Dynamics Corner

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

• Jeremy Vyska • Season 4 • Episode 434

Share episode

In this episode of Dynamics Corner, Kris and Brad are joined by Microsoft MVP Jeremy Vyska. The trio discusses the intersection of AI and Business Central development. Jeremy shares his journey from being skeptical about AI to embracing AI tools, highlighting his innovative Nubimancy Project. This project provides an AI-based team for developing Business Central extensions. The discussion also addresses the ethical considerations surrounding AI, the creation of fictional business scenarios for educational purposes, and the practical applications of AI in coding and project management. The conversation offers valuable insights into how AI can enhance productivity while upholding ethical standards.

Send us a text

Support the show

#MSDyn365BC #BusinessCentral #BC #DynamicsCorner

Follow Kris and Brad for more content:
https://matalino.io/bio
https://bprendergast.bio.link/

SPEAKER_00:

Welcome everyone to another episode of Dynamics Corner. What does MCP stand for? And what does it have to do with anything in the fantasy magical world? I'm your co-host Chris.

SPEAKER_03:

And this is Brad. This episode is recorded on October 9th, 2025. Chris, Chris, Chris. What does it have to do with the in the realm of a fantasy world? I don't know. But we did have the opportunity to learn about that because I grew up playing those tabletop role-playing fantasy games. And I wish that we still lived in a world where those were much more popular than they are. With us today, we had the opportunity to speak with Jeremy Viscous.

SPEAKER_01:

Yes. Hello, hello.

SPEAKER_03:

How are you doing?

SPEAKER_01:

Uh busy, as always.

SPEAKER_03:

Busy? Always busy. I like the new background. It's uh it's different. It's different.

SPEAKER_01:

Yeah. Well, I mean, you know, things have changed up a little bit. Uh I'm I'm not with Spare Brained anymore, so I don't have my own uh little studio space. 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.

SPEAKER_03:

But uh it's it's uh getting back to working in the office, as they say.

SPEAKER_01:

In a fashion, definitely.

SPEAKER_03:

Yeah, no, that's good. That's good. It's I like being in the office at sometimes. 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. 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. So I think sometimes people are a little more apprehensive to maybe reach out and talk to somebody. So I think uh it's it was a little more challenging. So I think going to the going to the office is it has its benefits and it also has its drawbacks.

SPEAKER_00:

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. But you know, he's actually right there.

SPEAKER_03:

Yeah, no, it's it's good. You get some of that small talk. Um, so again, welcome back. 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. But before we jump into that, would you mind telling us a little bit about yourself?

SPEAKER_01:

Sure, sure. Uh let's see. Um I'm Jeremy Visca. I'm an American who relocated to Sweden ten years ago. I've been working with BC now uh for coming up on 26 years, uh so a real long time. I've been a BC MVP for five years. Coming up on five years, something like that. Uh in that neighborhood. Time's a blur. 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. 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. So uh lots going on.

SPEAKER_03:

Lots going on, lots going on in uh your your API book I still have as a reference, which is nice. Uh and I do appreciate all that you've done for the community. And as you had mentioned, I started watching you with this. 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? 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. Uh, would you mind telling us a little bit about that project?

SPEAKER_01:

Sure. Uh I mean let me bring you on the journey, like well, bring the audience along uh for the first time keeping up.

SPEAKER_03:

But the first question I have to get to cut you off, how do you pronounce it?

SPEAKER_01:

The the uh newbiancy project?

SPEAKER_03:

Yes, that's it. Thank you. Thank you. I want to go on the journey now, but that was like one of the things I'm saying. I'm like, I call it like I was calling it like nubibacy. 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?

SPEAKER_01:

I carefully test uh and make sure that everything I bring on the show is something difficult for you to say. It's it's mission accomplished, right off the show. Hey, me too. Just let's say, Chris, watch out. I know he's from the northeast. You missed that.

SPEAKER_03:

He he he he relocated to Sweden, but he wasn't too far from me.

SPEAKER_01:

Uh which is an interesting aside to the things we've talked about before. 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. When I shut down Spare Brain at the end of last year, I did that product didn't die. That became open source. Uh and it's on App Source still now for free with no licensing. 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. Um you can now climb through all the source code and get to know how the heck did I do all that stuff? Go look.

SPEAKER_03:

That's good, excellent. So Braid is now open source and still available in App Source. Excellent. Excellent.

