=1139&q=75)
Similar videos from our catalog
%3Aformat(webp)%2Fi.ytimg.com%252Fvi%252F5F9F3EQhTSg%252Fsddefault.jpg&w=1139&q=75)
%3Aformat(webp)%2Fi.ytimg.com%252Fvi%252FAakV-3RtmuI%252Fmaxresdefault.jpg&w=1139&q=75)
%3Aformat(webp)%2Fi.ytimg.com%252Fvi_webp%252FB2x6ggpKFqU%252Fsddefault.webp&w=1139&q=75)
%3Aformat(webp)%2Fi.ytimg.com%252Fvi%252FKIoNyJc1tkk%252Fmaxresdefault.jpg&w=1139&q=75)
%3Aformat(webp)%2Fi.ytimg.com%252Fvi%252FRxNbi-d4A94%252Fsddefault.jpg&w=1139&q=75)
%3Aformat(webp)%2Fi.ytimg.com%252Fvi%252FSYWsGh87BlM%252Fmaxresdefault.jpg&w=1139&q=75)
%3Aformat(webp)%2Fi.ytimg.com%252Fvi%252FjQ3AzjrZCBQ%252Fmaxresdefault.jpg&w=1139&q=75)
%3Aformat(webp)%2Fi.ytimg.com%252Fvi_webp%252Fjrcr28HGtEA%252Fmaxresdefault.webp&w=1139&q=75)
%3Aformat(webp)%2Fi.ytimg.com%252Fvi_webp%252Fq2LlvqQ-QH8%252Fmaxresdefault.webp&w=1139&q=75)
%3Aformat(webp)%2Fi.ytimg.com%252Fvi%252FtBZy_FdbA9k%252Fmaxresdefault.jpg&w=1139&q=75)
Video tags
Subtitles
00:00:10
[music]00:00:12
Hey mates, I'm Alex00:00:14
>> and I'm Gaston. [clears throat]00:00:16
>> Welcome to Powermates.00:00:19
>> This is the place to learn and share00:00:21
about fabric and power platform. If this00:00:23
is your first time here, don't forget to00:00:24
subscribe, like, and share this channel00:00:27
with your friends and colleagues. So00:00:30
today, Alex, we are going to be about to00:00:32
explore one of the at least from my end00:00:35
the most exciting innovations in the00:00:38
overall Microsoft ecosystem. But that00:00:40
means the combination between our fabric00:00:42
data agents and copilot studio.00:00:45
>> If you have ever wondered how to turn00:00:49
raw data into intelligent, you know,00:00:52
insight or maybe in the future automated00:00:55
actions, I think this is a video for00:00:58
you. And you know we've been talking00:01:00
about this that the fabric data agents00:01:02
is is is a game changer. The the way we00:01:05
think about how to bring smart you know00:01:08
uh connections and making more decisions00:01:11
and connect all your data process00:01:13
semantic models and decisions in real00:01:16
time. This video again is is for you. So00:01:20
yeah, so they don't just you know uh00:01:23
read data or or or or or interpret it or00:01:26
act on it even you can trigger workflows00:01:30
uh autonomously. So a and and the best00:01:33
part for the business people came from00:01:37
low code and also from the data side of00:01:40
the house no code is required. So know00:01:43
and so in in today world data is00:01:46
everywhere but insight on some point uh00:01:49
often come too late.00:01:52
>> Yeah and you know with the data agents00:01:54
and this combination between data agents00:01:56
and copilot studio you can create00:01:58
multiple solution that respond uh00:02:01
quickly to to any kind of decision that00:02:04
you need to make in top of your data. So00:02:06
imagine for example a sales dashboard00:02:08
that not only shows trends but also send00:02:12
alerts or updates CRM records or even00:02:16
draft emails and all of these you can00:02:19
automate the overall process.00:02:21
>> Let's see how it work. You want to let00:02:23
us know how it works?00:02:24
>> Yes. Yeah. Let's let's go and find out00:02:26
you know how we linked all together the00:02:28
perfect data agents and data sets and00:02:30
configurations and you know you we can00:02:33
see within minutes how we can build this00:02:37
agent from scratch. So let's go over to00:02:39
my machine. So again this is our fabric00:02:42
uh landscape. So in the fabric landscape00:02:45
in this case I am uh accessing one of00:02:48
the workspace that we have over here. We00:02:50
already have a solution that we've been00:02:53
building with and showcase with Alex uh00:02:55
in terms of landing data from stocks00:02:58
live. This is a live uh realtime00:03:01
intelligence solution with uh a stream00:03:03
live connection. Then we build a00:03:06
lakehouse and and the dumping data from00:03:09
stocks into a lakehouse at the same time00:03:12
we are dumping data into a KQL database.00:03:15
uh and then uh of course the lakehouse00:03:19
has the the structure as it is a SQL uh00:03:22
