Episode 49 - Dataverse MCP with Copilot Studio with Nathan Rose

WEBVTT
00:00:58.719 --> 00:01:04.799
Today we have a special topic called Data Force MTP in Copal Studio.
00:01:04.959 --> 00:01:08.079
And we have a special guest called Nathan Rose.
00:01:08.400 --> 00:01:10.000
Can you please introduce yourself?
00:01:10.640 --> 00:01:10.879
Sure.
00:01:11.120 --> 00:01:12.400
So good to see you, Nicholas.
00:01:12.480 --> 00:01:13.599
Thanks so much for having me on.
00:01:13.760 --> 00:01:14.319
So nice.
00:01:15.280 --> 00:01:15.760
Hello everyone.
00:01:15.840 --> 00:01:16.799
I'm Nathan Rose.
00:01:17.120 --> 00:01:25.439
I am a Microsoft MVP and I'm a functional architect at HSO based here in beautiful Auckland, New Zealand.
00:01:26.799 --> 00:01:27.120
Okay.
00:01:28.000 --> 00:01:32.239
I'm curious to know what's I never heard a top title functional architect.
00:01:32.319 --> 00:01:34.799
So what do you day-to-day conferences of?
00:01:35.280 --> 00:01:36.560
That's a great question.
00:01:36.719 --> 00:01:40.079
I was once asked how that's different from a non-functional architect.
00:01:40.159 --> 00:01:43.280
And I said, well, you know, non-functional architects don't do shit.
00:01:43.519 --> 00:01:50.560
But um seriously, um the idea is um I I come from a low-code background, right?
00:01:50.640 --> 00:01:56.879
So I I don't code um the way some more traditional solution architects would.
00:01:57.200 --> 00:02:03.680
So I I architect the solution, but very much from that functional point of view.
00:02:04.000 --> 00:02:08.479
Um so so your background as a functional consultant.
00:02:08.800 --> 00:02:14.800
Um yeah, so that's that's kind of the difference, I guess, if that makes sense.
00:02:15.120 --> 00:02:19.280
Okay, so anything that's functional working that needs to be working?
00:02:19.759 --> 00:02:27.199
Yeah, so in terms of of what the solution's gonna do, um functionality, all of that, that's that's what I do.
00:02:27.439 --> 00:02:49.120
Um when it comes down to kind of nitty-gritty, what you know, I I would make the decision whether we're gonna do it with code or not, but then once we're once we've decided, hey, we're gonna achieve this by writing writing some C sharp or some JavaScript, I'm gonna hand that off to to a dev or or a more technical architect to to fulfill the requirement.
00:02:49.520 --> 00:02:58.159
Okay, so your day-to-day conversions of like designing it, like the requirement within your team or leading team as well.
00:02:58.560 --> 00:03:00.639
Yeah, yeah, exactly.
00:03:01.439 --> 00:03:08.159
Okay, so today we our theme of this episode is databurst in Kapat Studio.
00:03:08.319 --> 00:03:14.400
I I know a couple of months ago it was released on Microsoft at night, database MTP.
00:03:14.639 --> 00:03:19.120
Uh, do you want to uh just give us an introduction of what Databurst?
00:03:20.159 --> 00:03:21.360
Yeah, absolutely.
00:03:21.520 --> 00:03:29.439
So so for those of you who don't come from the BizApp's business applications background, Dataverse is that shared data layer.
00:03:29.680 --> 00:03:35.120
That is really the magic behind what makes Dynamics 365 and Power Platform so powerful.
00:03:35.360 --> 00:03:38.479
Because we don't have to go writing point-to-point integrations anymore.
00:03:38.560 --> 00:03:54.879
We just build apps on top of the shared data layer and things like accounts and contacts and cases and all that good stuff can be shared between applications naturally without having to build integrations and service buses and things like we would have had to do in the past.
00:03:55.039 --> 00:03:56.639
So that's what Dataverse is.
00:03:56.719 --> 00:04:04.800
And then the product team have released Model Context Protocol for Dataverse to work in Copilot Studios.