SPEAKER_01:

So all right. So the uh the the actual story we wanted to talk about. Okay. So um conference season in Europe happens pretty heavy in the spring. We've got a lot of great conferences from March through June. Um, there's a lot of things going on in that time stretch. You know, the holidays are finally over, it's nice enough to go outside, and and boy, do things get busy. 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. 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?

SPEAKER_03:

Companion, I think.

SPEAKER_01:

Companio. Thank you. Yeah, that is correct. 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. 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. It had as much value to me as that. 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. And I'm like, what's the disconnect? How is it possible that 30% of code is coming from people hitting tab? That doesn't make sense. Exactly.

SPEAKER_03:

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. 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. So that video is available. The BC Tech Days video did come out uh recently. 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.

SPEAKER_01:

Yep. So the that was the seed of understanding for me was get copilot out of ask mode. 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. It's it's a very different experience when you switch over to that agentic mode. Um and kind of hearing that, I went, I still don't I still don't feel it. Like, you know, I I I've been doing this a long time. It can't possibly be faster. Frankly, I'm a very fast coder. 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. Um and uh so I I was pretty suspicious. 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. 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. What can we do to use and abuse that level of capacity? So um, you know, I did I plan to do this talk on the parallel development. Um I've gotten feedback since that some people have gotten operations that were nine-day operations down to six-hour operations. Wow. So uh it's making a big difference for some folks. Um but I set myself out the challenge of if I'm gonna do this, I want to challenge me, not just my audience. And I made it that I am not allowed to touch or write the code. I have to only write instructions for the agent to understand what I'm trying to accomplish.

SPEAKER_03:

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.

SPEAKER_01:

Hands off.

SPEAKER_03:

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. And I I just I don't even I'm speechless with this whole instruct mode and uh and such. So that's uh that's a challenge.

SPEAKER_01:

So um so it was a little bit interesting. 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. Um I I happily uh lifted from AJ Kaufman uh his opening line that he likes to give for some of his sessions. That uh congratulations, you're in a session that is a co-pilot-free session. 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. It doesn't provide value to me, and yet that's all I can hear about. That's terrible. Yeah, it's really frustrating. 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. So there's a natural pushback and reaction to that, and so people you know applauded with that. 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. 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. And then we spent some time talking through how that actually came about.

SPEAKER_00:

Behind the curtain, there's actually a copilot.

SPEAKER_01:

I actually did get a couple of negative reviews from that of I can't believe that you would do that to us. It's like it's still real code.

SPEAKER_03:

I I think that I think that's a little fun. So so let's take it through uh through your journey. 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. 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. Um so you then had a session that you did hands-off. How did that go? And is that what also sparked the project that you have? 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. Is that together?

SPEAKER_01:

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. And um after that experience of okay, it could do the job. 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. I could go hands back on the wheel and and not worry about it. Um but it succeeded. I got what I needed out of it for producing decent code. Um, and I genuinely was well a little bit surprised by that. So I started pushing myself um uh a little bit more to explore it in the day-to-day job. 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. Um so I didn't I didn't really have time to pick it back up. And then um in July, I took off the first half of July for vacation. 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. What stuff am I missing that I could be doing better? 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. 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. Um, you know, there's a lot of stuff that we're doing in our organization with DevOps and pipelines. 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? I can't share our organization DevOps. So newbie Mancy as a project and the AI development in hand in hand kind of happened at the same time. Of what can I do to share all this stuff that's in my head? Um, what can I do to bring more knowledge about all these different pieces? Is it unfolding construction-wise as a story and a narrative? Uh no, not as not as smoothly as I would like it to. Um but uh in July I spent a lot of time trying to figure out the AI did an okay job for me. It did okay, but I feel like it could do better. And it was right around that same time uh Dmitry Katzen was working on the AL guidelines site. He was trying to put together some instruction set that would help the AI understand AL best practices better. 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. 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. Um and out of that, I started realizing what made good instructions. 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. 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. It picks up where right where you've left it every single time it's starting at the beginning. So if your instruction set is right, right at the beginning, that's where it starts every time. 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. What's the point?

SPEAKER_03:

Yeah, so let's take a step back as you're talking about um instruction set and agents. 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? And maybe we can, I'm sure we'll get into how do we give that agent those instructions. And you're also talking about multiple. I I see I told you I'm just gonna run with this, but we'll start with that. That's when you started with this infrastructure for your team. Sure.

