Episode 434: Business Central, Noobies, Magic, and AI United

WEBVTT

00:00:05.759 --> 00:00:09.759
Welcome everyone to another episode of Dynamics Corner.

00:00:09.919 --> 00:00:13.199
What does MCP stand for?

00:00:13.359 --> 00:00:18.239
And what does it have to do with anything in the fantasy magical world?

00:00:18.399 --> 00:00:20.239
I'm your co-host Chris.

00:00:20.559 --> 00:00:21.519
And this is Brad.

00:00:21.600 --> 00:00:24.800
This episode is recorded on October 9th, 2025.

00:00:25.039 --> 00:00:26.480
Chris, Chris, Chris.

00:00:26.800 --> 00:00:31.440
What does it have to do with the in the realm of a fantasy world?

00:00:31.839 --> 00:00:32.960
I don't know.

00:00:33.200 --> 00:00:40.399
But we did have the opportunity to learn about that because I grew up playing those tabletop role-playing fantasy games.

00:00:40.560 --> 00:00:44.640
And I wish that we still lived in a world where those were much more popular than they are.

00:00:44.960 --> 00:01:03.759
With us today, we had the opportunity to speak with Jeremy Viscous.

00:01:08.719 --> 00:01:09.200
Yes.

00:01:09.439 --> 00:01:10.319
Hello, hello.

00:01:10.719 --> 00:01:12.079
How are you doing?

00:01:13.439 --> 00:01:15.120
Uh busy, as always.

00:01:15.439 --> 00:01:15.920
Busy?

00:01:16.319 --> 00:01:16.799
Always busy.

00:01:16.959 --> 00:01:18.000
I like the new background.

00:01:18.319 --> 00:01:20.239
It's uh it's different.

00:01:20.400 --> 00:01:20.959
It's different.

00:01:21.200 --> 00:01:21.519
Yeah.

00:01:22.079 --> 00:01:25.120
Well, I mean, you know, things have changed up a little bit.

00:01:25.280 --> 00:01:30.719
Uh I'm I'm not with Spare Brained anymore, so I don't have my own uh little studio space.

00:01:30.879 --> 00:01:42.799
Uh so you're getting kind of what you get, which uh I'm working for a Swedish company now, and uh we are in a shared office space, uh, so we have lots of little meeting rooms and whatnot.

00:01:42.879 --> 00:01:49.840
But uh it's it's uh getting back to working in the office, as they say.

00:01:50.400 --> 00:01:52.159
In a fashion, definitely.

00:01:52.480 --> 00:01:53.680
Yeah, no, that's good.

00:01:53.760 --> 00:01:54.159
That's good.

00:01:54.239 --> 00:01:57.040
It's I like being in the office at sometimes.

00:01:57.200 --> 00:02:10.560
I I think being remote sometimes, I think we miss out on a lot of that interpersonal communication type things where you can yell over, or you know, yell over a cube wall or knock on someone's door, or you do run some into someone in passing and you can ask them questions.

00:02:10.719 --> 00:02:19.919
Where I think in the remote world it's a little more challenging because you have to check are they online, you know, are they in a meeting, or you know, if you have teams or whatnot.

00:02:20.080 --> 00:02:25.520
So I think sometimes people are a little more apprehensive to maybe reach out and talk to somebody.

00:02:25.759 --> 00:02:29.520
So I think uh it's it was a little more challenging.

00:02:29.599 --> 00:02:32.960
So I think going to the going to the office is it has its benefits and it also has its drawbacks.

00:02:33.280 --> 00:02:46.560
You got your water cooler too, like it's nicer, you know, and just stop over and have some water cooler talk, you know, as a group, rather than trying to get teams going, like, oh, he's green or red or he's yellow, he's not in yet.

00:02:46.639 --> 00:02:48.159
But you know, he's actually right there.

00:02:48.479 --> 00:02:50.080
Yeah, no, it's it's good.

00:02:50.159 --> 00:02:51.280
You get some of that small talk.

00:02:51.520 --> 00:02:53.280
Um, so again, welcome back.

00:02:53.360 --> 00:03:07.599
But uh so much I want to talk to with you about, and uh I I don't know, it's probably one of those conversations where my mind is going so fast that I won't be able to uh my mouth will have a challenge keeping up with it, and I'll try not to go out the place.

00:03:07.680 --> 00:03:10.639
But before we jump into that, would you mind telling us a little bit about yourself?

00:03:11.120 --> 00:03:11.840
Sure, sure.

00:03:12.000 --> 00:03:13.199
Uh let's see.

00:03:13.280 --> 00:03:15.599
Um I'm Jeremy Visca.

00:03:15.759 --> 00:03:19.599
I'm an American who relocated to Sweden ten years ago.

00:03:19.680 --> 00:03:26.080
I've been working with BC now uh for coming up on 26 years, uh so a real long time.

00:03:26.159 --> 00:03:30.080
I've been a BC MVP for five years.

00:03:30.319 --> 00:03:32.240
Coming up on five years, something like that.

00:03:32.400 --> 00:03:34.719
Uh in that neighborhood.

00:03:34.960 --> 00:03:36.159
Time's a blur.

00:03:36.479 --> 00:03:48.560
But um the uh you know, written a couple of different books about BC over the time, uh released a few odds and ends, which we've talked about on previous episodes, uh, that people can make use of in the community.

00:03:48.719 --> 00:04:04.240
Um and these days, which I think is led to the uh us chatting at this particular moment in time, these days uh people are being amused to watch how quickly I'm kind of running uh with the AI ecosystem for business central world.

00:04:04.560 --> 00:04:07.199
So uh lots going on.

00:04:07.759 --> 00:04:14.400
Lots going on, lots going on in uh your your API book I still have as a reference, which is nice.

00:04:14.479 --> 00:04:16.879
Uh and I do appreciate all that you've done for the community.

00:04:17.040 --> 00:04:21.360
And as you had mentioned, I started watching you with this.

00:04:21.439 --> 00:04:29.360
I I've always followed a lot that you've done, and you know we've had lots of conversations, but recently you started a new project, right?

00:04:29.439 --> 00:04:42.240
That it's the world of AI, and you've been working with BC for a while, and then one day I was following uh some of the message that you had, and you referenced to an additional project that you had started.

00:04:42.480 --> 00:04:45.120
Uh, would you mind telling us a little bit about that project?

00:04:45.839 --> 00:04:46.399
Sure.

00:04:46.560 --> 00:04:52.319
Uh I mean let me bring you on the journey, like well, bring the audience along uh for the first time keeping up.

00:04:52.720 --> 00:04:56.160
But the first question I have to get to cut you off, how do you pronounce it?

00:04:57.519 --> 00:05:00.800
The the uh newbiancy project?

00:05:01.040 --> 00:05:01.920
Yes, that's it.

00:05:02.000 --> 00:05:02.399
Thank you.

00:05:04.560 --> 00:05:04.959
Thank you.

00:05:05.120 --> 00:05:08.000
I want to go on the journey now, but that was like one of the things I'm saying.

00:05:08.160 --> 00:05:10.959
I'm like, I call it like I was calling it like nubibacy.

00:05:11.120 --> 00:05:17.199
Like I was coming up with all these phrases, and like that's the first thing I have to get out of Jeremy is how do you pronounce it?

00:05:17.519 --> 00:05:24.000
I carefully test uh and make sure that everything I bring on the show is something difficult for you to say.

00:05:24.160 --> 00:05:28.399
It's it's mission accomplished, right off the show.

00:05:32.560 --> 00:05:33.839
Hey, me too.

00:05:34.720 --> 00:05:36.319
Just let's say, Chris, watch out.

00:05:36.560 --> 00:05:37.920
I know he's from the northeast.

00:05:38.319 --> 00:05:38.959
You missed that.

00:05:39.040 --> 00:05:45.120
He he he he relocated to Sweden, but he wasn't too far from me.

00:05:45.199 --> 00:05:50.560
Uh which is an interesting aside to the things we've talked about before.

00:05:50.639 --> 00:05:57.839
Uh, for fans of the show who've watched these various episodes, and in the past we've talked about Braider uh as that like API factory.

00:05:58.079 --> 00:06:03.040
When I shut down Spare Brain at the end of last year, I did that product didn't die.

00:06:03.199 --> 00:06:04.959
That became open source.

00:06:05.120 --> 00:06:08.800
Uh and it's on App Source still now for free with no licensing.

00:06:08.959 --> 00:06:15.680
So any of the folks who have watched the previous episode where we're talking about what you could do with it, just go hit install and start using it.

00:06:15.759 --> 00:06:21.040
Um you can now climb through all the source code and get to know how the heck did I do all that stuff?

00:06:21.600 --> 00:06:22.079
Go look.

00:06:22.800 --> 00:06:23.600
That's good, excellent.

00:06:23.680 --> 00:06:26.959
So Braid is now open source and still available in App Source.

00:06:27.279 --> 00:06:27.839
Excellent.

00:06:28.079 --> 00:06:28.720
Excellent.

00:06:28.879 --> 00:06:29.920
So all right.

00:06:30.079 --> 00:06:33.360
So the uh the the actual story we wanted to talk about.

00:06:33.519 --> 00:06:33.839
Okay.

00:06:34.160 --> 00:06:39.199
So um conference season in Europe happens pretty heavy in the spring.

00:06:39.279 --> 00:06:43.439
We've got a lot of great conferences from March through June.

00:06:43.600 --> 00:06:46.399
Um, there's a lot of things going on in that time stretch.

00:06:46.480 --> 00:06:52.079
You know, the holidays are finally over, it's nice enough to go outside, and and boy, do things get busy.

00:06:52.160 --> 00:07:01.680
So there's all the days of knowledge and dynamics minds and BC Tech days and all these different great events that uh happen throughout the spring season.

00:07:02.000 --> 00:07:14.160
And um I had the pleasure of attending one of the days of knowledge uh events in the spring uh and spent a lot of time with Tina um from uh I want to say continuum?

00:07:14.800 --> 00:07:15.759
Companion, I think.

00:07:16.000 --> 00:07:16.560
Companio.