00:04:04.960 --> 00:04:08.719
So you may have heard the term model context protocol, MCP.
00:04:08.800 --> 00:04:12.080
It was kind of the the hot topic of 2025.
00:04:12.639 --> 00:04:16.319
And you've probably heard it described as USB-C.
00:04:16.560 --> 00:04:27.759
The idea is that we can plug and play our uh large language models with our existing apps and data and things like that.
00:04:27.920 --> 00:04:43.759
And so Dataverse MCP makes it really easy to connect an agent in Copilot Studio to Dataverse, and it comes with a bunch of preset tools, things that will let you search, things that will let you update records, create records, and things like that.
00:04:43.920 --> 00:04:48.800
And you can do that all through um the Dataverse MCP tool.
00:04:49.040 --> 00:04:55.279
Now, where it gets really cool is I literally just have to write instructions for my agents.
00:04:55.439 --> 00:05:02.959
So I've got agents that can do stuff in my system that all I have to do is write instructions.
00:05:03.040 --> 00:05:06.720
So I don't have to go doing a lot of config, I don't have to do coding or anything like that.
00:05:06.879 --> 00:05:08.879
So I'll give you an example.
00:05:09.120 --> 00:05:19.600
Um, last year I demoed an agent for a government scenario, and this came from a real life scenario with clients that I've worked with here in New Zealand.
00:05:19.759 --> 00:05:35.519
Um, and a common common scenario for government is they've got contact centers where they're using, say, Dynamics 365 customer service to manage cases, say citizens are contacting them for questions to fix things, to that type of thing.
00:05:35.839 --> 00:05:46.800
And you've you've got a common issue where you've got a lot more cases being created, people calling this contact center, then they have agents to deal with them.
00:05:47.040 --> 00:06:00.399
And when they've analyzed their data, they found that a lot of them can be answered from a lot of the cases can be answered from existing knowledge that they have on their website because a lot of government departments have really detailed websites.
00:06:00.560 --> 00:06:00.720
Yeah.
00:06:01.360 --> 00:06:03.439
People just haven't bothered to look.
00:06:03.600 --> 00:06:10.879
And the other thing is that there's an interesting subset of cases where you don't really need a human to respond to it.
00:06:10.959 --> 00:06:14.399
And this actually came out of we were looking at how do we mask profanity.
00:06:14.480 --> 00:06:22.720
So somebody's having a really bad day and they've gone to the website and they've logged a case and they've used abusive language.
00:06:22.959 --> 00:06:26.079
And, you know, you don't want to have to read that all day, right?
00:06:26.160 --> 00:06:28.079
Nobody wants to have to wade through that.
00:06:28.319 --> 00:06:35.600
And um, so there's this subset of cases where somebody's just having a bad day and they just want to complain to somebody.
00:06:35.680 --> 00:06:37.759
You know, they don't have a question that can be answered.
00:06:37.839 --> 00:06:40.240
There's not something that they actually want you to do.
00:06:40.480 --> 00:06:44.000
They just, you know, they're they're just having a bad day inventing.
00:06:44.079 --> 00:06:52.879
You know, I had, you know, I went to the swimming pool and the water was too cold, and so now I'm really grumpy and complaining about it.
00:06:53.120 --> 00:06:55.759
Okay, you know, what do you expect us to do about that?
00:06:56.000 --> 00:07:01.360
And so what you can do with those is you can automatically generate an empathetic response to the person.
00:07:01.439 --> 00:07:03.439
You don't need a human in the loop doing that.
00:07:03.680 --> 00:07:07.120
So I built an agent that did these things, right?
00:07:07.199 --> 00:07:12.639
It would basically look at an incoming email request and it would determine what does this person want?
00:07:12.879 --> 00:07:14.800
Do they have a question I can answer?
00:07:15.120 --> 00:07:16.639
Do they need to create a case?
00:07:16.800 --> 00:07:18.639
Maybe they're reporting something that's broken.
00:07:18.720 --> 00:07:19.040
Yeah.