SPEAKER_01:

Okay. 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. But they they they've read only the textbooks in school about development practices. Maybe they've heard of Business Central. And but they're ready to go. Um it doesn't always work great. 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. all espressoed up and you're you're ready to jump in. Uh first go read this instruction manual and then come back to me. And now it's time for you to pick up your task for the day. 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. Here are some of the things you should and shouldn't do. Here's some of the stuff you should know about, and some of the stuff you should know not to do. And that's just a language file because these are running on large language models. So uh one of the recurring jokes these days is what pro what languages do you program in? English.

SPEAKER_04:

Yes.

SPEAKER_01:

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.

SPEAKER_03:

So you you you mentioned the MCP server as well. Again, it's it's it's all I think we'll come full circle to others. 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. So then you can have different instruction files for different agents to do different functions. 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? And then how does it fit with an MCP server? And you know, I'll ask you the$10,000 question. What is an MCP server along with all of this?

SPEAKER_01:

So yeah. 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. What does it need to know to help you out? And what are the things it can and should do, and what are the things it can't do? So, for example, the sales order agent in Business Central, the way they've built that up is through very careful articulation of instructions. It's following instructions just like our agents are in GitHub uh in the uh GitHub chat window in your Visual Studio Code. Um uh that sometimes is referred to as the prompts, prompt engineering, and all that sort of thing. That's the what instructions does the model understand to accomplish and all that. Um so effectively, yes, you you by giving different instructions to the same engine, you give it a different job. 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. What are you doing today? Well, today you're a documentation guy. Today you're a sales order processor, tomorrow you're gonna be an expense agent. 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.

SPEAKER_03:

Okay, okay.

SPEAKER_01:

Um then to the uh MCP server question. 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. 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. Like what what what language are you speaking? 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. That's it. That's really all it is. 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. For example, an MCP server I'm using all the time is connecting to Azure DevOps or connecting to GitHub. It understands how to log in as me on my behalf. Jeremy sent me to create this issue here, have an issue. Okay. 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? 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. Once someone makes that toolbox available, everyone can use it and everyone can say, here you go, to your agents. And that's pretty amazing.

SPEAKER_00:

I like that explanation. It's probably the easiest where I can now picture what is an MCP and what it does. Because that it's it everyone tells me different things. I'm like, okay, can you just explain? That's probably the best one I've heard so far, Jeremy. So thank you for explaining that to me.

SPEAKER_01:

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. 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. And that thinking process is burning tokens. 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. And so tools like Visual Studio Code will actually yell at you if you try to use too many uh MCP tools. 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. 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. 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.

SPEAKER_03:

Yes. Okay, so just if I can peel it back from your explanation, which is as Chris had mentioned, was great. 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. 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. That telephone's a standard that anybody can use, and then someone on the other side will pick up and say hello. So it's a standard way of communicating, and then you can have multiple of those running. 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. 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. But if there's another one for reading instructions or manuals, possibly, you may have a server for that. Another thing that you had mentioned, which I hear a lot of with AI, is tokens. And you mentioned that you can burn up a lot of tokens. What is a token in the context of MCP AI instructions? Is it money? Effective is it's a gold token.

SPEAKER_01:

Right? I know. It brings us back to the arcade days, right? Burning quarters.

SPEAKER_03:

Um the um we put them on the pinball machine when it's your for your turn. You have to remember do you remember that stack in the quarters?

SPEAKER_02:

Yeah, I got next. I got next.

SPEAKER_03:

Just I don't want to digress. I know Jeremy, you want to jump into but just think about what like someone who's younger today. Well, we're talking about putting quarters on a pinball machine or even a regular arcade game to get next. And they grew up with an entire arcade in their hand. It's pretty incredible.

SPEAKER_01:

It is incredible. 100%. 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. Um it's the same sort of idea. A good set of instructions is more compact and it is very much more precise around what should the agent be processing. 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. 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? 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. And the measurement that the LLM uses is tokens. And so that's why people talk about that. 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. Um and tokens are how they meter that, the same way you would meter electricity and water and those sort of things. So a unit of measure.

SPEAKER_03:

Okay, great. And then so it is, it's a meter that goes through it. Okay. So now we talked about instruction sets that someone can write, and I'm sure there's a format for that. We have agents, we have an MCP server, and we have Jeremy's journey through this as well.

SPEAKER_01:

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. 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. 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. I want the agent, I want you to do this task. It did not give me the results I expected. 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. How would I the next agent to know to do it my way? So you can ask the agent, how do I improve it for the next guy?

