1
00:00:00,874 --> 00:00:08,394
Megan Campbell is Digital Marketing Account Manager at Running Robots, a digital marketing agency based in Iowa City.

2
00:00:09,114 --> 00:00:17,154
She has embedded AI directly into daily workflows, developing systems that reduce task completion time by as much as 85%.

3
00:00:17,834 --> 00:00:24,794
Joining her is Adam Engel, owner of Running Robots, Inc., serving more than 150 organizations nationwide.

4
00:00:25,034 --> 00:00:35,274
Adam will challenge a common pitfall in AI adoption, automating broken processes, and demonstrate how to redesign operations for meaningful impact.

5
00:00:35,514 --> 00:00:37,834
Please join me in welcoming Megan and Adam.

6
00:00:43,034 --> 00:00:43,394
Awesome.

7
00:00:43,394 --> 00:00:46,674
I got to turn my mic on.

8
00:00:46,674 --> 00:00:46,874
Awesome.

9
00:00:46,954 --> 00:00:47,354
Thank you.

10
00:00:47,994 --> 00:00:56,314
Well, I'm amazed to see the standing room only, and I'm excited to dive into what we're going to showcase today because it's kind of an exciting time.

11
00:00:57,514 --> 00:01:01,834
I just wanted to start by saying we were making rocks think.

12
00:01:02,834 --> 00:01:03,114
And

13
00:01:03,834 --> 00:01:13,434
we're getting to a place where those rocks and those things that we mold into a certain shape and size are starting to transform how we think as humans and what our economy looks like.

14
00:01:13,434 --> 00:01:20,474
And it's just me being at this conference, and I know our team being at the conference here, we're learning right along with you all.

15
00:01:21,114 --> 00:01:25,074
It changes every day and just exciting time to be in the space.

16
00:01:25,074 --> 00:01:28,234
And the fact that you're here and listening is, it's

17
00:01:29,114 --> 00:01:34,114
reassuring that we're all learning at the same time, and we're all kind of ingesting what everybody else is doing.

18
00:01:34,874 --> 00:01:42,874
So with that, we'll kind of jump into the next slide here, maybe.

19
00:01:44,794 --> 00:01:45,114
There we go.

20
00:01:45,114 --> 00:01:53,874
So what we're going to go over today, there might be a little bit of an introduction, and I'm going to talk through some of the things that we're doing at Running Robots.

21
00:01:54,954 --> 00:02:01,274
But I think that the concepts that we're outlining and the things that we're talking about can be applied in any business.

22
00:02:01,274 --> 00:02:03,834
We work pretty heavily with manufacturing businesses.

23
00:02:04,314 --> 00:02:15,114
And when you're hearing our talk around, let's say, SEO or pay-per-click or website, I want you to equate those things in your mind to the departments within your own business, regardless of what that is.

24
00:02:16,394 --> 00:02:20,794
We'll go through the structure of our data, and then we'll get into a demo.

25
00:02:20,794 --> 00:02:22,234
And Megan's going to help me.

26
00:02:22,394 --> 00:02:24,154
There might be some crowd interaction.

27
00:02:24,794 --> 00:02:28,874
with some QR codes and some submissions that you guys can give us.

28
00:02:29,674 --> 00:02:33,754
If we end up using your question, you'll get a running robots mug from there.

29
00:02:33,834 --> 00:02:38,154
So try and think of the best question and we might use yours in the demo here.

30
00:02:38,154 --> 00:02:49,274
So with that being said, the framework we're going to go over today and what we're highlighting is really something that you've already technically been using if you've used the Sirius AI website.

31
00:02:50,074 --> 00:02:52,394
As Paul stated in the intro this morning,

32
00:02:53,034 --> 00:02:55,914
We came to him and said, OK, we want to build the website.

33
00:02:55,914 --> 00:02:58,314
We want to make it AI first.

34
00:02:58,434 --> 00:03:08,554
And how do we make an AI website and make it so that you all can use the AI tools that you have on your machines and be able to get the most out of the conference?

35
00:03:08,554 --> 00:03:18,794
And I think that the framework and the data that we put together on the site is a direct relationship, indirect relationship to what we're going to be going over today and how we operate as a business.

36
00:03:21,194 --> 00:03:21,594
So

37
00:03:22,554 --> 00:03:36,314
In the future, as these AI agents evolve and as they scrape the internet, as they're going out and starting to understand the context of the internet and what we've put out there, we believe your business is actually going to have two websites.