00:07:19.360 --> 00:07:23.040
Or do they are they just having a bad day and complaining, right?
00:07:23.519 --> 00:07:35.839
And once it made that determination, it would either answer the question based on knowledge and send a response, create a case for the user, or um just send an empathetic response to them.
00:07:36.000 --> 00:07:45.360
Now, the first iteration of this agent that I built pre-MCP had five different connectors that I had to create, as well as a knowledge source.
00:07:45.600 --> 00:07:49.040
So are those custom connectors that you built on Dataverse?
00:07:49.439 --> 00:08:02.879
So they were they were out-of-the-box ones from Microsoft, but they were still, you know, so I was using Outlook and Dataverse connectors, but I still had to go configure all of these connectors individually, as well as give the agent instruction sets.
00:08:03.279 --> 00:08:09.199
With MCP, those five connectors and knowledge sources went down to two connectors.
00:08:09.360 --> 00:08:12.399
One MCP for Dataverse, one for Outlook.
00:08:12.639 --> 00:08:14.879
And so the agent became a lot simpler.
00:08:14.959 --> 00:08:19.279
I simply gave it an instruction set and said, This is what I want you to do.
00:08:19.360 --> 00:08:21.519
And then I hooked it up to Dataverse MCP.
00:08:21.600 --> 00:08:24.560
I hooked it up to Outlook MCP when it needed to email.
00:08:24.720 --> 00:08:26.879
And so it got a lot simpler.
00:08:27.040 --> 00:08:32.879
And so this is becoming increasingly low and no code with tools like MCP.
00:08:32.960 --> 00:08:34.399
So that's why this is really exciting.
00:08:34.559 --> 00:08:41.120
Yeah, because more agents you add to it, the more it becomes like a multi-agent MCP.
00:08:43.120 --> 00:08:44.080
Yeah, yeah.
00:08:44.240 --> 00:08:54.240
So um, so yeah, so MCP is is a is a huge step forward in terms of giving our agents the ability to go solve problems.
00:08:54.559 --> 00:09:05.279
When I was playing with Dataverse MCP, just to give you an idea of how cool this is, um, I got a question on my YouTube channel about whether or not it could update choice columns.
00:09:05.440 --> 00:09:08.799
So um you have you know you have a drop-down on your form.
00:09:09.519 --> 00:09:17.919
And so I so I tried it out and um I I I um yeah, so I was playing with it and I tried to get it to do it.
00:09:18.159 --> 00:09:29.600
And the agent, the agent was was, and I'm doing this in um from memory, I think I was doing it in Claude Desktop um with Dataverse MCP.
00:09:29.840 --> 00:09:34.399
And it was it said, okay, let me try to update this this column.
00:09:34.720 --> 00:09:37.120
Um oh, I couldn't do that.
00:09:37.360 --> 00:09:40.080
Um, the data type is navcarmax.
00:09:40.159 --> 00:09:42.720
Let me update and try to do that again.
00:09:42.960 --> 00:09:44.080
That didn't work.
00:09:44.399 --> 00:09:49.840
All right, let me look through other choice columns in the system because I've got access to all the tables.
00:09:50.080 --> 00:09:55.840
Let me look through other choice columns in the system so I can get an idea of how this data is formatted and try again.
00:09:56.159 --> 00:10:00.639
Oh, um, you were too lazy to set any of these in your dev system.
00:10:00.879 --> 00:10:04.240
So now I'm gonna go to the SDK and see what I can learn.
00:10:04.399 --> 00:10:10.080
And long story short, it wasn't able to do it, but watching it attack the problem the way a human would, right?
00:10:10.240 --> 00:10:14.159
Let me try this, let me look at relevant data, let me look at the SDK.
00:10:14.240 --> 00:10:16.080
Like, this is the way you and I would try to solve this problem.
00:10:16.320 --> 00:10:17.279
Yeah, it's quite smart.
00:10:17.679 --> 00:10:19.519
Yeah, this is very, very cool.
00:10:19.679 --> 00:10:20.399
So yeah.