SPEAKER_04:

Okay.

SPEAKER_03:

Wow. That see, this is ingenious. I'm thinking of all the things I'll have all these agents do for me right now. Like just do a code review. 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.

SPEAKER_01:

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.

SPEAKER_03:

Yes. 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. As a human, right? 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. So we we talked about all these MCP servers, and I definitely want to get into the Nubimency. Nubimency. Nubanincy.

SPEAKER_01:

I'll make it easy for you. Newbie, as in like new guy. I'm a newbie. Okay. Um, which is one of the Latin permutations for cloud and mancy for magic. So it's cloud magic.

SPEAKER_03:

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. 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. I knew you would have to have something like that in there. Absolutely just because of uh the interest that you have outside of AL coding. Okay, so now we have these MCP servers, we have these agents, we have these instructions. How do we get them? How do we create one? Right? So now we're saying we have instructions for an agent, we have this MCP toolbox. Where do we put it? How do we create it? How do we do it? Right? I mean, if you think about this, it's how do we put all that together?

SPEAKER_01:

Well, I mean, the short answer to that, my favorite answer is when you don't know, ask the agent. It knows. 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?

SPEAKER_02:

It'll tell you. See, that's beautiful.

SPEAKER_03:

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? Let me Google that for you. So it's the same thing, but different. Now we're getting into asking the agent how to do something.

SPEAKER_01:

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. It's it's built right into the OS or Visual Studio Code environment. We don't think about it. 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. And each of those tool sets will store their instructions in different places. 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. 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. So like it's dot github slash copilot dash instructions dot md. It's just markdown files, so it's just English. Um and anything you put in there, the copilot will automatically pick up as part of just existing. So it's pretty nice.

SPEAKER_03:

I have to pause because now I'm thinking about all this. 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. To every time.

SPEAKER_01:

So it's like a welcome kit that as soon as that excited employee shows up, it's like, ah good, welcome inside. Here, read this first, then come see me.

SPEAKER_03:

I like that. And then can you specify which instruction set to use so you can have multiple functions, or do you have one big function?

SPEAKER_01:

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. Um the I built a very nice, lovely book, but the LLM only looks at so much. It's not gonna read every single page carefully and memorize everything about a whole dictionary's worth of stuff. That's too much. 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. And what I ended up realizing that as developers, we do context switching. 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. All of those are different contexts. We as people slide between them without thinking, they're just so very comfortable to us. There's no friction of moving between those things for most people. I won't say everyone, but most people, it's very easy to slide between those different roles. Some people are better at those different parts than others, and maybe they'll say, you do the architecture, I'll write the code. It's fine. 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. 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. I don't want you to do any coding work for me. I just want a plan so that I can validate the plan before it goes into code production. 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. So it could be like, I want to talk to Sam about code, I want to talk to Roger about reviewing.

SPEAKER_03:

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. It's it's laughable. It's it's almost laughable. And what are some of the names? I do have questions about this, but what are some of the names that you gave them since Chris uh mentioned it?

SPEAKER_01:

Let's see, Alex Architecture, uh Sam Coder, Roger Reviewer, Quinn Tester, Jordan Debugger. Uh we've got a special uh one specifically to help like people who are new to BC development called Maya Mentor. 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? What sh where should I start? 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? 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.

SPEAKER_00:

Yeah, you it's just funny because I I did look at your website and I was like, are these real people? Like the project leaders, Mistress, Scopewell, uh, supply chain, functional consult, pick forward, been right. I'm like, are these real people? And I'm like, I had to pause for a minute, and I'm like, okay, they're not real people. This is fascinating. But you give a name, right? Like it's like you fall in love with them.

SPEAKER_03:

But it's almost like you build your own team. 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. 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. So it's like building your own team. 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. So when you're talking with your agent, you say you are uh Maya mentor. Here's my question, basically, or you are you know Brad, the best coder, write this function procedure for me, right? And then it will do that for you.

SPEAKER_00:

I I love the reference to the like you said, you know.

SPEAKER_03:

I have to just stop this conversation right now because I'm gonna go set all of this up.

SPEAKER_00:

I love the magical references though, like the fantasy world that you've built. Yeah. 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? When you're building this thing. This is fascinating.