38
00:03:36,634 --> 00:03:38,634
One is the human-based website.

39
00:03:38,634 --> 00:03:39,834
You all know what that looks like.

40
00:03:39,834 --> 00:03:41,354
You all know what that feels like.

41
00:03:41,674 --> 00:03:43,434
You're seeing it with your eyes.

42
00:03:43,434 --> 00:03:45,674
You're navigating it with your mouse, and it's great.

43
00:03:45,994 --> 00:03:52,674
But the second website is a new concept for a lot of people, and we just wanted to kind of highlight what that is and why that's important.

44
00:03:53,194 --> 00:04:03,274
So the image on the right, I know you can't read the text on it, but it's basically a, let's say, an MD file or a code file, something that actually can be ingested by the agent.

45
00:04:03,674 --> 00:04:19,954
And the cleaner and more efficient that you make that file and the more that you add to those explanations for the agent, the more that you're going to actually be seen within search results or prompts within the generations of those LLMs.

46
00:04:19,954 --> 00:04:29,354
So the two website scenario is something that we want to kind of highlight here, but it does tie directly into that structured data approach.

47
00:04:32,234 --> 00:04:36,394
So as I said a minute ago, we're going to talk about marketing lingo.

48
00:04:36,394 --> 00:04:37,434
We're going to talk about SEO.

49
00:04:37,434 --> 00:04:38,794
We're going to talk about pay-per-click.

50
00:04:39,114 --> 00:04:43,994
But try and equate those things in your mind to the actual departments within your business.

51
00:04:44,314 --> 00:04:45,274
Think about shipping.

52
00:04:45,274 --> 00:04:46,154
Think about welding.

53
00:04:46,154 --> 00:04:53,034
Think about the things that you do within your business that could actually equate to customer success and customer knowledge.

54
00:04:53,554 --> 00:04:58,754
And how you communicate with your customer could actually use these same concepts going forward.

55
00:04:59,834 --> 00:05:01,834
So what's the process?

56
00:05:01,914 --> 00:05:08,114
I named the slide or the PowerPoint around the broken process.

57
00:05:08,114 --> 00:05:09,194
What's not working?

58
00:05:09,594 --> 00:05:15,914
And one of the things that we see from that is not looking at things from an AI-first perspective.

59
00:05:16,234 --> 00:05:29,194
Understanding, hey, there's an actual LLM, there's a bot, there's a thing that can help translate what it is that you do in a much more efficient way than you're probably doing today with your humans.

60
00:05:29,594 --> 00:05:42,154
And being able to relate that information down to the human, to have them understand or to, let's say, the example I like to use is actually when, we all know the person that really only responds to texts.

61
00:05:42,154 --> 00:05:43,514
Maybe they don't have an e-mail.

62
00:05:43,674 --> 00:05:48,634
Maybe they don't have, you know, an inbox that they check regularly like I do.

63
00:05:48,954 --> 00:05:53,834
So it's how do you actually put in your CRM or put into your systems

64
00:05:54,074 --> 00:06:01,834
that Johnny at XYZ company really only responds to a text message or wants to receive these updates via text.

65
00:06:02,234 --> 00:06:10,474
If you're able to, let's say, meet the customer where they're at, that's where we think the power of this framework and this system is really going to demonstrate today.

66
00:06:13,354 --> 00:06:17,994
I was going to say too that it also lives in three areas.

67
00:06:17,994 --> 00:06:29,114
So like when a vendor has information around, okay, how the product should be configured for your business, that's all in their head or all in that type of system.

68
00:06:30,154 --> 00:06:32,714
The dashboard, I'm guilty of this.

69
00:06:32,714 --> 00:06:39,594
We send out monthly reports and we look at the metrics of how people are using the dashboards that they said, hey, they want to create.

70
00:06:39,954 --> 00:06:44,914
A lot of times they're looking and they're scrolling, but they're not really ingesting that information.

71
00:06:44,914 --> 00:06:54,914
It's not really relevant to them at that significant moment where they maybe have a question about how to pivot on their business strategy with just the information from the dashboard.

72
00:06:55,954 --> 00:07:01,034
And then the AI tools, as good as they are, they still hallucinate.

73
00:07:01,354 --> 00:07:07,914
So how do we help the system or help structure the system so that the hallucinations

74
00:07:08,154 --> 00:07:10,234
are mitigated down to as little as possible.