00:10:20.639 --> 00:10:25.039
Yeah, it's it's like your assistant buddy, so not a personage.
00:10:26.159 --> 00:10:33.600
So have you been using database MCP as a POC or in production, or you just test your purposes now?
00:10:33.919 --> 00:10:39.120
So it just went GA in November at Ignite.
00:10:39.279 --> 00:10:42.639
So it's still relatively early days.
00:10:42.879 --> 00:10:44.879
I have not used it in production yet.
00:10:45.039 --> 00:10:48.240
Most of pretty much everything I've built has been a POC.
00:10:48.320 --> 00:10:49.440
Um, yeah, yes.
00:10:49.679 --> 00:10:59.440
But um, I would say for production scenarios, the ones that I would be looking at is the the read and query capabilities are really good.
00:10:59.679 --> 00:11:23.840
Um, and so where you've got say dynamic um um data sources where you've got lots of tables perhaps being added, or um you need to give the agent more flexibility to answer questions for users, then MCP is the way to go because it's gonna figure out what to do based on what it knows.
00:11:24.000 --> 00:11:37.679
Whereas with a more traditional connector, you're gonna say, I'm gonna hook you up to cases and you can look at cases, but let's say it you know it needs to look at something else, it needs to look at a contact or an account.
00:11:37.759 --> 00:11:40.240
Um, if you haven't given it access to that, it can't do it.
00:11:40.399 --> 00:11:43.519
Whereas with MCP, the world's its oyster.
00:11:44.080 --> 00:11:44.399
Okay.
00:11:44.799 --> 00:11:56.480
I take it you can hook up databurse mcp to other, like you what you mean cloud desktop, or can it does with does it work with uh Microsoft Foundry as well?
00:11:56.639 --> 00:11:59.519
Or um it should do.
00:11:59.679 --> 00:12:07.120
I I have not been hands-on with Foundry yet, so I am I'm very much left tenant low code, so copilot studio is my jam.
00:12:07.440 --> 00:12:15.600
Um so I do need to get hands-on with foundry just so I can set the AB100 exam that everybody has been passing recently.
00:12:15.919 --> 00:12:18.080
Um so I do need to spend a bit of time with it.
00:12:18.240 --> 00:12:27.279
But um, you you can use it in Cloud Desktop, you can use it in um GitHub Copilot, um, copilot studio.
00:12:27.679 --> 00:12:31.360
Um, and that's just that's just the official one from Microsoft.
00:12:31.519 --> 00:12:35.200
There are lots of Dataverse MCP servers out there.
00:12:35.279 --> 00:12:36.159
You can go on GitHub.
00:12:36.240 --> 00:12:39.039
There's one that I'm told has 70 different tools.
00:12:39.360 --> 00:12:43.440
Um yeah, and you so you could you could create your own.
00:12:43.519 --> 00:12:53.600
So if if the uh this is not something I've tried yet, but you could go and create your own Dataverse MCP server um to do exactly what you want it to do.
00:12:53.840 --> 00:12:56.559
Um I would say a word of caution.
00:12:56.639 --> 00:13:07.919
Um, if you are downloading anything created by someone else, just be really careful, make sure you're absolutely certain you know what that thing is doing before you hook it up to your data.
00:13:08.080 --> 00:13:15.759
Um, because somebody could stick something in there where it's you know doing something behind the scenes that that you're not aware of.
00:13:16.080 --> 00:13:21.360
Otherwise, you just do it for internal uses in your company, like for HO or anything else.
00:13:21.919 --> 00:13:22.559
Yeah.
00:13:23.679 --> 00:13:28.720
So you say you want to show us like a preview of data press MCP?
00:13:29.039 --> 00:13:30.559
Yeah, let me let me take you through it.
00:13:30.639 --> 00:13:31.840
Let me share my screen.
00:13:32.240 --> 00:13:32.799
Sure.
00:13:34.240 --> 00:13:38.480
I went GA in November at Ignite.
00:13:38.799 --> 00:13:42.080
So it's still relatively early days.