SPEAKER_01:

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. And uh because they're not they're they're related, but they're not record dependent on each other. Um the uh all of the stuff that I've learned with like these instructions and everything. I also learned how to interpret like the project AL guidelines.dev. All of that wisdom is brought into the MCP server that I released called BC Code Intelligence. And all of the AL guidelines are brought in. So that MCP, like I mentioned, the toolbox, that includes in it all of the topics that are on AL guidelines. And so what that MCP for BC code intelligence is for, again, open source, anyone can install it. 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. Um, the GitHub project for the BC code intelligence, there's literally a blue button that says install this into my Visual Studio Code. Um click, that's it.

SPEAKER_03:

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? What do I do and stuff? I was talking to him, and he just wrote back to me, just hit the blue button. That's what it's like the like it goes back to what he was talking about. Like the agent would do a follow, and I'm like, okay, what do I do? How do I do it? He goes, here's the link, just click the blue button, and it will do it.

SPEAKER_01:

Yeah. 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. And it does require a little bit of uh prerequisites. So for example, uh many MCP servers are actually JavaScript or TypeScript type uh little ecosystems. Um, so it does typically require that you have the node.js uh libraries installed on your machine. Uh those are usually included in the README's with people. So you if you don't have it for some reason, you can get it up and going. So the uh BC Code Intelligence MCP contains all of those experts that we were just talking about. It contains all the AL guidelines. Um, and some of the roles uh have expanded a little bit over the past couple months. 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. What's the goal of this app? 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? 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? Can you explain what the right version of that would be? So um, and there's a bunch of different prompts that are built into that, which are pre-built instructions. 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. 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. So, like for example, I want you to help me understand this app. I want you to help me upgrade this app to version 27 and fix all those number series dependencies that just started breaking. 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.

SPEAKER_03:

I'm just not saying anything because I had to fix a number series yesterday. And I had some help. Don't tell anybody. Uh so you're mentioning these MCP servers. So you hit the blue button and install. In the con in this scenario, where does that run? Because I know there's MCP servers for Learn that you can connect to. There's MCP servers for uh some other MCP servers that others have created. We're talking about these servers, MCP server. We know what it is. Where does it run when you click install?

SPEAKER_01:

Just like the wonderful world of USB-C is absolutely universal for everything, right? Uh MCPs are universal for everything, right? Um, there's two main types of MCP servers. Uh, ones that are networked and you can use them in larger projects and on ecosystems, multiple people can call it. Um, those are typically the things like the GitHub MCP or the Microsoft Docs MCP. There's actually a server running on GitHub or Microsoft site that you're calling directly, and that server ecosystem is out there. 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. Um and that's what the case with a BC code intelligence. It like many other uh MCPs, it actually starts a little node process on your machine to run the JavaScript server. 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. So it's on your local machine at the time.

SPEAKER_03:

Okay. And then is it only running when you have Visual Studio Code open or is it running all the time? Okay. So I just wanted to get clarification for those. I know that many have questions on that on when they're uh running and such. So thank you.

SPEAKER_01:

And typically a lot of times the MCP servers will only start once they're called. 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. And one of the options is list servers. 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. And that way you can also select each one and say, I want to start or stop this one. So you can be in very uh careful control of those as you want to.

SPEAKER_03:

Oh, good. So you can keep are they resource intensive? I know we talked about tokens, data, and load. Are these MCB servers? Typically not. Okay.

SPEAKER_01:

Typically, they're often just uh many of them are just reflectors. Uh for example, talking to Azure DevOps. It's uh a wrapper that's calling the uh APIs at Azure DevOps. It just is a nice way of going. 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. So many of them are very lightweight.

SPEAKER_03:

Excellent. Excellent. 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. So now let's jump into the newbimancy project. Right? It's you had me you you had mentioned it's it's similar, but related.

SPEAKER_01:

Um so uh oftentimes I uh I do a lot of presentation and training and writing around Business Central. 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. 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. Um I want to create more books. 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. I can't do that with my clients' data, I can't do that with our products. So I went, I need to be able to do this more regularly. I I speak at conferences every year. 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. And I'm kind of a nutter. I like to cross-pollinate from some of the different things that I enjoy in life. 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. Uh, I've DM'd for a long time. 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. What if I crossbreed those? What if I do something silly with those things together? 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. These retired heroes help save the world, and now they've ridden off into the sunset, but happily ever after means what? 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? And so they're trying to run their respective businesses, but you know, running a business still takes a lot of work. 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. And because this is all 100% fictional, I can do this in uh an open way. So, for example, I'm building DevOps up with only public projects for this area. So that way, if you're trying to figure out, okay, how is this guy doing pipelines in Azure DevOps? Well, all of the source files are there. You can just go in and look at them, you can see all of the flow and everything. So it it gives me a platform by which I can share more about how to do all these different things.