analytics endpoint we are creating a00:03:24
semantic model on top of that and then I00:03:26
finally get a power via report uh in00:03:30
this case I'm going to showcase how to00:03:32
create the the fabric uh data agent in00:03:35
top of a KQL database because it's not00:03:38
so common so first of all in the00:03:40
workspace environment I can go here and00:03:44
click on the new item option in the top00:03:48
left of my screen. New item. Then going00:03:51
to all items. I can go to the data00:03:55
agents to find data agents. And then in00:03:58
top of this I can create my first stocks00:04:03
powermates data agent and create the00:04:07
agent from a scratch here. So first of00:04:10
all you need to create the data agent.00:04:11
The next steps in this process is adding00:04:14
a data source. So when I click the data00:04:16
source option top left of our screen, I00:04:20
can go here and get the data source. I00:04:24
can in this case remember that I00:04:26
mentioned a couple of times that I'm00:04:27
going to connect with a KQL database00:04:30
instead of the common uh semantic models00:04:32
or connect to the lakehouse. Remember00:04:34
that the fabric derations allow you00:04:36
today to connect to all these kind of00:04:38
items. In this case in uh I'm going to00:04:41
connect with the KQL database and click00:04:44
in add option. And then after I add the00:04:47
option it's going to be adding the00:04:51
house database. I can click on that one00:04:56
and I can start setting up the process00:04:58
because I already have this up and00:05:00
running. First of all I'm going to00:05:02
showcase this is my KQL database that I00:05:04
have in another tab with all the00:05:06
information from different stocks. some00:05:09
of them all the symbols of the stocks if00:05:12
they belong to any of the sectors and00:05:15
then the bit price the bit size and all00:05:17
the data that is coming into the event00:05:20
house after this we set up the agent as00:05:24
I mentioned before we set up the agent00:05:26
connecting to one of the tables in the00:05:28
event house remember and today is really00:05:31
important to do the setup of this you00:05:34
know the setup here you can include the00:05:37
Asian instruction instructions, the data00:05:40
source instructions and the sample00:05:42
queries. This is really important for00:05:45
the agent to have some context on what00:05:48
are the answers that the agent is going00:05:52
to give the end user. So if you check00:05:54
the agent instruction, I can set up the00:05:57
instruction in markdown language right00:05:59
now. So you can define how the agent is00:06:04
going to react in my uh in my thing00:06:07
here. I am connecting the dots in terms00:06:09
of helping the agent to understand what00:06:12
are the instructions for an enduser00:06:14
perspective. Then I'm going to click in00:06:16
the data source instruction and I can00:06:18
give data source descriptions and then00:06:22
data source instructions. again I can00:06:25
complete and remember it's really00:06:27
important to uh you know spend some time00:06:30
the defining the description and00:06:32
instruction on the data source and then00:06:34
the example of queries in my case I am00:06:37
giving the agent couple of of uh queries00:06:41
uh what the end user can ask leveraging00:06:44
natural language and then what is going00:06:47
to look like the KQL queries that you00:06:49
need to run to answer those questions in00:06:52
my case I am defining hey what I define00:06:55
the top 10 symbols with the highest bit00:06:58
price in the software service sector and00:07:01
then I gave the instruction of what is00:07:04
going to look like the KQL query that00:07:06
answer that questions. The same happens00:07:09
here. Get the last 20 updates for a00:07:11
specific symbol sort by time and I00:07:14
answer that with a KQL query that allow00:07:18
the agent to understand how to process00:07:21
the the data. Then if I uh love to this00:07:28
you can see in the uh right of uh my00:07:32
screen that you can define the test of00:07:36
the Asian response. So you can go in the00:07:39