00:13:42.399 --> 00:13:44.399
I have not used it in production yet.
00:13:44.559 --> 00:13:47.679
Most of pretty much everything I've built has been a POC.
00:13:47.840 --> 00:13:58.879
Um but um I would say for production scenarios, the ones that I would be looking at is the the read and query capabilities are really good.
00:13:59.120 --> 00:14:23.360
Um, and so where you've got say dynamic um um data sources where you've got lots of tables perhaps being added, or um, you need to give the agent more flexibility to answer questions for users, then MCP is the way to go because it's gonna figure out what to do based on what it knows.
00:14:23.440 --> 00:14:37.200
Whereas with a more traditional connector, you're gonna say, I'm gonna hook you up to cases and you can look at cases, but let's say it you know it needs to look at something else, it needs to look at a contact or an account.
00:14:37.279 --> 00:14:39.759
Um, if you haven't given it access to that, it can't do it.
00:14:39.840 --> 00:14:42.960
Whereas with MCP, the world's its oyster.
00:14:43.519 --> 00:14:43.840
Okay.
00:14:44.240 --> 00:14:55.919
I take it you can hook up DataForce MCP to other, like you what you mean Cloud Desktop, or can it does with does it work with uh Microsoft Foundry as well?
00:14:56.080 --> 00:14:59.039
Or um it should do.
00:14:59.200 --> 00:15:06.559
I I have not been hands-on with Foundry yet, so I am I'm very much Lieutenant Low Code, so copilot studio is my jam.
00:15:06.879 --> 00:15:15.039
Um so I do need to get hands-on with Foundry just so I can set the AB100 exam that everybody has been passing recently.
00:15:15.440 --> 00:15:17.519
Um so I do need to spend a bit of time with it.
00:15:17.679 --> 00:15:26.879
But um, you you can use it in Cloud Desktop, you can use it in um GitHub Copilot, um, copilot studio.
00:15:27.200 --> 00:15:30.879
Um, and that's just that's just the official one from Microsoft.
00:15:31.039 --> 00:15:34.639
There are lots of Dataverse MCP servers out there.
00:15:34.720 --> 00:15:35.600
You can go on GitHub.
00:15:35.679 --> 00:15:38.559
There's one that I'm told has 70 different tools.
00:15:38.799 --> 00:15:42.879
Um yeah, and you so you could you could create your own.
00:15:42.960 --> 00:15:53.120
So if if the uh this is not something I've tried yet, but you could go and create your own Dataverse MCP server um to do exactly what you want it to do.
00:15:53.279 --> 00:15:56.000
Um I would say a word of caution.
00:15:56.080 --> 00:16:07.360
Um, if you are downloading anything created by someone else, just be really careful, make sure you're absolutely certain you know what that thing is doing before you hook it up to your data.
00:16:07.519 --> 00:16:15.200
Um, because somebody could stick something in there where it's you know doing something behind the scenes that that you're not aware of.
00:16:15.519 --> 00:16:20.879
Otherwise you just do it for internal uses in your company, like for H or anything else.
00:16:21.360 --> 00:16:22.000
Yeah.
00:16:23.120 --> 00:16:28.559
So your use case that you think could be useful for it for using Dataverse MCP?
00:16:28.799 --> 00:16:30.159
Yeah, yeah.
00:16:30.399 --> 00:16:34.799
Um, I mean, you could, I mean, I would really say the limit is your imagination at this point.
00:16:34.960 --> 00:16:35.120
Yeah.
00:16:35.360 --> 00:16:37.679
Um you can yeah.
00:16:37.759 --> 00:16:39.039
Um, I mean, I think so.
00:16:39.200 --> 00:16:49.120
The thing I've been challenging myself with is if we come to this list of tools, I I feel like I've been too deterministic with this, right?
00:16:50.080 --> 00:16:54.879
Go create the create the record, go look up the record.
00:16:55.120 --> 00:17:01.840
Where this gets really exciting is with things like say creating a table.