SPEAKER_03:

I think it's amazing. 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. And I'm like, oh, is Jeremy doing this or are all these other people doing it?

SPEAKER_01:

So it was uh You know, I'd have to look. 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. And as I'm fleshing out the story this fall for the heroes and their businesses, no man is uh an island. 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?

SPEAKER_03:

It's it's a fun, it's a fun project to follow, it's a fun site to follow. 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. I can't really call them all, I apologize, but I remember the concepts. Uh definitely a great follow. It's definitely entertaining. 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.

SPEAKER_01:

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. I've mapped out uh this past weekend, I was working on it a little bit. Uh 38 total apps are gonna be in the constellation of all the different pieces to like demonstrate all of the different parts. 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. 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. Just like uh Kentoso has, you know, the ability to install the different modules. 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? Go for it.

SPEAKER_03:

That's impressive. 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? 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. 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. I wish life was still like that back then, to be honest with you, because that was so much fun doing all those. But it's almost like you're building a whole world or a whole universe. Absolutely. Yep, how you're doing this?

SPEAKER_01:

There's you know, there is a fictional world, there's fictional countries, there's a whole bunch of stuff. 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. I've got a knowledge repo about all of the different countries and like what are the cities in each of them. So that way when we're generating the demo data, there's there's a basis to work from.

SPEAKER_03:

You know what I think would be interesting from this? 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. 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. I think that would be an interesting result if you're building it up this much.

SPEAKER_01:

We we strike there into an interesting heart of an ethical conundrum. 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. It gets a lot of pushback. So for example, I don't use AI generative tools for images. I hire graphic artists. 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. 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. 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. Yes. So there's some very big pushback.

SPEAKER_03:

Yes, I understand. No, I understand the pushback, and I understand that whole dilemma as well. Yeah. Um because it's uh it's it's it's a fine line.

SPEAKER_01:

Um it is the it's challenging to be pro-AI. I see the value, I experience the benefit. 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. There's a bunch of stuff that I'm multitasking between, and these tools are helping me do faster. Um I genuinely am getting much more done than I've ever gotten done before in the past few months. And I described it to someone as, you know how autistic folks talk about, you know, the around their friends they can unmask. They can uh they can be their true selves, they don't have to like be an interface to the rest of the world. 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. It feels like for the first time I'm going the speed that I can be at in my head. And that's a big deal.

SPEAKER_03:

No, that's I I can see it's it's it goes back to what you would just sort of talk about. 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.

SPEAKER_01:

But that and you'll see like traces of that in some of the things that I do. 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. That no, that's physically something I just made. 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. 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. 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. So if people are using it in a way to get better results more correctly, there's less wasteful use of AI. 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.

SPEAKER_03:

Yes. 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. Right? Or the negative impact or the side effects. You're talking about climate and this this side effects or impact of AI across the board. 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?

SPEAKER_01:

Because he wants to have that purity of I can always say this is something I'm not doing at all. That I'm I'm just against using it. And I agree wholeheartedly with his decision to do that. 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.

SPEAKER_00:

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. 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. So you know they they don't use it. 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. That's the only time they have to use it.

SPEAKER_01:

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. 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. And BC code intelligence as an MCP is that same sort of idea that it's it's about trying to close those gaps.

SPEAKER_03:

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.

SPEAKER_01:

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. And that includes adding more specialists. 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.

SPEAKER_03:

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. Oh that's the wicked on the rabbit hole of object naming and object numbering and affixes and namespace. We could spend all day talking about those.

SPEAKER_01:

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. Yeah that'd be awesome.

SPEAKER_03:

Then you can make a game a tabletop game with these characters. See that's what this I want something like this. 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. 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. 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?

SPEAKER_01:

Uh these days the most often place I'm I'm chatting with people tends to be LinkedIn. I am on Blue Sky so you can find me there as well um but LinkedIn has been the most active for me lately. That's where the Microsoft people hang out so I'll join them there.

SPEAKER_03:

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. 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. 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.

SPEAKER_00:

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. Again thank you everyone thank you and take care of

People on this episode

Head Shot

Kris

Host
Contributor

Brad

Co-host