00:07:16.720 --> 00:07:16.959
Thank you.

00:07:17.360 --> 00:07:18.160
Yeah, that is correct.

00:07:18.560 --> 00:07:28.000
Um and uh, you know, he and I have always gotten along pretty well, and he did some uh great talks about AI is more than just fancy autocomplete.

00:07:28.560 --> 00:07:41.040
Um which up until that point, my GitHub co-pilot experience in Visual Studio Code was it's just as annoying as when you're trying to type on your phone and it's suggesting all sorts of nonsense to you.

00:07:41.360 --> 00:07:44.079
It had as much value to me as that.

00:07:44.240 --> 00:07:53.680
Um it didn't really feel like it was earth-shattering, and yet we're you're hearing keynote after keynote that's talking about all these things that AI can do for you.

00:07:53.759 --> 00:07:55.920
And I'm like, what's the disconnect?

00:07:56.160 --> 00:08:01.199
How is it possible that 30% of code is coming from people hitting tab?

00:08:01.759 --> 00:08:03.439
That doesn't make sense.

00:08:03.839 --> 00:08:04.399
Exactly.

00:08:04.560 --> 00:08:18.399
And yeah, it's funny that you mentioned that because with Tina, that same session, and he has to um polish it every couple weeks, it seems like, because of the way the content changes.

00:08:18.639 --> 00:08:32.480
But at Directions North America, I saw his session on that, and that also what drove me into it, where I was floored at how you could use AI with AL development.

00:08:32.720 --> 00:08:34.559
So that video is available.

00:08:34.639 --> 00:08:37.600
The BC Tech Days video did come out uh recently.

00:08:37.679 --> 00:08:46.000
So anybody who wants to watch the session or listen to the session uh and watch the screen, um, that's also on YouTube, which it's well worth the listen.

00:08:46.320 --> 00:08:46.960
Yep.

00:08:47.279 --> 00:08:54.720
So the that was the seed of understanding for me was get copilot out of ask mode.

00:08:54.879 --> 00:09:04.960
It's not just a conversational partner, it's not just an autocomplete that's waiting for you to hit tab and you know, you're just trying to indent a line, the thing's getting in the way.

00:09:05.200 --> 00:09:10.720
It's it's a very different experience when you switch over to that agentic mode.

00:09:11.039 --> 00:09:16.559
Um and kind of hearing that, I went, I still don't I still don't feel it.

00:09:16.720 --> 00:09:19.679
Like, you know, I I I've been doing this a long time.

00:09:19.919 --> 00:09:22.080
It can't possibly be faster.

00:09:22.480 --> 00:09:24.879
Frankly, I'm a very fast coder.

00:09:25.039 --> 00:09:36.960
A lot of the times I have to cr cross-check what I'm doing with someone else to go, what is a reasonable time estimate, because I think I can do this faster than probably I should offer to people.

00:09:37.360 --> 00:09:42.480
Um and uh so I I was pretty suspicious.

00:09:42.879 --> 00:09:55.840
So uh since that was in May, um, and I was speaking at Tech Days in June, I set myself up with the challenge, uh, and I didn't tell anyone about this until halfway through the talk.

00:09:56.000 --> 00:10:15.200
Uh, in BC Tech Days, um, I was presenting a whole bunch of stuff on making job queues run in parallel um and how to make uh the most of the fact that BC gives us the ability to run multiple tasks per user, and they really opened up the job queue to really handle a lot of bandwidth.

00:10:15.360 --> 00:10:19.120
What can we do to use and abuse that level of capacity?

00:10:19.279 --> 00:10:23.840
So um, you know, I did I plan to do this talk on the parallel development.

00:10:23.919 --> 00:10:31.360
Um I've gotten feedback since that some people have gotten operations that were nine-day operations down to six-hour operations.

00:10:31.519 --> 00:10:31.679
Wow.

00:10:32.000 --> 00:10:35.440
So uh it's making a big difference for some folks.

00:10:35.679 --> 00:10:43.440
Um but I set myself out the challenge of if I'm gonna do this, I want to challenge me, not just my audience.

00:10:43.679 --> 00:10:49.039
And I made it that I am not allowed to touch or write the code.

00:10:49.840 --> 00:10:56.639
I have to only write instructions for the agent to understand what I'm trying to accomplish.

00:10:57.360 --> 00:11:11.840
That is an interesting challenge to yourself that somebody who's been coding for as long as you have, who has the ability to code quickly and understands the language, to now basically go into instruct mode.

00:11:12.080 --> 00:11:12.559
Hands off.

00:11:13.039 --> 00:11:21.120
Hands are off, and now you have to write, which that's a whole other topic is writing instructions because I was I've been following this project and what you've been doing.

00:11:21.840 --> 00:11:28.000
And I I just I don't even I'm speechless with this whole instruct mode and uh and such.

00:11:28.159 --> 00:11:31.120
So that's uh that's a challenge.

00:11:31.679 --> 00:11:33.840
So um so it was a little bit interesting.

00:11:34.000 --> 00:11:46.080
I I've happily at the beginning of that tech day's talk, uh, where I was gonna show off all this code and how it works and everything like that, which you know, um that demonstration went really well for you know the hour or so.

00:11:46.240 --> 00:11:54.080
Um I I happily uh lifted from AJ Kaufman uh his opening line that he likes to give for some of his sessions.

00:11:54.159 --> 00:11:59.440
That uh congratulations, you're in a session that is a co-pilot-free session.

00:11:59.679 --> 00:12:10.240
And just as he's experienced, the crowd went kind of crazy, like happy because they're so fatigued about hearing about AI, because they had the same experience I did.

00:12:10.399 --> 00:12:14.799
It doesn't provide value to me, and yet that's all I can hear about.

00:12:15.039 --> 00:12:16.080
That's terrible.

00:12:16.320 --> 00:12:18.000
Yeah, it's really frustrating.

00:12:18.240 --> 00:12:27.039
When you're like out of that lockstep and suddenly all of the mainstream content means nothing to you, it doesn't feel very good.

00:12:27.279 --> 00:12:32.799
So there's a natural pushback and reaction to that, and so people you know applauded with that.

00:12:33.120 --> 00:12:42.320
Um the fun moment for me was then an hour, hour or so later, to be saying, by the way, I lied to you at the very beginning of this.

00:12:42.480 --> 00:12:51.600
Uh, not only is it not a copilot-free session, every single bit of code we've just looked at, and the product of that code was copilot written.

00:12:52.399 --> 00:12:58.559
And then we spent some time talking through how that actually came about.

00:12:59.519 --> 00:13:02.240
Behind the curtain, there's actually a copilot.

00:13:04.399 --> 00:13:10.080
I actually did get a couple of negative reviews from that of I can't believe that you would do that to us.

00:13:10.480 --> 00:13:14.960
It's like it's still real code.

00:13:15.360 --> 00:13:17.279
I I think that I think that's a little fun.

00:13:17.519 --> 00:13:20.720
So so let's take it through uh through your journey.

00:13:20.879 --> 00:13:30.480
So Tina sort of sparked, I guess you you sort of sparked uh your uh inquisitiveness for AI, uh, I think it's it's it's funny.

00:13:30.559 --> 00:13:37.039
It's uh I had the similar I had a similar experience, and that's also what started my journey with this was seeing that.

00:13:37.200 --> 00:13:40.639
Um so you then had a session that you did hands-off.

00:13:40.879 --> 00:13:42.000
How did that go?

00:13:42.159 --> 00:13:45.519
And is that what also sparked the project that you have?

00:13:45.679 --> 00:13:53.120
Um because you had some interesting blogs on there about your journey, uh blog articles, excuse me, on that project website about your journey as well.

00:13:53.279 --> 00:13:54.879
Is that together?

00:13:55.279 --> 00:14:05.279
Um, that was uh I kind of think of it a little bit as Tina uh planted the seed and the challenge to myself, let it take root.

00:14:05.679 --> 00:14:11.679
And um after that experience of okay, it could do the job.

00:14:11.840 --> 00:14:18.240
Like at any point in time during that week, if it really couldn't do the job, I still had enough time to write the things myself.

00:14:18.480 --> 00:14:22.159
I could go hands back on the wheel and and not worry about it.

00:14:22.320 --> 00:14:24.240
Um but it succeeded.

00:14:24.480 --> 00:14:28.960
I got what I needed out of it for producing decent code.

00:14:29.120 --> 00:14:33.120
Um, and I genuinely was well a little bit surprised by that.

00:14:33.279 --> 00:14:40.000
So I started pushing myself um uh a little bit more to explore it in the day-to-day job.

00:14:40.080 --> 00:14:44.960
But you know, as always, when you get back from a conference, you've just got the pile of things you need to get done.

00:14:45.120 --> 00:14:48.799
Um so I didn't I didn't really have time to pick it back up.

00:14:49.120 --> 00:14:55.120
And then um in July, I took off the first half of July for vacation.

00:14:55.279 --> 00:15:05.279
Uh, but when I came back and everyone else was still on vacation for the rest of July, making it a really nice quiet time, I challenged myself to a July of AI.

00:15:05.759 --> 00:15:10.639
What stuff am I missing that I could be doing better?

00:15:10.960 --> 00:15:19.519
And that was the beginning point of where the blog series that you're referring to kind of picked up on the uh newbimanse.com site.

00:15:19.600 --> 00:15:29.840
Um, and that was also the seed of the idea of that project uh at that moment in time of um there's always more to be learning and everything like that.

00:15:30.000 --> 00:15:35.519
Um, you know, there's a lot of stuff that we're doing in our organization with DevOps and pipelines.

00:15:36.000 --> 00:15:45.919
And, you know, over the summer I had been meeting with a bunch of people talking about all the things that we're doing in pipelines and how can I bring that information to the community at large?

00:15:46.159 --> 00:15:48.879
I can't share our organization DevOps.

00:15:49.279 --> 00:15:56.879
So newbie Mancy as a project and the AI development in hand in hand kind of happened at the same time.

00:15:57.039 --> 00:16:02.399
Of what can I do to share all this stuff that's in my head?