75
00:07:10,474 --> 00:07:19,594
There will still be hallucinations, and there will still be things that are not accurate, and they are not to the point now where we're like, just ship it out the door without human oversight.

76
00:07:19,674 --> 00:07:24,034
There still has to be that human-in-the-loop scenario.

77
00:07:26,154 --> 00:07:39,514
So the three principles of how we reorganize as running robots and what we do when we look at the systems that we're using or running today is really before we automate, we start to look at every task.

78
00:07:39,554 --> 00:07:51,034
And Megan can probably attest to this firsthand and the amount of hours that we've spent into our project management system and just going through the list and saying, does this apply in the age of AI?

79
00:07:51,554 --> 00:07:53,514
Does the customer get benefit from this?

80
00:07:53,674 --> 00:08:01,274
And how do we understand what's the output of that task or of that sequence of tasks as they fit together within the system?

81
00:08:02,794 --> 00:08:12,714
The other thing is AI inside the system and using AI for what it's good for, but not just bolting it on the side and saying, oh, by the way, we're AI first because we put a chatbot on our website.

82
00:08:12,954 --> 00:08:17,274
That's a different scenario and that's a different way of operating with these new tools.

83
00:08:18,714 --> 00:08:20,954
The memory aspect, the third principle.

84
00:08:21,354 --> 00:08:26,954
is that without that additional context of what happened last month, this month doesn't really mean much.

85
00:08:27,194 --> 00:08:42,354
So by actually having a log or a system that can actually go through version control of what you've changed and how things look, that system doesn't really have as much value if it doesn't have context of where it's coming from and potentially going to.

86
00:08:42,354 --> 00:08:47,594
And so that memory layer, we're playing around with a solution called MemPalace.

87
00:08:47,594 --> 00:08:49,994
I don't know, has anybody in the room heard of MemPalace?

88
00:08:50,634 --> 00:08:52,074
Okay, I got a couple of geeks in the room.

89
00:08:52,074 --> 00:09:17,834
Cool, But the idea there is that the actual information that's stored within a palace and a room or a hallway is really adding that structure to the data and being able to understand, okay, what happened last month and what happened this month are different pieces of data, but comparing them in a particular way allows that data to be ingested and used by the LLM much more effectively.

90
00:09:19,154 --> 00:09:20,914
All right, so here's where we get into the good stuff.

91
00:09:20,914 --> 00:09:23,634
And this is where I had a little fun with this presentation.

92
00:09:23,634 --> 00:09:35,794
And today we're actually kind of announcing or releasing our version or our remade architecture as a business and how we're actually telling the world of how we're going to interact with our clients.

93
00:09:35,794 --> 00:09:37,914
So our clients haven't seen this.

94
00:09:38,714 --> 00:09:43,034
but we're really actually starting to roll this out here in the next month or two.

95
00:09:43,514 --> 00:09:52,394
So every client and every business, every person that we interact with as a business is actually going to get a robot or an avatar.

96
00:09:52,754 --> 00:10:00,714
And within that avatar, and why that's important, is that we're actually assigning properties and attributes to the things that they're doing with our business,

97
00:10:01,034 --> 00:10:06,154
but also in how they interact with our business and where they're at in their own marketing knowledge.

98
00:10:06,314 --> 00:10:18,234
So we're meeting the customer where they're at and understanding that, okay, maybe Johnny with just a cell phone and not an inbox is going to prefer that text and that information would be stored within their avatar.

99
00:10:21,114 --> 00:10:24,114
So let's look at the pieces of what we've built.

100
00:10:24,114 --> 00:10:29,634
Again, translate this to your business, because I know you're probably not, you know, let's say going through the

101
00:10:30,234 --> 00:10:37,354
the automation integration or content creation pieces, but translate that into something that relies on your business.

102
00:10:37,754 --> 00:10:44,074
But for us, we've assigned different body parts of the robot to the different service departments that we operate.

103
00:10:44,314 --> 00:10:45,514
And why do we do that?

104
00:10:45,514 --> 00:10:46,274
Why is that important?