left and you can see what are the00:07:40
historical trends across all my data. Uh00:07:44
which symbol had the highest speed part.00:07:46
So what I'm doing here is I'm testing00:07:48
the agent before we publish the agent.00:07:53
And the final uh step on this process is00:07:57
hit the publish option right away here.00:08:02
After we publish the agent, what is00:08:04
going to happen? The next steps is um00:08:08
leverage this agent from another00:08:11
platform. But before going to the00:08:13
copilot studio side of things, I would00:08:15
love to showcase that even if I publish00:08:18
this agent that allow me to go to00:08:21
PowerBI00:08:23
and click this option over here00:08:26
and this option is going to be00:08:29
leveraging copilot within the PowerBI.00:08:33
So you can click here,00:08:36
click on the agent itself and I can00:08:39
interact with the agent in natural00:08:42
language within PowerBI. So meaning that00:08:45
the copilot experience in PowerBI allow00:08:49
you to ask natural language to your00:08:52
reports to your semantic models but also00:08:55
to your fabric data agents today. So you00:08:57
can run those natural language uh00:09:00
questions and this copilot experience is00:09:03
going to go and bring the data from the00:09:05
fabric dation itself. Then as I00:09:08
mentioned before once you publish the00:09:10
agent you're going to be able to go and00:09:13
this is again00:09:15
copilo studio. So the experience within00:09:18
Copilo studio and correct me if I am00:09:22
doing something wrong here Alex because00:09:25
you are expert in this field but when00:09:27
you create the fabric uh data agent and00:09:30
you publish that you define the overall00:09:35
uh copilo studio agent you are asking00:09:40
and you are answering some of the00:09:42
description for the agent you're picking00:09:44
up the model but the most important00:09:46
thing is here you00:09:48
Yeah, let me let me show you that00:09:50
exactly Gaston how how that work. Gaston00:09:52
just mentioned okay you can publish your00:09:54
your your data agent and you can use00:09:58
directly into PowerBI. So that's great.00:10:01
So maybe your next question is okay guys00:10:04
but uh what happen is I want to use it00:10:08
on M365 copilot or even some other uh uh00:10:13
other platforms I don't know like I want00:10:15
to embed that into SharePoint or I want00:10:17
to embed that into my dynamic 36500:10:21
homepage or power pages you know we have00:10:23
a we have a bunch of different scenarios00:10:25
and use cases where you may need the the00:10:28
the data aation connected with other00:10:31
platforms. So in this case is where uh00:10:34
compiler studio take action is because00:10:36
compiler studio is not going to do any00:10:38
magic for the data agent because the00:10:41
data the data agent uh uh training00:10:44
itself and all was a piece that Gaston00:10:47
already show. So if you want to publish00:10:50
to other platform or even connect with00:10:52
M36500:10:53
or also maybe another another good00:10:56
example is uh I have my copilot studio00:11:01
that uh users are using it for uh00:11:05
request information for from other00:11:07
system from internal policies or I don't00:11:10
know different uh scenarios but you want00:11:12
to also incorporate uh an add into your00:11:16
copilot studio capabilities this00:11:18
particular agent you want to include the00:11:20
data agent. So let's assume that you00:11:23
want to start from a scratch. You can00:11:25
click came here to agent. Then you came00:11:27
here to create a blank agent. Let's00:11:31
create one black agent for demo on00:11:33
propose. Then as as Gaston mentioned,00:11:36
you can start adding your descriptions,00:11:39
the trigger and there that's another00:11:41
important uh part here are interactions00:11:44
where you can give more directly insions00:11:47
to to the agent on what you need from00:11:50
the agent or what the agent have to do.00:11:52
But the the important thing here when we00:11:55
are trying to connect with a data agent00:11:57
is let's came here into agent. Let's00:12:00
click on agents. Let's click on add.00:12:03