00:16:02.639 --> 00:16:07.519
Um, what can I do to bring more knowledge about all these different pieces?

00:16:08.159 --> 00:16:12.639
Is it unfolding construction-wise as a story and a narrative?

00:16:12.799 --> 00:16:16.240
Uh no, not as not as smoothly as I would like it to.

00:16:16.480 --> 00:16:24.879
Um but uh in July I spent a lot of time trying to figure out the AI did an okay job for me.

00:16:25.039 --> 00:16:28.960
It did okay, but I feel like it could do better.

00:16:29.200 --> 00:16:36.000
And it was right around that same time uh Dmitry Katzen was working on the AL guidelines site.

00:16:36.080 --> 00:16:44.080
He was trying to put together some instruction set that would help the AI understand AL best practices better.

00:16:44.240 --> 00:16:53.919
Um, he was contributing that to the ALguidelines.dev project under the vibe coding section, which you can go grab now and plug into your agents and all that sort of stuff.

00:16:54.080 --> 00:17:03.919
And there was some really good discussion in that thread of that pull request of what are people using for instructions and what makes good instructions.

00:17:04.240 --> 00:17:09.920
Um and out of that, I started realizing what made good instructions.

00:17:10.160 --> 00:17:21.440
And so by the time my team got back at the end of July, I had this massive pile of infrastructure and education that the co-pilot had been through.

00:17:21.599 --> 00:17:31.599
And the way that training all these agentic coding things is as long as you've built up that instruction set, every agent is kind of a disposable thing.

00:17:31.680 --> 00:17:36.960
It picks up where right where you've left it every single time it's starting at the beginning.

00:17:37.119 --> 00:17:42.319
So if your instruction set is right, right at the beginning, that's where it starts every time.

00:17:42.720 --> 00:17:55.039
And my team started trying to get their hands around it, and it was it was a learning journey for them because they're in the same position you are of this is just annoying and it doesn't do anything.

00:17:55.599 --> 00:17:56.559
What's the point?

00:17:56.960 --> 00:18:03.119
Yeah, so let's take a step back as you're talking about um instruction set and agents.

00:18:03.680 --> 00:18:16.000
Uh so for those that are listening that may be in the same position that we were, what is an agent and what is the instruction set that you're referencing?

00:18:16.400 --> 00:18:22.480
And maybe we can, I'm sure we'll get into how do we give that agent those instructions.

00:18:22.640 --> 00:18:25.039
And you're also talking about multiple.

00:18:25.279 --> 00:18:28.720
I I see I told you I'm just gonna run with this, but we'll start with that.

00:18:28.880 --> 00:18:31.039
That's when you started with this infrastructure for your team.

00:18:31.440 --> 00:18:31.839
Sure.

00:18:32.079 --> 00:18:32.400
Okay.

00:18:32.640 --> 00:18:46.000
The one of the things that I learned early on with agentic coding, it's like you're a development manager who's just been given a really enthusiastic rookie on a lot of coffee, ready to go, let's do this.

00:18:46.160 --> 00:18:51.519
But they they they've read only the textbooks in school about development practices.

00:18:51.680 --> 00:18:53.839
Maybe they've heard of Business Central.

00:18:54.079 --> 00:18:56.079
And but they're ready to go.

00:18:56.319 --> 00:18:59.599
Um it doesn't always work great.

00:19:00.720 --> 00:19:15.519
So um what I kind of think of instruction files as, and this uh is jumping ahead a little bit, but also MCP servers, it's like taking that junior developer and saying, Okay, I'm glad you're here to report for work at 8 a.m.

00:19:15.759 --> 00:19:18.880
all espressoed up and you're you're ready to jump in.

00:19:19.039 --> 00:19:23.440
Uh first go read this instruction manual and then come back to me.

00:19:23.680 --> 00:19:26.640
And now it's time for you to pick up your task for the day.

00:19:26.880 --> 00:19:40.960
And so when I'm talking about instructions, it's literally a pile of uh usually files uh that are basically you are a business central development helper, and here are some of the rules that you need to follow.

00:19:41.039 --> 00:19:43.599
Here are some of the things you should and shouldn't do.

00:19:43.759 --> 00:19:48.240
Here's some of the stuff you should know about, and some of the stuff you should know not to do.

00:19:48.480 --> 00:19:53.920
And that's just a language file because these are running on large language models.

00:19:54.160 --> 00:19:59.759
So uh one of the recurring jokes these days is what pro what languages do you program in?

00:20:00.079 --> 00:20:00.880
English.

00:20:01.519 --> 00:20:02.160
Yes.

00:20:02.880 --> 00:20:16.240
Um so instruction files and again MCP servers are basically you've got that happy junior uh go go read the manual, go take this class, and when you come back from those, then we can start working.

00:20:17.279 --> 00:20:20.559
So you you you mentioned the MCP server as well.

00:20:20.799 --> 00:20:23.680
Again, it's it's it's all I think we'll come full circle to others.

00:20:23.759 --> 00:20:34.319
So you have instruction sets, which are something that you give to an agent, which we'll equate to as a person in this scenario that you're telling what to do.

00:20:34.400 --> 00:20:39.920
So then you can have different instruction files for different agents to do different functions.

00:20:40.319 --> 00:20:50.559
Um, and in here in the case we're talking about a business central developer, but you could have someone who is uh someone who's documenting code, or I mean, how would you break those agents up?

00:20:50.720 --> 00:20:54.240
And then how does it fit with an MCP server?

00:20:54.559 --> 00:20:59.359
And you know, I'll ask you the$10,000 question.

00:20:59.759 --> 00:21:02.880
What is an MCP server along with all of this?

00:21:03.200 --> 00:21:04.480
So yeah.

00:21:04.720 --> 00:21:14.000
Um okay, so to take those in turn, yes, uh instruction files are basically you've got this LLM, it wants to help you out.

00:21:14.240 --> 00:21:16.400
What does it need to know to help you out?

00:21:16.559 --> 00:21:20.720
And what are the things it can and should do, and what are the things it can't do?

00:21:20.880 --> 00:21:30.160
So, for example, the sales order agent in Business Central, the way they've built that up is through very careful articulation of instructions.

00:21:30.319 --> 00:21:37.680
It's following instructions just like our agents are in GitHub uh in the uh GitHub chat window in your Visual Studio Code.

00:21:37.920 --> 00:21:43.359
Um uh that sometimes is referred to as the prompts, prompt engineering, and all that sort of thing.

00:21:43.599 --> 00:21:49.359
That's the what instructions does the model understand to accomplish and all that.

00:21:50.079 --> 00:21:58.640
Um so effectively, yes, you you by giving different instructions to the same engine, you give it a different job.

00:21:59.200 --> 00:22:06.160
So uh that's why I kind of like to think of the agent as that enthusiastic young person ready to show up and do whatever.

00:22:06.400 --> 00:22:07.599
What are you doing today?

00:22:07.759 --> 00:22:10.079
Well, today you're a documentation guy.

00:22:10.319 --> 00:22:14.799
Today you're a sales order processor, tomorrow you're gonna be an expense agent.

00:22:14.960 --> 00:22:23.039
It it really doesn't matter, uh it's still it's showing up and what is the uh uniform you're putting on it on it when it shows up.

00:22:24.000 --> 00:22:24.720
Okay, okay.

00:22:25.359 --> 00:22:29.039
Um then to the uh MCP server question.

00:22:29.119 --> 00:22:38.160
An MCP server, uh it's annoying, uh it stands for model context protocol, which means nothing to anyone uh unless you're really deep in the weeds.

00:22:38.400 --> 00:22:51.599
It's it's one of my challenges with AI at the minute is that there's such a big gap between the leading edge people and the rest of us that they'll often forget that we'd have no idea what you mean by rag versus vector.

00:22:51.920 --> 00:22:54.559
Like what what what language are you speaking?

00:22:54.880 --> 00:23:12.720
Um the uh the thing about the MCP, it's basically just a toolbox that can contain the instruction manuals and also some tools that the uh guy showing up that day for work, he can unpack the toolbox and let's go.

00:23:13.680 --> 00:23:14.160
That's it.

00:23:14.480 --> 00:23:15.839
That's really all it is.

00:23:16.079 --> 00:23:28.160
Uh MCP servers allow the agent to understand how to do stuff on your behalf, whether that comes through knowledge or whether that comes through talking to third-party systems.

00:23:28.400 --> 00:23:35.359
For example, an MCP server I'm using all the time is connecting to Azure DevOps or connecting to GitHub.

00:23:35.599 --> 00:23:39.119
It understands how to log in as me on my behalf.

00:23:39.359 --> 00:23:42.640
Jeremy sent me to create this issue here, have an issue.

00:23:43.519 --> 00:23:43.839
Okay.

00:23:44.720 --> 00:24:00.480
So the MCP ecosystem is how many different toolboxes can we invent for these agents so that way when you show up, uh when you get there and you're starting your workday and the agent shows up and it's ready to go, what toolboxes can you give them?

00:24:00.880 --> 00:24:08.240
And the cool thing about an MCP server is that these are just bits of code and bits of software, so there's an infinite number of them.

00:24:08.400 --> 00:24:14.559
Once someone makes that toolbox available, everyone can use it and everyone can say, here you go, to your agents.

00:24:14.720 --> 00:24:15.920
And that's pretty amazing.

00:24:16.400 --> 00:24:17.680
I like that explanation.

00:24:17.759 --> 00:24:22.960
It's probably the easiest where I can now picture what is an MCP and what it does.

00:24:23.119 --> 00:24:25.440
Because that it's it everyone tells me different things.

00:24:25.519 --> 00:24:27.440
I'm like, okay, can you just explain?

00:24:27.519 --> 00:24:29.680
That's probably the best one I've heard so far, Jeremy.

00:24:29.759 --> 00:24:31.599
So thank you for explaining that to me.

00:24:33.759 --> 00:24:44.559
The reason I also use that metaphor is um MCP servers, you get you once you start getting used to them, you can go, oh, I should install a hundred of them, and then I've got all these different tools.