105
00:10:46,354 --> 00:11:16,274
or how does that actually relate? Well, it makes sense when you see this type of robot. And yes, there can be a one-leg, one-armed robot because it's instantly visual and we instantly see, okay, maybe this robot isn't running as fast as what it could be with these other legs or arms of the service. So by having that visual and having that understanding from a human perspective, we can instantly see, okay, there's things that might need to be tweaked or updated within that client's profile

106
00:11:16,554 --> 00:11:43,434
to give that robot a full avatar. This is where the, I guess, the fun comes in. So one of the things that we struggle with as a business is that when we come into a client meeting on a monthly basis, there's a lot of, let's say, what did we talk about last month? Or how did we, what did we actually go over? Or what's the next step? What are the different areas of our business that we can improve? And

107
00:11:43,754 --> 00:12:10,474
There's a way in which we can architect that, but I thought, why not make it look like a monopoly board and have the monopoly board actually represent the different parts of our business? And that actually helps our customers understand where they're at and how those different services relate together. And then when they're actually interacting with the business or coming to their dashboard, they can see this and click into each one of these boxes. So we've got

108
00:12:11,354 --> 00:12:36,074
the four different departments or the four different areas. One thing I would call out is this master data download. And what that does, it's kind of like what's on the Cirrus website that we've introduced here, is that you can really get all of the structured data from the different departments into your LLM by just going to that download. But what happens when you click, let's say, into one of those boxes?

109
00:12:37,034 --> 00:13:04,554
It actually allows us to focus that information and get a little bit more granular in the operation and what they're actually doing with that data. So you can get the overall, let's say, full marketing context, if you click download data on the monopoly board. But the individualized data per department actually allows us to say, okay, I'm going to ask a specific question around, and this is AI visibility, so I've basically clicked into that little box,

110
00:13:05,194 --> 00:13:32,314
But from there, you can see the two scores. And what are those two scores? One is the knowledge score of the customer. So in our meetings with our customers, we're recording them. We're understanding what words, acronyms, things that they're using. And by doing that, we can assign them a score to meet them at their level. So if somebody comes in and starts talking about ROAS and cost per click, and they're getting down into the nitty-gritty of marketing terms,

111
00:13:33,074 --> 00:13:58,874
By doing, assigning the score, we can actually meet them to where they are. If they're just saying, hey, I don't really know this pay-per-click thing, help me explain how Google Ads works and all of that, we can meet them, their score might get a little lower, but at that time, it'll actually help them understand the concepts and bring their score up over time. So it helps our team and the bots understand where that customer is when we're delivering the message.

112
00:14:02,954 --> 00:14:32,154
One thing with this slide as well is that we have an ability to, let's say, chat against the data and use our bots. So we're using our system prompts and our information, which I think is useful, but it's not necessarily an AI first when it's not the customer's information. I feel like getting the information into the customer's system on their desktop, laptop, whatever it is, and allowing their bots, the ones that are trained to communicate to them,

113
00:14:33,154 --> 00:14:54,074
as where the value is added, if that makes sense. So the scores, and I just went over this a little bit, but I want to go a little bit deeper. And the terminology and things that we do within the score can increase over time and help that robot go from that small little robot that you saw in the beginning

114
00:14:54,474 --> 00:15:18,794
to a bigger robot in the end. So by the size of the robot, we're actually determining the score. And that's another visual cue for our team to understand where that person or business is in their marketing journey. So what we're covering here, what the framework is that I'm outlining here, is really from avatar of meeting the person, understanding who they are,

115
00:15:19,434 --> 00:15:43,914
getting into the game board and explaining, okay, here is how we operate. Here is the process that we go through on a monthly basis. And then we're actually looking at the individual departments. So clicking into one of those squares, seeing the data that's there, and understanding that the information that's presented there is not necessarily created just by AI. It's not just a box and data filled with an AI.

116
00:15:45,114 --> 00:16:06,314
output, it's actually our team's input that created that dashboard. So each department head of our business is actually critiquing and understanding the flow for that customer and getting information. And I'm going to go through that here in a second, but it's essentially not using AI up until the point where it actually gets the information from that system.

117
00:16:08,794 --> 00:16:27,114
I didn't show the Plinko board. The Plinko board is still a concept in play, but I wanted to address it in that the game of Plinko or the Plinko operation is, you know, you drop a ball or a token into the top and it hits a bunch of different pegs on the way down, and then it ends up in a certain area.