Okay. Then as you can see here we have00:12:06
new childation that mean that you can00:12:08
create like childation like is pretty00:12:10
pretty much the same paradigm as we have00:12:13
when we create child flows on power00:12:15
automate or something is like trying to00:12:17
divide a conquer a problem but also here00:12:20
we have connected agents and here we00:12:23
have this piece here connect to an00:12:26
external agent.00:12:28
So we are going to click here and as you00:12:30
can see here we have Microsoft fabric,00:12:34
we have Microsoft Foundry and Asian to00:12:36
Asia. Okay. So Microsoft fabric is what00:12:40
Gaston uh show us how to create a data00:12:43
agent also the next level maybe of00:12:47
automation or create agent is using00:12:49
Microsoft Finry and so you can create00:12:52
like on some point a smarter uh agent00:12:54
and also agent to Asian connection. So00:12:57
let's select Microsoft Fabric.00:13:00
I'm already connected here. I'm going to00:13:03
use that connection.00:13:06
Then click next. And then you should see00:13:09
your fabric uh data.00:13:13
And you can select as you can see here I00:13:15
have two but the one who Gaston sh00:13:18
created was this one fabon mates. So we00:13:22
going to click on this one stocks data00:13:25
agent add and configure and that's it00:13:28
you know your copilot studio it's00:13:31
already connected with your uh data00:13:34
agent at this time you can just publish00:13:36
and start asking questions to your00:13:39
copilot studio but at the end of the day00:13:41
it's going depends of the question when00:13:44
the compiler studio consider that okay00:13:46
this qu because of the of the00:13:48
intelligent root method and all is going00:13:51
to call the data agent and get your00:13:54
answer. So that's it. It's pretty00:13:56
simple. From now it's just publish. You00:13:58
can publish your your copilot studio.00:14:00
You can also as I mentioned at the at00:14:02
the beginning, you can decide which00:14:04
other platform or channels you want to00:14:06
publish your copilot studio. But what00:14:09
they are doing is probably uh allowing00:14:11
users on SharePoint or teams or M36500:14:15
copilot to use your data agent too. And00:14:17
that is the point on how why to use the00:14:20
copilot studio and also because you can00:14:22
add other intentions and other00:14:24
automations with the same data agent. So00:14:27
that's it uh powermate for for today. So00:14:31
you know that with fabric data agent and00:14:33
copilot studio you are not just00:14:36
analyzing data you can also act on on it00:14:40
act on the day00:14:41
>> and you know this is the kind of the00:14:43
future of where where Asians are going00:14:46
and you know how to automate overall00:14:48
process and it is available today so go00:14:50
there you know be hands on and start the00:14:53
process of building your your own00:14:55
agents. Yeah, exactly. And if this help00:14:58
you, you know, again uh hit the like,00:15:00
subscribe, hit the notification bell.00:15:02
It's free. So that helps other to reach00:15:05
uh this kind of material. So maybe them00:15:09
some others outside that want to learn00:15:11
more. So stay powerful and join us on00:15:14
this journey00:15:15
>> together. Let's unlock the full00:15:17
potential of power platform and [music]00:15:19
Microsoft Power.Description:
What happens when Data Agents in Microsoft Fabric meet Copilot Studio? You get a powerful, end-to-end way to turn raw data into actionable, conversational intelligence. In this video, I’ll show how Data Agents and Copilot Studio work better together, enabling you to build copilots that don’t just answer questions — they reason over data, trigger actions, and support real business decisions. If you’re building intelligent solutions with Microsoft Fabric, Power Platform, or Copilot Studio, this is a must-watch. Data Agents & Copilot Studio: Better Together for Intelligent Business Experiences #microsoftfabric
Mediafile available in formats
* — If the video is playing in a new tab, go to it, then right-click on the video and select "Save video as..."