00:24:44.799 --> 00:24:55.599
The thing is, is that when you um install these MCP servers for the agents to work with, um the agent has to decide what's the right tool for the job.

00:24:55.759 --> 00:24:58.400
And that thinking process is burning tokens.

00:24:58.480 --> 00:25:05.200
It's it's using up some of its ability to get the job done, has to stop and think about what tools to use.

00:25:05.440 --> 00:25:12.319
And so tools like Visual Studio Code will actually yell at you if you try to use too many uh MCP tools.

00:25:12.480 --> 00:25:20.960
And I like to think of that as the look, the intern can only fit so many tools on his belt before it's just gonna weigh the poor intern down.

00:25:21.200 --> 00:25:39.200
Don't give it a narrow focus of what tools to think about, because if it has to try to figure out between 50 different toolboxes what should I use to do what you just asked me to do, it's gonna spin for a long time and it's gonna be very inefficient, and inefficient costs a lot of time and effort.

00:25:39.279 --> 00:25:56.559
And part of being ethical about AI usage, which is a challenge uh for energy and water consumption, part of being ethical is also making sure that if you're using AI, you are being efficient with it rather than having to argue with it for a couple of hours to get what you need.

00:25:57.519 --> 00:25:57.839
Yes.

00:25:58.079 --> 00:26:03.119
Okay, so just if I can peel it back from your explanation, which is as Chris had mentioned, was great.

00:26:03.359 --> 00:26:22.160
MCP server is basically a standard set of tools that a an agent, which I'll call it, uh that eager, that eager uh uh employee that shows up one morning to be able to do their task.

00:26:22.319 --> 00:26:32.160
And that tool can be something internal or it can be something that they can use externally, such as like a telephone to call somebody to make an appointment.

00:26:32.319 --> 00:26:36.880
That telephone's a standard that anybody can use, and then someone on the other side will pick up and say hello.

00:26:36.960 --> 00:26:42.480
So it's a standard way of communicating, and then you can have multiple of those running.

00:26:42.799 --> 00:26:50.960
So each one of those has a set of tools for the agent, and they the agent will choose which tools to do the job.

00:26:51.119 --> 00:26:57.759
So if we have an MCP server for uh hardware tools to build a house, if they're building a house, they'll go to that server.

00:26:57.839 --> 00:27:02.720
But if there's another one for reading instructions or manuals, possibly, you may have a server for that.

00:27:02.960 --> 00:27:07.519
Another thing that you had mentioned, which I hear a lot of with AI, is tokens.

00:27:07.920 --> 00:27:10.400
And you mentioned that you can burn up a lot of tokens.

00:27:10.559 --> 00:27:16.640
What is a token in the context of MCP AI instructions?

00:27:16.799 --> 00:27:17.920
Is it money?

00:27:19.039 --> 00:27:22.160
Effective is it's a gold token.

00:27:22.480 --> 00:27:22.799
Right?

00:27:22.960 --> 00:27:23.359
I know.

00:27:23.599 --> 00:27:25.440
It brings us back to the arcade days, right?

00:27:25.839 --> 00:27:26.640
Burning quarters.

00:27:27.119 --> 00:27:32.160
Um the um we put them on the pinball machine when it's your for your turn.

00:27:32.240 --> 00:27:34.400
You have to remember do you remember that stack in the quarters?

00:27:34.880 --> 00:27:36.079
Yeah, I got next.

00:27:36.319 --> 00:27:37.359
I got next.

00:27:38.799 --> 00:27:40.720
Just I don't want to digress.

00:27:40.799 --> 00:27:45.839
I know Jeremy, you want to jump into but just think about what like someone who's younger today.

00:27:46.000 --> 00:27:51.279
Well, we're talking about putting quarters on a pinball machine or even a regular arcade game to get next.

00:27:51.519 --> 00:27:56.640
And they grew up with an entire arcade in their hand.

00:27:57.839 --> 00:27:58.880
It's pretty incredible.

00:27:59.200 --> 00:28:00.319
It is incredible.

00:28:00.640 --> 00:28:01.359
100%.

00:28:02.000 --> 00:28:18.880
So the uh the token thing, just to kind of speak to that, is um just like with water and power, you kind of like meter your usage, and like uh for your home, uh you buy a washer or a dishwasher that maybe uses water more efficiently.

00:28:19.119 --> 00:28:21.680
Um it's the same sort of idea.

00:28:21.839 --> 00:28:30.799
A good set of instructions is more compact and it is very much more precise around what should the agent be processing.

00:28:31.119 --> 00:28:52.640
And the amount of information that goes from your local discussion point to these LLM servers, that that's the underlying tech behind the agents, um the uh the amount of information that's going, that's uh there's no weight to it, there's no data volume precisely, it's it's measured in tokens.

00:28:52.799 --> 00:29:04.640
So, how heavy is that information stack that you're sending to the AI platform, GitHub or Co uh Anthropic or all these other things, how heavy is that data stack?

00:29:04.880 --> 00:29:12.079
And the amount of data that's in that pile is the amount of effort that the LLM has to go through all of that stuff.

00:29:12.240 --> 00:29:15.680
And the measurement that the LLM uses is tokens.

00:29:15.839 --> 00:29:18.079
And so that's why people talk about that.

00:29:18.319 --> 00:29:35.599
Um, and so uh oftentimes if you're using GitHub uh chat and doing the copilot things in Visual Studio Code using GitHub, um you might have premium requests which are using tokens talking to companies that aren't included uh up to a certain point.

00:29:36.000 --> 00:29:42.079
Um and tokens are how they meter that, the same way you would meter electricity and water and those sort of things.

00:29:43.599 --> 00:29:45.200
So a unit of measure.

00:29:46.000 --> 00:29:46.559
Okay, great.

00:29:46.880 --> 00:29:49.920
And then so it is, it's a meter that goes through it.

00:29:50.079 --> 00:29:50.319
Okay.

00:29:50.799 --> 00:29:56.559
So now we talked about instruction sets that someone can write, and I'm sure there's a format for that.

00:29:56.640 --> 00:30:03.119
We have agents, we have an MCP server, and we have Jeremy's journey through this as well.

00:30:03.440 --> 00:30:12.160
Because uh well, one of my favorite ways of developing instructions, because I'm not a I again, I I've been doing this less than six months.

00:30:12.240 --> 00:30:19.039
Uh one of my favorite ways to do uh instruction tuning is to get the agent to help me write the instruction for the next guy.

00:30:19.839 --> 00:30:28.880
So what I'll do is I'll set uh you know, oftentimes, especially in July when I was new at this, I would say, okay, I've got a task in front of me.

00:30:29.039 --> 00:30:31.680
I want the agent, I want you to do this task.

00:30:32.079 --> 00:30:34.400
It did not give me the results I expected.

00:30:34.559 --> 00:30:48.640
So what I will do is I'll make the results I expected and then go, explain to me, like you would explain to the next agent, what the difference between what I now have that I've done versus what you did.

00:30:48.799 --> 00:30:52.720
How would I the next agent to know to do it my way?

00:30:53.039 --> 00:30:56.640
So you can ask the agent, how do I improve it for the next guy?

00:30:56.880 --> 00:30:57.200
Okay.

00:30:57.839 --> 00:30:58.480
Wow.

00:30:59.920 --> 00:31:02.319
That see, this is ingenious.

00:31:02.480 --> 00:31:05.519
I'm thinking of all the things I'll have all these agents do for me right now.

00:31:05.680 --> 00:31:07.279
Like just do a code review.

00:31:07.440 --> 00:31:15.119
You know, do a code review before you set it up to GitHub Copilot, do a code review, and also do some other interesting things.

00:31:15.359 --> 00:31:27.839
So code review and documentation are becoming great opportunities because they're often the things that take a fair amount of time, but we don't always necessarily get a lot of time to do them.

00:31:28.480 --> 00:31:28.880
Yes.

00:31:29.440 --> 00:31:43.519
And depending upon uh again with any code review, I don't care what anybody says, if you have 4,000 files to go through on a code review, your level of detail is going to be much less than if you have to go through one file change.

00:31:43.920 --> 00:31:45.119
As a human, right?

00:31:45.200 --> 00:31:54.319
I think it's it's the level that you can the level of effort and time that you go through is challenging, the larger the code review is for the pull request that you made we're reviewing.

00:31:54.720 --> 00:31:59.359
So we we talked about all these MCP servers, and I definitely want to get into the Nubimency.

00:31:59.599 --> 00:32:00.400
Nubimency.

00:32:00.559 --> 00:32:01.119
Nubanincy.

00:32:09.200 --> 00:32:10.559
I'll make it easy for you.

00:32:10.799 --> 00:32:13.039
Newbie, as in like new guy.

00:32:13.119 --> 00:32:13.920
I'm a newbie.

00:32:14.079 --> 00:32:14.400
Okay.

00:32:14.880 --> 00:32:20.240
Um, which is one of the Latin permutations for cloud and mancy for magic.

00:32:20.559 --> 00:32:21.599
So it's cloud magic.

00:32:21.839 --> 00:32:28.559
I was going to ask you where it came from as we talked about the setup of your project and what the project is, but it's newbie, I got that.

00:32:28.640 --> 00:32:36.720
That's the old days of noobs and newbies and all the terms that we had for somebody that was new, and Mancy for magic.

00:32:37.039 --> 00:32:39.359
I knew you would have to have something like that in there.

00:32:39.599 --> 00:32:44.319
Absolutely just because of uh the interest that you have outside of AL coding.

00:32:45.039 --> 00:32:49.599
Okay, so now we have these MCP servers, we have these agents, we have these instructions.

00:32:49.920 --> 00:32:52.319
How do we get them?

00:32:52.559 --> 00:32:53.680
How do we create one?

00:32:53.839 --> 00:32:54.079
Right?

00:32:54.160 --> 00:32:59.519
So now we're saying we have instructions for an agent, we have this MCP toolbox.

00:32:59.839 --> 00:33:01.039
Where do we put it?

00:33:01.119 --> 00:33:02.240
How do we create it?

00:33:02.400 --> 00:33:04.480
How do we do it?