118
00:16:27,514 --> 00:16:51,834
And by visualizing in that way and saying, okay, a customer came in from pay-per-click, they dropped the token in and they hit the homepage, they hit the product page, they've hit the product category page, then they hit the contact or the checkout. And by visualizing those things as we're going through the data and having that visualization through the marketing process, it helps the end user

119
00:16:52,794 --> 00:17:13,914
understand where those leads came from, where those pieces of information are being used. And just again, adding that visualization that the customer can then say, oh, okay, aha, I see where that information is coming from and how this data was put together by the robot team. So what you take home. So

120
00:17:14,474 --> 00:17:38,394
One of the things that we're doing here, and so if you can see on the right-hand side, we've got a GA4 export, a Search Console CSV, a Screaming Frog Excel spreadsheet. These are all pieces of data that we're capturing from different services. And so our team has worked together to restructure how we operate. And I don't know if anyone was in the room,

121
00:17:38,714 --> 00:18:03,994
The last year when I gave a presentation, I was all about N8N and how we connected Google Ads to your CRM, to your ERP, and then pulled all that information down to make a really cool report. We're still all in on that piece of software, but that's not really the key takeaway here. It's basically that AI is great for ingesting and understanding data, but we don't want to introduce hallucinations.

122
00:18:04,554 --> 00:18:25,674
into the ingestion of information. So we're still using tools to go out and grab that information from Google Analytics, from Google Ads, from screaming fraud. We're scraping raw data so that we have an understanding of where that information is, and we know that it's not hallucinated against. So there's a place and time to use AI.

123
00:18:26,074 --> 00:18:51,274
But then there's a place and time to use AI to actually just get the information directly from an API call or directly from a dashboard or a system that's not using hallucination type devices. And that's really leading into the trust by design. So by doing this, and I'll go through this real quick, the clean APIs, and I just listed those different pieces or those different tools,

124
00:18:52,954 --> 00:19:21,994
The AI's job is small in that regard. It adds a small bit of context to say, hey, here's what I saw in the data, maybe in comparison to last month, but it's not actually manipulating that information in any way. So it's kind of a separation layer or a way to actually say that we trust the information that we're putting within these files because we know AI hasn't touched it yet. There's a summary, but there's not actually manipulation or getting that information directly from an LLM.

125
00:19:24,314 --> 00:19:49,914
The other thing here is 1 file per department. So when we first started doing this, I was in a talk last year, and the person giving the talk, I won't say the name, but they basically said, hey, I took all of my information and just shoved it into the system. I took our HR manual, I took our SOP, I took all of our stuff and just put it in there and I started asking the question. It was great. Well, if you do that, the context window is muddy.

126
00:19:50,394 --> 00:20:12,394
It gets really inaccurate, and the AI doesn't really know where to look or what to look at. So we've spent a lot of time as a business trying to understand that context window and how to organize the marketing data within that context window so we get the best answers out of those things. And so by creating the basically MD or markdown file,

127
00:20:13,594 --> 00:20:41,594
per department, we're then able to structure that data or point to the information, and the device or the LLM can then articulate or say, aha, here's a good summary of what's there, but not so much that it's just overwhelmed with information and it starts hallucinating. Does that make sense? So what happens through this process, or what are we going to see in the demo, and how do we actually understand what's happening? It's one,

128
00:20:41,914 --> 00:21:09,754
pulling the information from a system, as I just mentioned, one of those many logos on the last slide, we're generating a short summary. A person from our team, once a month or once a week, will be reviewing that information. So that lives on GitHub. We pull that information over, and the person or department head at Running Robots looks at each client's file. Maybe they're just looking at, maybe they're the pay-per-click specialist and they're just looking at pay-per-click data.

129
00:21:10,274 --> 00:21:31,594
They're opening up that file, they're reviewing the summary, they're reviewing the information, and verifying as a human, hey, this is actually accurate, or there's something wrong here, maybe we need to tweak how this works, or something that needs to pivot within the account to make an optimization. So there is human oversight and review in that workflow.

130
00:21:32,154 --> 00:21:46,274
Once we actually say, okay, yes, that information looks good, we like the output, we like the data, we'll do a commit. And that's just basically a geek's term for basically pushing something to GitHub to say, I commit this to a public.

131
00:21:46,474 --> 00:21:52,154
or private repo to say, here is the information and how we're going to share that to a client.

132
00:21:52,154 --> 00:21:55,114
So once we hit commit, that information becomes live.