** — Link intended for online playback in specialized players
Questions about downloading video
How can I download "Data Agents & Copilot Studio: Better Together for Intelligent Business Experiences #microsoftfabric" video?
http://univideos.ru/ website is the best way to download a video or a separate audio track if you want to do without installing programs and extensions.
The UDL Helper extension is a convenient button that is seamlessly integrated into YouTube, Instagram and OK.ru sites for fast content download.
UDL Client program (for Windows) is the most powerful solution that supports more than 900 websites, social networks and video hosting sites, as well as any video quality that is available in the source.
UDL Lite is a really convenient way to access a website from your mobile device. With its help, you can easily download videos directly to your smartphone.
Which format of "Data Agents & Copilot Studio: Better Together for Intelligent Business Experiences #microsoftfabric" video should I choose?
The best quality formats are FullHD (1080p), 2K (1440p), 4K (2160p) and 8K (4320p). The higher the resolution of your screen, the higher the video quality should be. However, there are other factors to consider: download speed, amount of free space, and device performance during playback.
Why does my computer freeze when loading a "Data Agents & Copilot Studio: Better Together for Intelligent Business Experiences #microsoftfabric" video?
The browser/computer should not freeze completely! If this happens, please report it with a link to the video. Sometimes videos cannot be downloaded directly in a suitable format, so we have added the ability to convert the file to the desired format. In some cases, this process may actively use computer resources.
How can I download "Data Agents & Copilot Studio: Better Together for Intelligent Business Experiences #microsoftfabric" video to my phone?
You can download a video to your smartphone using the website or the PWA application UDL Lite. It is also possible to send a download link via QR code using the UDL Helper extension.
How can I download an audio track (music) to MP3 "Data Agents & Copilot Studio: Better Together for Intelligent Business Experiences #microsoftfabric"?
The most convenient way is to use the UDL Client program, which supports converting video to MP3 format. In some cases, MP3 can also be downloaded through the UDL Helper extension.
How can I save a frame from a video "Data Agents & Copilot Studio: Better Together for Intelligent Business Experiences #microsoftfabric"?
This feature is available in the UDL Helper extension. Make sure that "Show the video snapshot button" is checked in the settings. A camera icon should appear in the lower right corner of the player to the left of the "Settings" icon. When you click on it, the current frame from the video will be saved to your computer in JPEG format.
How do I play and download streaming video?
- in video formats, hover your mouse over "Streaming Video**";
- right-click on "Copy link";
- open VLC-player;
- select Media - Open Network Stream - Network in the menu;
- paste the copied link into the input field;
- click "Play".
- copy the video address (URL);
- select "Open Network Stream" in the "Media" item of VLC player and paste the link to the video into the input field;
- click on the arrow on the "Play" button and select "Convert" in the list;
- select "Video - H.264 + MP3 (MP4)" in the "Profile" line;
- click the "Browse" button to select a folder to save the converted video and click the "Start" button;
- conversion speed depends on the resolution and duration of the video.
For this purpose you need VLC-player, which can be downloaded for free from the official website https://www.videolan.org/vlc/.
How to play streaming video through VLC player:
To download streaming video via VLC player, you need to convert it:
Warning: this download method no longer works with most YouTube videos.
What's the price of all this stuff?
It costs nothing. Our services are absolutely free for all users. There are no PRO subscriptions, no restrictions on the number or maximum length of downloaded videos.