00:33:04.640 --> 00:33:04.960
Right?

00:33:05.200 --> 00:33:08.640
I mean, if you think about this, it's how do we put all that together?

00:33:09.039 --> 00:33:13.839
Well, I mean, the short answer to that, my favorite answer is when you don't know, ask the agent.

00:33:14.000 --> 00:33:14.960
It knows.

00:33:16.960 --> 00:33:22.640
So when it when it gives you the instructions and you go, that's really cool, but where the heck do I put this for next time?

00:33:22.799 --> 00:33:23.920
It'll tell you.

00:33:24.559 --> 00:33:25.519
See, that's beautiful.

00:33:25.599 --> 00:33:35.759
That's the whole you know, I I gave someone an answer the other day, and you just gave the answer back to me because somebody asked me a question and I gave them L M G T F Y, right?

00:33:35.920 --> 00:33:37.119
Let me Google that for you.

00:33:37.279 --> 00:33:39.599
So it's the same thing, but different.

00:33:39.839 --> 00:33:44.160
Now we're getting into asking the agent how to do something.

00:33:44.559 --> 00:33:58.400
Well, and one of the things is true, is like a lot of us in the business central space use VS Code, and if we are using agentic coding or even AI at all in our development experience, it's typically GitHub co-pilot chat because it's easy.

00:33:58.480 --> 00:34:02.559
It's it's built right into the OS or Visual Studio Code environment.

00:34:02.799 --> 00:34:03.920
We don't think about it.

00:34:04.079 --> 00:34:14.159
But the reality is there are multiple different providers out there that provide different coding tools, um, and some people encourage people to explore which one works best for them.

00:34:14.320 --> 00:34:18.639
And each of those tool sets will store their instructions in different places.

00:34:18.800 --> 00:34:26.480
So it's valuable to say, it's valid to say, you know, depending on the tools you're using, the defaults may be somewhere else.

00:34:26.719 --> 00:34:38.000
In our organization where we are using GitHub Copilot, um, there's a standard name you can give the file in the standard folder, and it will know to always look at that instruction set.

00:34:38.400 --> 00:34:43.360
So like it's dot github slash copilot dash instructions dot md.

00:34:43.519 --> 00:34:46.159
It's just markdown files, so it's just English.

00:34:46.320 --> 00:34:52.000
Um and anything you put in there, the copilot will automatically pick up as part of just existing.

00:34:52.559 --> 00:34:53.679
So it's pretty nice.

00:34:55.599 --> 00:34:58.000
I have to pause because now I'm thinking about all this.

00:34:58.159 --> 00:35:17.679
So that anybody that has a project, they can create a special folder and you can ask the agent if you don't know what it is, if Jeremy just said it, and you can put your own instructions in there, and then the GitHub co-pilot chat that's within VS Code environment, will use those instructions every time.

00:35:17.920 --> 00:35:19.039
To every time.

00:35:20.400 --> 00:35:26.320
So it's like a welcome kit that as soon as that excited employee shows up, it's like, ah good, welcome inside.

00:35:26.400 --> 00:35:29.199
Here, read this first, then come see me.

00:35:30.639 --> 00:35:31.440
I like that.

00:35:31.679 --> 00:35:40.400
And then can you specify which instruction set to use so you can have multiple functions, or do you have one big function?

00:35:41.360 --> 00:35:54.559
What we ended up doing, and what I've referenced um that I I referenced in that blog series the after the first week or so um of using the instruction set that I baked up, it was too big.

00:35:54.800 --> 00:36:01.679
Um the I built a very nice, lovely book, but the LLM only looks at so much.

00:36:01.840 --> 00:36:08.559
It's not gonna read every single page carefully and memorize everything about a whole dictionary's worth of stuff.

00:36:08.639 --> 00:36:09.840
That's too much.

00:36:10.079 --> 00:36:22.079
So what it was doing was we were finding that depending on what the developer in our team was doing at the time, it sometimes was fantastic or sometimes would be way off course.

00:36:22.400 --> 00:36:29.760
And what I ended up realizing that as developers, we do context switching.

00:36:30.000 --> 00:36:54.079
I might be in spec reading mode and analy uh analyzing mode to look at what someone's asking me to do, and then I'm trying to turn that into an architecture and a plan, and then I'm trying to code it, and then I'm trying to think about performance, and then I'm trying to think about telemetry, and then I'm trying to think about testability, and then I'm thinking about documentation, and then I'm thinking about extensibility.

00:36:54.239 --> 00:36:56.400
All of those are different contexts.

00:36:56.639 --> 00:37:02.639
We as people slide between them without thinking, they're just so very comfortable to us.

00:37:02.800 --> 00:37:06.320
There's no friction of moving between those things for most people.

00:37:06.800 --> 00:37:11.679
I won't say everyone, but most people, it's very easy to slide between those different roles.

00:37:11.840 --> 00:37:17.679
Some people are better at those different parts than others, and maybe they'll say, you do the architecture, I'll write the code.

00:37:17.760 --> 00:37:18.800
It's fine.

00:37:19.119 --> 00:37:31.519
What we ended up doing was we gave special instruction sets that defined each of those coding contexts to say, you are, in this context, only an architect.

00:37:31.679 --> 00:37:40.800
Don't write me any code, just write me a plan of what the application should be structured like and what it should do based on the specification that we've got.

00:37:41.039 --> 00:37:43.440
I don't want you to do any coding work for me.

00:37:43.519 --> 00:37:48.719
I just want a plan so that I can validate the plan before it goes into code production.

00:37:49.119 --> 00:37:59.519
Um and what we ended up doing with that, uh, just to make it very easy to like mentally think through that code context switching, uh, it ends up working really easy to give each of them names.

00:37:59.679 --> 00:38:04.400
So it could be like, I want to talk to Sam about code, I want to talk to Roger about reviewing.

00:38:04.880 --> 00:38:29.119
Um, if you don't know about the project, check out the project and read the the trail that Jeremy left as he's gone through this project because that's what it actually came up to was a bunch of you spoiled it, Chris, a bunch of names for all of these agents.

00:38:29.360 --> 00:38:31.199
It's it's laughable.

00:38:31.280 --> 00:38:32.480
It's it's almost laughable.

00:38:32.719 --> 00:38:33.760
And what are some of the names?

00:38:34.000 --> 00:38:37.360
I do have questions about this, but what are some of the names that you gave them since Chris uh mentioned it?

00:38:37.760 --> 00:38:45.679
Let's see, Alex Architecture, uh Sam Coder, Roger Reviewer, Quinn Tester, Jordan Debugger.

00:38:45.920 --> 00:38:53.440
Uh we've got a special uh one specifically to help like people who are new to BC development called Maya Mentor.

00:38:53.760 --> 00:39:06.159
Um and she, for example, we've got new people who joined us since the summer, and it's phenomenal because our juniors have been able to just pop open projects and then ask this Maya role, can you explain this project to me?

00:39:06.239 --> 00:39:07.599
What sh where should I start?

00:39:07.760 --> 00:39:15.840
And it understands your role is just to explain to this new guy who's never seen AL code before, where do I even start to read it?

00:39:16.079 --> 00:39:23.760
So um we found that it was really easy for people to remember like the names much more than I need to talk to the review guy.

00:39:24.559 --> 00:39:28.960
Yeah, you it's just funny because I I did look at your website and I was like, are these real people?

00:39:29.039 --> 00:39:35.039
Like the project leaders, Mistress, Scopewell, uh, supply chain, functional consult, pick forward, been right.

00:39:35.519 --> 00:39:36.960
I'm like, are these real people?

00:39:37.039 --> 00:39:41.599
And I'm like, I had to pause for a minute, and I'm like, okay, they're not real people.

00:39:41.840 --> 00:39:42.800
This is fascinating.

00:39:43.119 --> 00:39:44.159
But you give a name, right?

00:39:44.320 --> 00:39:46.079
Like it's like you fall in love with them.

00:39:46.400 --> 00:39:48.079
But it's almost like you build your own team.

00:39:48.400 --> 00:39:56.719
And that's the key with this, is I'm following what everybody is doing with this, uh, within the community and outside the community, because you mentioned REG and all those other things.

00:39:56.800 --> 00:40:06.559
I find myself in the in the when I'm driving somewhere, I listen to YouTube now, trying to get up with all these new terms, and I always end up forgetting most of them because they always have like a new one, it seems.

00:40:06.880 --> 00:40:08.800
So it's like building your own team.

00:40:08.880 --> 00:40:19.760
So you can have multiple instruction files in your repo in this in the context of what we're talking about, and those different instruction files have something in that say what they do.

00:40:19.840 --> 00:40:27.039
So when you're talking with your agent, you say you are uh Maya mentor.

00:40:28.480 --> 00:40:38.400
Here's my question, basically, or you are you know Brad, the best coder, write this function procedure for me, right?

00:40:38.639 --> 00:40:40.159
And then it will do that for you.

00:40:40.400 --> 00:40:42.559
I I love the reference to the like you said, you know.

00:40:42.880 --> 00:40:46.559
I have to just stop this conversation right now because I'm gonna go set all of this up.

00:40:46.880 --> 00:40:51.199
I love the magical references though, like the fantasy world that you've built.

00:40:51.280 --> 00:40:51.599
Yeah.

00:40:51.920 --> 00:41:01.840
And as a uh when I was growing up as a gamer, I I love the references to that because it's like, oh yeah, I can it's easy for me to remember those characters, right?

00:41:02.159 --> 00:41:03.519
When you're building this thing.

00:41:03.599 --> 00:41:04.960
This is fascinating.

00:41:05.599 --> 00:41:16.559
So let's wrap the MCP topic up with one last thing that is on this like journey and everything like that, and then I'll talk to the the newbie mancy project and what the heck is that.

00:41:16.800 --> 00:41:21.760
And uh because they're not they're they're related, but they're not record dependent on each other.

00:41:22.000 --> 00:41:27.599
Um the uh all of the stuff that I've learned with like these instructions and everything.

00:41:27.760 --> 00:41:32.079
I also learned how to interpret like the project AL guidelines.dev.