133
00:21:55,394 --> 00:22:06,074
And what I think is the power there or the reason why we're actually pivoting towards GitHub instead of a monthly e-mail with a PDF attached is that's instant.

134
00:22:06,474 --> 00:22:14,634
So as soon as that person hits commit, as soon as one member of our team says, okay, this file looks good, that information is then

135
00:22:14,954 --> 00:22:16,474
live for that customer.

136
00:22:16,474 --> 00:22:20,914
They can go and prompt against that repo and say, what's new?

137
00:22:20,914 --> 00:22:21,994
What's happening?

138
00:22:22,194 --> 00:22:27,594
And it just really depends upon the cycle of time that customer wants to review that information.

139
00:22:27,594 --> 00:22:28,234
So if we're...

140
00:22:28,714 --> 00:22:30,954
let's say every day reviewing that client.

141
00:22:31,114 --> 00:22:35,194
Maybe it's a new product launch and we want to look at that data every day.

142
00:22:35,434 --> 00:22:40,634
There can be a commit or a cycle that couldn't be available prior to using these tools.

143
00:22:40,834 --> 00:22:47,434
And so our speed in which we deliver information to a client and the speed in which they ingest it has drastically increased.

144
00:22:47,434 --> 00:22:54,554
And the ability for us to really help them make business decisions, even a day or two after a product launch, makes total sense.

145
00:22:54,754 --> 00:22:57,194
And it really speeds up the ingestion or the

146
00:22:57,554 --> 00:22:59,914
let's say, usefulness of that information.

147
00:23:01,114 --> 00:23:04,714
The sharing part is really just saying, hey, this information's out there.

148
00:23:05,074 --> 00:23:10,874
And by allowing others within your organization, maybe it's not just the marketing director that gets this.

149
00:23:10,874 --> 00:23:12,074
Maybe it's the CEO.

150
00:23:12,154 --> 00:23:17,194
Maybe it's the product specialist that can all have access to these files.

151
00:23:17,354 --> 00:23:21,674
They can ask different questions and have different avatars around that same data.

152
00:23:21,994 --> 00:23:27,354
So if your CEO might not, you might think he knows a lot about the way

153
00:23:27,554 --> 00:23:41,114
marketing works, but the chief marketing officer really realizes that maybe he doesn't know what he's talking about, we can tailor the responses or tailor the avatar of that response per business role and per customer.

154
00:23:41,354 --> 00:23:48,794
So that really helps in how we're actually ingesting that and how the, let's say, CEO perceives the data versus the marketing director.

155
00:23:51,434 --> 00:23:51,754
So

156
00:23:52,674 --> 00:23:58,714
Growing the knowledge base and why do we use GitHub or what is in this GitHub thing that you keep talking about, Adam?

157
00:23:58,954 --> 00:24:02,874
Well, the information is organized in a very simple way.

158
00:24:03,034 --> 00:24:07,914
Who in here has actually used or know what I mean when I say MD file or Markdown file?

159
00:24:09,034 --> 00:24:10,314
Okay, we got a couple.

160
00:24:10,554 --> 00:24:11,994
We got geeks in progress here.

161
00:24:12,074 --> 00:24:15,354
So we've got a couple of geeks in the back, but we're learning Markdown.

162
00:24:15,714 --> 00:24:20,474
And if you think of Markdown, if you look at it that way, it's really a fancy text file.

163
00:24:20,994 --> 00:24:22,314
Honestly, that's all it is.

164
00:24:22,474 --> 00:24:30,794
It's a text file that just has certain ways of formatting information that make it easy for LLMs and bots to understand.

165
00:24:31,154 --> 00:24:39,274
And so what we're doing as a business is taking that information, making it a markdown file, and putting it in the structure that you see here.

166
00:24:39,594 --> 00:24:49,994
So as a repository goes, and we'll kind of open that up here in a second, but we'll actually let you guys see the public repository, see our

167
00:24:50,714 --> 00:24:56,154
new structure and actually prompt against it with a demo client that you guys will see here in a second.

168
00:24:56,154 --> 00:25:05,034
So if you want to see the repo and what we've put together or how we structure that data, please just scan the QR code.

169
00:25:05,034 --> 00:25:10,714
This will take you right to the public repo and we'll be actually asking questions against it in our demo.

170
00:25:11,114 --> 00:25:13,634
So you'll kind of understand who that is.

171
00:25:15,674 --> 00:25:16,874
Everybody got the QR code?