00:17:02.399 --> 00:17:15.119
Um let's say it determines, hey, I need a table to keep track of you know whatever it is you're asking, and for it to go and do that on the fly, that's where this starts to get really exciting.
00:17:15.359 --> 00:17:20.000
And so um I've been kind of challenging myself to come up with some ideas.
00:17:20.079 --> 00:17:30.799
I'm still not there yet, but coming up with ideas for yeah, you can have an agent, you can have an agent to perform the action, one agent to read only and does things and delete.
00:17:31.200 --> 00:17:40.319
Yeah, so I have played with I did try with multi-agent late last year, um, and I was running into some issues with it.
00:17:40.480 --> 00:17:46.319
So I did have a demo, so la uh not last year, the year before last, 2024.
00:17:46.559 --> 00:18:03.279
Um, we did a demo using semantic kernel and copilot studio to create um basically, we basically created a CPQ where you'd say I need five of these and six of those and that type of thing, and it would go and create an order for you with those those things on it.
00:18:03.839 --> 00:18:17.599
I was able to replicate it using MCP, um, but I was limited to a single product, and so I tried to break it into a multi-agent um experience, but I I was running into some difficulties with it.
00:18:17.680 --> 00:18:19.440
So it's still something I'm working on.
00:18:19.680 --> 00:18:26.160
Um but yeah, um, it it does get really exciting when you think multi-agent and and what you could do with it.
00:18:26.240 --> 00:18:36.640
You've got one that's gonna determine this is what I need to do, one will go off and create records, one will go off and um um run prompts or do other things.
00:18:36.720 --> 00:18:38.880
So yeah, there's yeah, there's some really exciting things.
00:18:39.039 --> 00:18:46.960
Yeah, because you couldn't probably have one agent that only deletes stuff and to race stuff in production, those things if you want to go that side.
00:18:47.359 --> 00:18:48.319
Yeah, yeah.
00:18:48.559 --> 00:18:52.319
So um, so yeah, you could definitely break it up.
00:18:52.400 --> 00:19:01.599
And and I would recommend doing it because um what I've what I'm finding is my agent journey is very similar to my power automate journey.
00:19:01.680 --> 00:19:05.759
My early power automates were um monolithic, right?
00:19:05.839 --> 00:19:08.079
These huge flows that did everything.
00:19:08.400 --> 00:19:13.920
And over time you learn to break it up into a more modular design.
00:19:14.079 --> 00:19:31.200
And I think with agents, we need a similar experience where you've got smaller pieces, smaller, smaller agents handling a piece of the puzzle because what you'll find in Copilot Studio is if you try to get it to do too much, you will start running up against generative AI orchestration limits.
00:19:31.599 --> 00:19:41.759
Yeah, so yeah, don't do it like four agents at a time, do it like maybe one or two or three, just keep going up once you like understand what you're gonna do.
00:19:42.000 --> 00:19:44.240
So yeah, yeah, exactly.
00:19:44.400 --> 00:19:51.359
And it just makes them easier to triage, to troubleshoot, and to update as time goes on.
00:19:52.000 --> 00:19:52.960
That's great.
00:19:53.519 --> 00:20:04.480
Is there do you currently do you as at the moment do you just use in uh dataverse at your workplace as POC, or are you looking at something else?
00:20:05.039 --> 00:20:08.640
Um so Dataverse has been in production for quite some time.
00:20:08.720 --> 00:20:11.599
So we use Dataverse in all of our projects.
00:20:11.839 --> 00:20:28.319
Um Dataverse MCP is very new to being generally available, and so it's something that that we are looking at with with agents, but everything that I've built agent-wise with with model context protocol is is still still a POC.
00:20:29.359 --> 00:20:30.319
Excellent.
00:20:30.559 --> 00:20:42.960
And you can see how easily to to learn about database MCP is just low-code, drag and drop, and it you even get like the agent to write the instruction for you.
00:20:43.039 --> 00:20:47.599
So all you need to do is just configure it and get it working.
00:20:48.079 --> 00:20:49.440
It's literally that easy.