00:41:32.639 --> 00:41:39.039
All of that wisdom is brought into the MCP server that I released called BC Code Intelligence.

00:41:39.199 --> 00:41:41.599
And all of the AL guidelines are brought in.

00:41:41.679 --> 00:41:49.760
So that MCP, like I mentioned, the toolbox, that includes in it all of the topics that are on AL guidelines.

00:41:50.159 --> 00:41:57.760
And so what that MCP for BC code intelligence is for, again, open source, anyone can install it.

00:41:57.920 --> 00:42:05.039
If you go to the GitHub project for it, I'm sure there'll be lots of lovely links in the comments because you guys do a great job of linking to things.

00:42:05.119 --> 00:42:12.719
Um, the GitHub project for the BC code intelligence, there's literally a blue button that says install this into my Visual Studio Code.

00:42:12.880 --> 00:42:15.440
Um click, that's it.

00:42:16.079 --> 00:42:23.119
No, I laughed because when I saw the project, I saw the project, I was talking with Jeremy because I'm trying to figure out, okay, with this MCP server, where does it run?

00:42:23.199 --> 00:42:24.079
What do I do and stuff?

00:42:24.159 --> 00:42:27.679
I was talking to him, and he just wrote back to me, just hit the blue button.

00:42:27.840 --> 00:42:31.039
That's what it's like the like it goes back to what he was talking about.

00:42:31.119 --> 00:42:33.280
Like the agent would do a follow, and I'm like, okay, what do I do?

00:42:33.360 --> 00:42:33.840
How do I do it?

00:42:34.000 --> 00:42:38.159
He goes, here's the link, just click the blue button, and it will do it.

00:42:39.440 --> 00:42:39.760
Yeah.

00:42:39.920 --> 00:42:52.079
So uh for the technically inclined, what that does is in Visual Studio Code, there's an MCP.json for your Visual Studio Code environment, and that lists all of the MCP servers and how to install those.

00:42:52.239 --> 00:42:55.599
And it does require a little bit of uh prerequisites.

00:42:55.760 --> 00:43:03.119
So for example, uh many MCP servers are actually JavaScript or TypeScript type uh little ecosystems.

00:43:03.199 --> 00:43:09.119
Um, so it does typically require that you have the node.js uh libraries installed on your machine.

00:43:09.199 --> 00:43:12.239
Uh those are usually included in the README's with people.

00:43:12.320 --> 00:43:15.519
So you if you don't have it for some reason, you can get it up and going.

00:43:15.920 --> 00:43:22.400
So the uh BC Code Intelligence MCP contains all of those experts that we were just talking about.

00:43:22.559 --> 00:43:24.880
It contains all the AL guidelines.

00:43:25.039 --> 00:43:29.360
Um, and some of the roles uh have expanded a little bit over the past couple months.

00:43:29.440 --> 00:43:41.119
Like I've got one that's specifically for uh code archaeology, because oftentimes we take over projects that we don't know anything about, and it's like, well, I need a role to help me understand this app.

00:43:41.280 --> 00:43:43.119
What's the goal of this app?

00:43:43.440 --> 00:43:51.039
Um, and so what you can just do is when you hit that install button and then you got it online, you go, Who's on the BC specialist team?

00:43:51.280 --> 00:44:07.760
And you know, it'll give you the list of all the names, and you'll be like, Great, let's uh, you know, let's have Logan, the archaeology guy, jump in here with me and help me understand this app, or have Maya help me explain why is runtime.8 uh 8.0, why is that set here?

00:44:07.920 --> 00:44:10.559
Can you explain what the right version of that would be?

00:44:10.800 --> 00:44:16.000
So um, and there's a bunch of different prompts that are built into that, which are pre-built instructions.

00:44:16.159 --> 00:44:24.960
So when you've got that MCP installed in your Visual Studio Code environment, you can actually just hit slash in your GitHub chat, as long as you're in agent mode.

00:44:25.039 --> 00:44:34.880
And there'll be this list of MCP BC code Intel prompts that will pre-fill in a whole bunch of stuff that you can just hit send.

00:44:35.039 --> 00:44:38.880
So, like for example, I want you to help me understand this app.

00:44:39.039 --> 00:44:46.079
I want you to help me upgrade this app to version 27 and fix all those number series dependencies that just started breaking.

00:44:46.239 --> 00:44:52.880
You know, all of these sort of things that are just pre-built as prompts that you can just hit slash, pick one, and just hit go.

00:44:53.280 --> 00:44:58.239
I'm just not saying anything because I had to fix a number series yesterday.

00:44:58.719 --> 00:45:00.159
And I had some help.

00:45:00.960 --> 00:45:02.239
Don't tell anybody.

00:45:02.480 --> 00:45:04.880
Uh so you're mentioning these MCP servers.

00:45:05.119 --> 00:45:06.960
So you hit the blue button and install.

00:45:07.119 --> 00:45:10.719
In the con in this scenario, where does that run?

00:45:11.039 --> 00:45:14.159
Because I know there's MCP servers for Learn that you can connect to.

00:45:14.239 --> 00:45:18.400
There's MCP servers for uh some other MCP servers that others have created.

00:45:18.800 --> 00:45:21.280
We're talking about these servers, MCP server.

00:45:22.320 --> 00:45:23.360
We know what it is.

00:45:23.599 --> 00:45:25.440
Where does it run when you click install?

00:45:26.239 --> 00:45:31.440
Just like the wonderful world of USB-C is absolutely universal for everything, right?

00:45:31.599 --> 00:45:34.559
Uh MCPs are universal for everything, right?

00:45:34.719 --> 00:45:37.679
Um, there's two main types of MCP servers.

00:45:37.760 --> 00:45:46.400
Uh, ones that are networked and you can use them in larger projects and on ecosystems, multiple people can call it.

00:45:46.559 --> 00:45:52.159
Um, those are typically the things like the GitHub MCP or the Microsoft Docs MCP.

00:45:52.320 --> 00:46:00.239
There's actually a server running on GitHub or Microsoft site that you're calling directly, and that server ecosystem is out there.

00:46:00.480 --> 00:46:16.400
Many of the ones that you can install and run for yourself on your development environment are actually another type where they're a little micro server that is actually running on your machine when you start that MCP uh up by having the chat talk to it.

00:46:16.559 --> 00:46:20.000
Um and that's what the case with a BC code intelligence.

00:46:20.159 --> 00:46:28.480
It like many other uh MCPs, it actually starts a little node process on your machine to run the JavaScript server.

00:46:28.639 --> 00:46:41.519
So while that's up and running, there's actually a little tiny server running on your machine that is listening for those calls from the uh copilot agent uh that will call into that local server.

00:46:41.679 --> 00:46:43.599
So it's on your local machine at the time.

00:46:43.920 --> 00:46:44.239
Okay.

00:46:44.400 --> 00:46:49.920
And then is it only running when you have Visual Studio Code open or is it running all the time?

00:46:50.159 --> 00:46:50.320
Okay.

00:46:50.480 --> 00:46:52.239
So I just wanted to get clarification for those.

00:46:52.320 --> 00:46:57.840
I know that many have questions on that on when they're uh running and such.

00:46:58.079 --> 00:46:59.119
So thank you.

00:46:59.599 --> 00:47:04.159
And typically a lot of times the MCP servers will only start once they're called.

00:47:04.320 --> 00:47:14.000
Um and uh in Visual Studio Code, you can hit F1 to open the command palette and say uh MCP, and you'll get a bunch of MCP options.

00:47:14.079 --> 00:47:16.239
And one of the options is list servers.

00:47:16.400 --> 00:47:23.280
That'll show you all the servers you have installed, and in that little window, it'll show you which ones are running and which ones are stopped.

00:47:23.440 --> 00:47:28.480
And that way you can also select each one and say, I want to start or stop this one.

00:47:28.559 --> 00:47:33.679
So you can be in very uh careful control of those as you want to.

00:47:34.239 --> 00:47:34.719
Oh, good.

00:47:34.880 --> 00:47:37.199
So you can keep are they resource intensive?

00:47:37.360 --> 00:47:39.920
I know we talked about tokens, data, and load.

00:47:40.239 --> 00:47:41.760
Are these MCB servers?

00:47:42.079 --> 00:47:42.800
Typically not.

00:47:42.880 --> 00:47:43.039
Okay.

00:47:43.599 --> 00:47:47.840
Typically, they're often just uh many of them are just reflectors.

00:47:48.000 --> 00:47:50.480
Uh for example, talking to Azure DevOps.

00:47:50.639 --> 00:47:55.519
It's uh a wrapper that's calling the uh APIs at Azure DevOps.

00:47:55.679 --> 00:47:58.079
It just is a nice way of going.

00:47:58.239 --> 00:48:13.119
I'll take what the LLM was telling me in natural English and I'll turn that into an HTTP call to Azure DevOps, and when it responds, I'll hand that response back to the uh agent, and the agent knows what to do with it from there.

00:48:13.280 --> 00:48:15.039
So many of them are very lightweight.

00:48:15.440 --> 00:48:16.000
Excellent.

00:48:16.239 --> 00:48:16.960
Excellent.

00:48:18.159 --> 00:48:27.840
Now I know everyone has a better understanding of this, and everyone's going to go click the blue button and install it because that's what I wanted to do when I first started reading this.

00:48:28.079 --> 00:48:30.880
So now let's jump into the newbimancy project.

00:48:31.199 --> 00:48:31.360
Right?

00:48:31.599 --> 00:48:36.239
It's you had me you you had mentioned it's it's similar, but related.

00:48:36.480 --> 00:48:45.119
Um so uh oftentimes I uh I do a lot of presentation and training and writing around Business Central.

00:48:45.280 --> 00:49:01.840
And one of the challenges uh with educating on BC, uh DevOps and all these related technologies, you can't show your work because you're doing client work, you're doing internal IP work, you're doing things that you cannot share.

00:49:02.000 --> 00:49:15.280
And so oftentimes when you're going to teach, uh you're wanting to share different things, you have to duplicate all that effort in a share-friendly way because you can't leak IP or GDPR data and all that sort of thing.

00:49:15.519 --> 00:49:18.480
Um I want to create more books.

00:49:18.639 --> 00:49:28.239
I would like to show off more things about uh how DevOps and GitHub and all these different pieces can work, but I can't do that with my company's data.

00:49:28.400 --> 00:49:31.679
I can't do that with my clients' data, I can't do that with our products.

00:49:31.920 --> 00:49:35.679
So I went, I need to be able to do this more regularly.

00:49:35.840 --> 00:49:38.320
I I speak at conferences every year.

00:49:38.480 --> 00:49:45.440
Uh every year I'm having to start over and coming up with like a new like fictional business and a fictional story behind this.

00:49:45.840 --> 00:49:48.400
And I'm kind of a nutter.

00:49:48.480 --> 00:49:53.199
I like to cross-pollinate from some of the different things that I enjoy in life.

00:49:53.360 --> 00:50:01.440
Um, and one of the things I enjoy a very great deal is tabletop gaming, um, particularly role-playing games, DD, and that sort of thing.

00:50:01.599 --> 00:50:04.000
Uh, I've DM'd for a long time.

00:50:04.320 --> 00:50:15.840
And so I I enjoyed the idea of what if I took both of those, uh, this thing that I love and this thing that I keep struggling to fulfill.

00:50:16.079 --> 00:50:18.159
What if I crossbreed those?

00:50:18.320 --> 00:50:21.440
What if I do something silly with those things together?

00:50:21.679 --> 00:50:34.719
And so Newbie Mancy is a project where I'm building a fictional business central partner that is fictionally helping a group of retired heroes.

00:50:35.119 --> 00:50:43.519
These retired heroes help save the world, and now they've ridden off into the sunset, but happily ever after means what?

00:50:44.320 --> 00:50:58.800
So each of these five retired heroes has their project that they've always wanted to do, and now that they've helped save the world and they've found their fortune and all that sort of thing, what do you do with your life now?

00:50:59.119 --> 00:51:07.599
And so they're trying to run their respective businesses, but you know, running a business still takes a lot of work.

00:51:08.000 --> 00:51:31.119
So the idea behind uh the newbie mancy project is I'm going to fictionally treat those five uh challenging customers as a family of companies that we're producing um some app source apps for, some uh PTEs for uh demo data, testability, all of that stuff.

00:51:31.360 --> 00:51:37.440
And because this is all 100% fictional, I can do this in uh an open way.

00:51:37.760 --> 00:51:45.039
So, for example, I'm building DevOps up with only public projects for this area.

00:51:45.199 --> 00:51:50.800
So that way, if you're trying to figure out, okay, how is this guy doing pipelines in Azure DevOps?

00:51:51.280 --> 00:51:53.679
Well, all of the source files are there.

00:51:53.840 --> 00:51:58.719
You can just go in and look at them, you can see all of the flow and everything.

00:51:58.960 --> 00:52:06.239
So it it gives me a platform by which I can share more about how to do all these different things.

00:52:08.639 --> 00:52:09.920
I think it's amazing.

00:52:10.000 --> 00:52:15.440
And it's funny because when I first looked at the website when you first started promoting it, I start with I saw a bunch of people on there.

00:52:15.599 --> 00:52:19.360
And I'm like, oh, is Jeremy doing this or are all these other people doing it?

00:52:19.599 --> 00:52:23.199
So it was uh You know, I'd have to look.

00:52:23.280 --> 00:52:31.519
I it's it's something in the neighborhood of like 30 or 40 fictional business central practice people who are gonna be implementing all this.

00:52:31.760 --> 00:52:39.280
And as I'm fleshing out the story this fall for the heroes and their businesses, no man is uh an island.

00:52:39.440 --> 00:52:47.039
So each of those uh businesses is gonna have their own little cast of characters for each of those businesses as well, because why not?

00:52:47.360 --> 00:52:52.079
It's it's a fun, it's a fun project to follow, it's a fun site to follow.

00:52:52.400 --> 00:53:04.559
And I also enjoyed the blog articles following the you know, from AI Skeptic to uh you know, in 90 days was your you know, I think your title for that, or you had a few of them on there.

00:53:04.639 --> 00:53:07.199
I can't really call them all, I apologize, but I remember the concepts.

00:53:07.280 --> 00:53:09.679
Uh definitely a great follow.

00:53:09.840 --> 00:53:11.519
It's definitely entertaining.

00:53:11.760 --> 00:53:21.360
And as Chris had mentioned before, some of the names are pretty unique for even on the website now as looking uh as you expand it, because uh you know you have been updating and added content with it.

00:53:21.440 --> 00:53:30.800
So it's um yeah, now it's not a small journey on that I'm taking uh with some of the stuff that I'm doing.

00:53:30.880 --> 00:53:35.280
I've mapped out uh this past weekend, I was working on it a little bit.

00:53:35.519 --> 00:53:44.000
Uh 38 total apps are gonna be in the constellation of all the different pieces to like demonstrate all of the different parts.

00:53:44.239 --> 00:54:02.880
So, like, you know, the app source app equivalent for this uh family of companies, uh a key foundation layer, and three apps that are on top of it to represent good, you know, multi-app infrastructure, and then individual PTEs that sit on top of each of those parts depending on the business type.

00:54:03.039 --> 00:54:18.400
Um, so I think I've got all 38 apps all now scaffolded with all the basics, and I'm gonna be working on uh pipelines and um the next step up for the big lift on this is I'm gonna be starting to produce all the demo data that will go with this.

00:54:18.480 --> 00:54:24.079
Just like uh Kentoso has, you know, the ability to install the different modules.

00:54:24.239 --> 00:54:32.719
Uh this solution is gonna be which of the heroes do you want to install into a test environment to be able to use their data as test data?

00:54:32.960 --> 00:54:33.760
Go for it.

00:54:36.079 --> 00:54:37.280
That's impressive.

00:54:37.519 --> 00:54:42.320
And I I sit back and I listen to all this, and I'm like, how do you have the time to do all of this?

00:54:42.480 --> 00:54:51.039
To to work, to speak, to to learn, and then also to put together a basically a fictional, I'm calling it a fictional universe.

00:54:51.199 --> 00:54:59.840
I go back because I also grew up playing tabletop games, you know, Dungeons and Dragons, uh, magic, you know, the card game, you know, all of these.

00:55:00.000 --> 00:55:04.320
I wish life was still like that back then, to be honest with you, because that was so much fun doing all those.

00:55:04.400 --> 00:55:09.280
But it's almost like you're building a whole world or a whole universe.

00:55:09.679 --> 00:55:10.320
Absolutely.

00:55:10.719 --> 00:55:12.000
Yep, how you're doing this?

00:55:12.800 --> 00:55:18.480
There's you know, there is a fictional world, there's fictional countries, there's a whole bunch of stuff.

00:55:18.639 --> 00:55:27.760
I've got a whole knowledge base that for my agents who are helping me build some of these things up, because yes, I'm using agents to help me build all these things.

00:55:28.000 --> 00:55:33.679
I've got a knowledge repo about all of the different countries and like what are the cities in each of them.

00:55:33.840 --> 00:55:38.400
So that way when we're generating the demo data, there's there's a basis to work from.

00:55:40.079 --> 00:55:42.400
You know what I think would be interesting from this?

00:55:43.199 --> 00:55:50.480
After you build this out and you have all these instructions for the countries and the companies and the people, have it write a book.

00:55:51.360 --> 00:56:07.760
Have it write a book about the countries and the people and their lies, just to see what like have an agent write the book and say, here's a book that's completely AI generated based upon this newbie mancy project.

00:56:08.159 --> 00:56:11.280
I think that would be an interesting result if you're building it up this much.

00:56:11.679 --> 00:56:16.079
We we strike there into an interesting heart of an ethical conundrum.

00:56:16.239 --> 00:56:45.599
We talk about this a lot in my family because my wife is from an art background, and the challenge of bringing AI into creative spaces is that there is a reasonable and angry sort of pushback from people that if you're using AI tools in such a way to do creative works that it would be better to utilize a creative person for, um, that that's not uh that that doesn't feel right.

00:56:45.760 --> 00:56:47.039
It gets a lot of pushback.

00:56:47.199 --> 00:56:52.320
So for example, I don't use AI generative tools for images.

00:56:52.480 --> 00:56:54.000
I hire graphic artists.

00:56:54.159 --> 00:57:05.119
I don't uh typically hire AI editors because I actually really rely on um some of the different people that I work with to help do a lot of the editing work.

00:57:05.360 --> 00:57:26.880
So it's an interesting balance for me of I don't want to use I'm okay with using AI to make the things I would do happen faster, but if I'm using AI to replace a creative person, and that includes, you know, my voice of storytelling, I actually would find that that would be really challenging for me to accept.

00:57:27.039 --> 00:57:42.159
And there are uh some fairly famous incidents uh at conferences of gaming conventions and things like that where there was a discovery that people were using AI tools to make the art that they were selling at the convention, and they were thrown out.

00:57:42.559 --> 00:57:42.880
Yes.

00:57:43.840 --> 00:57:45.840
So there's some very big pushback.

00:57:46.320 --> 00:57:46.960
Yes, I understand.

00:57:47.119 --> 00:57:52.159
No, I understand the pushback, and I understand that whole dilemma as well.

00:57:52.400 --> 00:57:52.559
Yeah.

00:57:52.800 --> 00:57:57.840
Um because it's uh it's it's it's a fine line.

00:57:58.000 --> 00:58:02.880
Um it is the it's challenging to be pro-AI.

00:58:02.960 --> 00:58:05.760
I see the value, I experience the benefit.

00:58:05.920 --> 00:58:12.320
Uh there's a lot of uh the answer to your question of how do you have time for so many of these things is because of AI.

00:58:12.480 --> 00:58:17.840
There's a bunch of stuff that I'm multitasking between, and these tools are helping me do faster.

00:58:18.079 --> 00:58:25.039
Um I genuinely am getting much more done than I've ever gotten done before in the past few months.