00:20:49.519 --> 00:20:50.000
Yep.
00:20:50.400 --> 00:20:51.839
So anyone can do that.
00:20:52.000 --> 00:20:56.960
So, how can someone get access to to Dynamics?
00:20:57.119 --> 00:20:58.400
Do they need a license?
00:20:58.480 --> 00:21:02.000
So they should have one once you got 365 license to play around with it.
00:21:02.640 --> 00:21:05.279
You do need a license, but you can set up a free trial.
00:21:05.359 --> 00:21:13.359
So if you just go and search on setting up a free trial for Dynamics 365, um, there's lots of options to do that.
00:21:13.440 --> 00:21:18.559
And then you can get started with Copilot Studio and Dataverse MCP and have a play with it.
00:21:18.880 --> 00:21:30.480
So that the first MCP, is that currently in uh dynamics at the moment, or is it like a you have to is that like a preview form you have to sign up for to get it there?
00:21:30.960 --> 00:21:35.200
Nope, it's it's it's there, it's ready and available in Copilot Studio now.
00:21:35.680 --> 00:21:37.039
Okay, brilliant.
00:21:37.279 --> 00:21:43.200
Yeah, uh yeah, so as aside from this episode, we love to know to guests.
00:21:43.279 --> 00:21:52.880
So anything, uh so what aside from like doing your amazing community works, uh do what do you normally do?
00:21:52.960 --> 00:21:54.480
Do you have any hobbies?
00:21:54.640 --> 00:22:01.440
Or um yeah, so I um I as you see behind me a I loved playing the piano.
00:22:01.519 --> 00:22:08.400
I've been playing for about three years now and I've taught myself how to play piano and that's that's kind of my thing that I do in my spare time.
00:22:08.799 --> 00:22:18.079
Um also very involved with uh with my local church and and um do quite a quite a lot of lot of work there in my spare time as well.
00:22:18.160 --> 00:22:22.319
So yeah, that's pretty much me when I'm not not doing my power platform thing.
00:22:24.000 --> 00:22:29.599
Uh yeah, so can you so you you know to play the piano?
00:22:29.680 --> 00:22:32.480
You've been playing for quite a long time, or you just start with it.
00:22:32.720 --> 00:22:40.480
Three years I I uh yeah it's something I I've been um so you can learn any Nicholas, you can learn anything on YouTube, and so that's literally how I learned.
00:22:40.720 --> 00:22:40.880
Yeah.
00:22:41.039 --> 00:22:49.440
Um and um yeah, so I I I I I just play chords, I don't do anything fancy, but but I do I do enjoy it.
00:22:50.799 --> 00:22:56.640
Yeah, and I see you're wearing the MVP t-shirt because you're gonna be at MVP Summit.
00:22:57.680 --> 00:23:00.319
The 2024 MVP Summit one.
00:23:00.559 --> 00:23:03.839
So oh okay, there's a color one, yeah.
00:23:04.079 --> 00:23:05.039
I don't remember.
00:23:08.079 --> 00:23:11.519
Um, so okay.
00:23:11.680 --> 00:23:14.640
Yeah, so this first one is.
00:23:14.960 --> 00:23:16.640
Yeah, next should be good.
00:23:16.799 --> 00:23:17.920
Should be a good one.
00:23:18.160 --> 00:23:20.559
So I hope to see you at Redbin, Nathan.
00:23:20.640 --> 00:23:22.240
So yeah, I can't wait.
00:23:22.799 --> 00:23:25.519
Yeah, so yeah, thanks for joining this episode.
00:23:25.680 --> 00:23:31.759
So hopefully uh some you guys learn about how easily you can set up DataPress MCP.
00:23:32.079 --> 00:23:36.319
And if you want to chew out, you can just get a trial license and play around with it.
00:23:36.559 --> 00:23:41.279
Any question, you can just pop uh ping names the roads on social media.
00:23:41.519 --> 00:23:42.240
Thank you.
00:23:42.559 --> 00:23:43.200
Bye.