00:58:25.199 --> 00:58:32.880
And I described it to someone as, you know how autistic folks talk about, you know, the around their friends they can unmask.

00:58:33.119 --> 00:58:39.519
They can uh they can be their true selves, they don't have to like be an interface to the rest of the world.

00:58:39.679 --> 00:58:57.360
Uh I describe my working with agentic development as one of the first times in my life where I'm able to produce code or content that is code adjacent that it's as fast as I can come up with the ideas.

00:58:58.400 --> 00:59:04.159
It feels like for the first time I'm going the speed that I can be at in my head.

00:59:04.559 --> 00:59:06.320
And that's a big deal.

00:59:06.880 --> 00:59:12.239
No, that's I I can see it's it's it goes back to what you would just sort of talk about.

00:59:12.400 --> 00:59:22.400
There's a fine line between the practical use of AI and how far you take the use of AI based upon uh what you're doing with it.

00:59:22.559 --> 00:59:28.960
But that and you'll see like traces of that in some of the things that I do.

00:59:29.119 --> 00:59:38.719
Like I'm still, as more often than not on social media, you'll see me post like hand-drawing things because there's an autent authenticity to that.

00:59:38.800 --> 00:59:42.079
That no, that's physically something I just made.

00:59:42.400 --> 00:59:56.239
And um for the folks who are AI skeptics or against AI, there's a kind of a respect and recognition of like you're you are not replacing a human with this work, and you're trying to be careful.

00:59:56.480 --> 01:00:08.159
So, uh, for example, there's a great business insider about like the uh article about the dangerous challenge of how much AI is impacting climate change, which is something I care a lot about.

01:00:08.480 --> 01:00:20.480
So for me, building BC code intelligence isn't to try to get to people to get people to use AI lots and lots more, but I know that that's going to happen anyways.

01:00:20.719 --> 01:00:29.119
So if people are using it in a way to get better results more correctly, there's less wasteful use of AI.

01:00:29.440 --> 01:00:39.199
So for me, by building these tools, it's uh it's about making it uh mm as ethical as I can make it if we're gonna do it anyways.

01:00:40.239 --> 01:00:40.800
Yes.

01:00:41.039 --> 01:01:06.960
I understand I mean I'm saying I understand and I see and again you hit it for anybody that may think or be a skeptic or may think that what we're discussing about ethics and AI contradict each other, that is a great way to put it that it's going to happen anyway, so why not do it in an efficient and ethical way to minimize the impact as much as possible.

01:01:07.119 --> 01:01:07.360
Right?

01:01:07.519 --> 01:01:09.039
Or the negative impact or the side effects.

01:01:09.199 --> 01:01:15.920
You're talking about climate and this this side effects or impact of AI across the board.

01:01:16.159 --> 01:02:12.960
So um I think uh we cover that that it makes you think you know we we we we we talk about all the great things of AI but it also does make you think about the AI's impact on uh the the world not only the physical world but also the people in the world and even um mentally with individuals now because I've uh had lots of conversations with individuals that struggle with AI and just what it's doing to them mentally if you take a look at it you know it's doing a lot of great things but it's also creating a lot of anxiety and angst in many individuals as well too well I'm a dad and you know I've got a kiddo in high school and you know one of his perspectives as a child growing up in the AI era is he's taken the ethical stance of I refuse to use AI while I'm in school at all so that I'm never in a discussion with anyone about is this work genuinely yours?

01:02:13.599 --> 01:02:20.559
Because he wants to have that purity of I can always say this is something I'm not doing at all.

01:02:20.880 --> 01:02:23.039
That I'm I'm just against using it.

01:02:23.199 --> 01:02:26.880
And I agree wholeheartedly with his decision to do that.

01:02:27.039 --> 01:02:37.199
I mean I would support him if he chose otherwise but he wants to in these formative years make sure that he's developing those skills himself and that's fair.

01:02:37.440 --> 01:02:47.760
Yeah that that is that is a good point because I have two high school kids right now that um you know they don't use like same similar to you Jeremy they refuse to use AI.

01:02:48.159 --> 01:03:00.159
They want to know it's like uh it's like the analogy of like you know you can fly a plane and autopilot and you'll be fine but if it doesn't work you need to be able to learn how to do it manually.

01:03:00.480 --> 01:03:02.559
So you know they they don't use it.

01:03:02.639 --> 01:03:11.519
Um the only time they've ever used it was they need to validate something and rather than Google they just had to copilot or chat GPT and that was it.

01:03:11.679 --> 01:03:13.039
That's the only time they have to use it.

01:03:13.679 --> 01:03:28.400
One of my favorite uses of it that is phenomenal uh that is also you know in that space of it's about making the person better um use AI and copilot tools to challenge what you're doing or to clarify.

01:03:28.559 --> 01:04:05.039
So for example if I'm doing presentations I will for example maybe run it through a copilot to say you're a uh consultant in the BC industry I'm talking about this topic this is the context here's the PowerPoint deck what questions would you have that I have failed to answer this is my premise have I really kind of hit the points of what I'm explaining so I do often use validation tools around Copilot to also help me make me a better communicator and make me think of the gaps that I'm missing.

01:04:05.199 --> 01:04:11.920
And BC code intelligence as an MCP is that same sort of idea that it's it's about trying to close those gaps.

01:04:12.079 --> 01:05:04.880
What are the things I forget what are the things I don't think of can we close those up yeah great great great uses for those it is it is and this has been a great discussion uh uh newbie mancy I learned how to say properly I think everyone should follow that project that the team and I think also um the uh code uh mcp that you have with all those agents is is also something that everyone should use and also help contribute to uh you had mentioned it's open source so if you have uh contributions uh we can make it a little more efficient for everybody and I I have to create a Brad one i i think I'll have to come up with some sort of agent that's a Brad one a Brad the I have to follow the naming the BC code intelligence MCP also supports um layering tech.

01:05:04.960 --> 01:05:31.039
I've talked to a couple of early adopters if you want to add stuff that's specific to your practice or even specific to your project there's a guide in the wiki for that project that says here's how I add stuff specifically for my organization and here's how I add stuff specific to my project because there might be good general guidelines that you do something slightly different and then you do something even slightly more different in the project level.

01:05:31.280 --> 01:05:33.920
And that includes adding more specialists.

01:05:34.079 --> 01:05:51.760
So if you want to experiment with it and add a new specialist type called Brad the superhero you absolutely can do that and the MCP server is built to support loading that as an extra layer much in the same way that BC does extensions, the MCP server does layers so that you can just add stuff in.

01:05:52.239 --> 01:06:04.639
See you thought of everything when you put that together the layering is great because like you had mentioned if somebody has any some individual specific rules that are unique to them that they may not want to share they still can use the project.

01:06:07.440 --> 01:06:14.800
Oh that's the wicked on the rabbit hole of object naming and object numbering and affixes and namespace.

01:06:15.760 --> 01:06:17.360
We could spend all day talking about those.

01:06:17.840 --> 01:07:13.360
Well Jeremy thank you again for taking the time to speak with us this has been extremely informative and I appreciate your time and thank you for sharing with us all that you have done and all that you're doing uh in this episode but as well as what you're doing for the with the community as far as your speaking engagements, your book writing and now uh offering these projects uh to individuals because I know I learned a lot uh following yeah what you had put together as well too I really would have to get uh on those characters do you have are you gonna put images of them like uh like an employee uh character is a phenomenal artist I know in town who loves to do RPG character art so I'm I'm hoping that as a uh Christmas gift to myself I'm actually gonna buy a portfolio from him of I would love to have character art for each of these uh wonderful little characters and we'll flesh out their backstories over the upcoming years.

01:07:13.519 --> 01:07:15.679
Yeah that'd be awesome.

01:07:16.000 --> 01:07:20.559
Then you can make a game a tabletop game with these characters.

01:07:20.719 --> 01:07:22.239
See that's what this I want something like this.

01:07:22.400 --> 01:07:32.320
I'm seeing this whole cool mythical world because I like those types of worlds too right it's I can just see this whole mythical world coming together from this project.

01:07:32.800 --> 01:08:06.639
I'll tease for the next time I'm joining you guys on the show in the uh probably after the new year of uh I I've got some l groundwork laid for uh BC character sheets we'll have to we'll we'll schedule that up soon to get you back on and also see you know I want to follow this project and see where it it grow it goes and and how it grows um it's um I I think with technology as a change is advanced I think you know give it tomorrow and there'll be new technology that we can utilize with this.

01:08:07.760 --> 01:08:19.359
But if anyone would like to get in contact with you to learn more about Nuba Mancy, learn more about your uh MCP server knowledge experience uh what's the best way to get in contact with you?

01:08:19.760 --> 01:08:24.319
Uh these days the most often place I'm I'm chatting with people tends to be LinkedIn.

01:08:24.399 --> 01:08:30.800
I am on Blue Sky so you can find me there as well um but LinkedIn has been the most active for me lately.

01:08:30.880 --> 01:08:35.279
That's where the Microsoft people hang out so I'll join them there.

01:08:36.399 --> 01:08:49.119
Great great thank you we'll have links in the show notes and then also we do have a guest profile so your guest profile will be attached to this as well with some of the additional information for others to get in contact with you.

01:08:49.439 --> 01:09:00.239
Thank you very much I'm going to go sit down and start thinking of Brad the superhero and I'm going to work on layering it to see what Brad can do for my coding projects.

01:09:00.720 --> 01:09:19.359
Sounds good thank you talk to you soon take care thank you Chris for your time for another episode of in the dynamics corner chair and thank you to our guests for participating thank you Brad for your time it is a wonderful episode of Dynamics Corner Chair.

01:09:19.520 --> 01:09:57.359
I would also like to thank our guests for joining us thank you for all of our listeners tuning in as well you can find Brad at developerlife com that is D V L P R L I F E dot com and you can interact with them via Twitter D V L P R L I F E you can also find me at mattalino and my Twitter handle is Mattalino16 and see you can see those links down below in the show notes.

01:09:57.520 --> 01:10:02.319
Again thank you everyone thank you and take care of