172
00:25:16,874 --> 00:25:17,994
I see the phones are still out.

173
00:25:17,994 --> 00:25:19,514
So I'll just hold on here for a second.

174
00:25:26,874 --> 00:25:27,274
All right.

175
00:25:29,114 --> 00:25:31,794
So next, what are we going to do?

176
00:25:31,794 --> 00:25:32,834
What's the demo?

177
00:25:32,834 --> 00:25:34,954
What is the special sauce?

178
00:25:34,954 --> 00:25:38,514
How are we going to demo this live?

179
00:25:38,874 --> 00:25:43,434
And what we're going to do, we used fictional data.

180
00:25:43,794 --> 00:25:44,954
And let me back up here.

181
00:25:45,274 --> 00:25:50,554
So I started by asking a client if I could use their data in this presentation.

182
00:25:51,274 --> 00:25:54,074
And I started basically saying, okay, we'll take the data.

183
00:25:54,394 --> 00:25:58,594
I built the repo and I said, okay, tell me about this client.

184
00:25:58,594 --> 00:26:00,074
And I asked it a couple questions.

185
00:26:00,074 --> 00:26:03,914
And after the first two questions, I was like, I can't use the data.

186
00:26:04,314 --> 00:26:11,354
I can't put this information up on the screen and ask customers to ask questions about a live customer because it was too good.

187
00:26:11,594 --> 00:26:19,794
It was actually beyond the place where I was like, okay, if there's a competitor in the market, it's just going to be an instant, okay, here's what they're doing as a business.

188
00:26:19,794 --> 00:26:20,074
So

189
00:26:20,954 --> 00:26:28,874
We did make up a client, but we used the structured data around that client to actually articulate what's in here.

190
00:26:28,874 --> 00:26:40,354
So the information that you're seeing and the data in the responses is accurate as far as how a typical business information suite would be ingested into this framework.

191
00:26:41,834 --> 00:26:45,194
So, and actually let me back up real quick here.

192
00:26:45,434 --> 00:26:49,834
It's Prairie Ridge Manufacturing doesn't exist, made the logo with ChatGPT.

193
00:26:50,634 --> 00:26:53,434
but we did give it a name.

194
00:26:53,434 --> 00:26:58,234
So it's Manufacturer is the made-up person.

195
00:26:58,314 --> 00:27:04,794
So Manny is the president of Prairie Ridge Manufacturing, and he is a relatively

196
00:27:06,634 --> 00:27:11,874
let's say, not advanced, but he is, let's say, not a beginner in the world of digital marketing.

197
00:27:11,874 --> 00:27:18,034
So he's one of those that would come in and say, you know, what is the ROAS of the pay-per-click campaign?

198
00:27:18,034 --> 00:27:20,434
What is happening within the marketing of my business?

199
00:27:20,434 --> 00:27:26,234
And they're not necessarily a newbie when it comes to talking lingo or marketing speak.

200
00:27:26,474 --> 00:27:33,914
But we'll kind of show you a little bit of a demo around how the information changes between Manny and

201
00:27:35,234 --> 00:27:36,234
And what was the other name?

202
00:27:36,594 --> 00:27:36,954
Algorhythm.

203
00:27:38,634 --> 00:27:44,074
Algorhythm is the, we'll see what Al's response is here.

204
00:27:44,794 --> 00:27:49,994
But one of the things that we want to do first is, so I'm going to go to the next slide here, and I might go back and forth.

205
00:27:50,474 --> 00:27:59,274
But if you can think of questions that you might want to ask Manny's bot, so if you put yourself in Manny's shoes,

206
00:27:59,674 --> 00:28:03,354
You can scan this QR code and e-mail Megan questions.

207
00:28:03,514 --> 00:28:15,114
So if you scan that, it'll pull up your e-mail, and then you can just type in a question, hit send, and then Megan will be sitting here watching the inbox, and she'll feed me links while she's prompting.

208
00:28:15,114 --> 00:28:18,194
And we'll be able to see some of the Claude responses.

209
00:28:18,194 --> 00:28:21,994
So if we pick your question, you win a mug.

210
00:28:21,994 --> 00:28:28,794
So please type away and let us know if there's any questions that you would like to ask against this repo.

211
00:28:30,394 --> 00:28:47,194
So let me actually back up here real quick, is that one of the things that we're demoing here is that the information on the GitHub repo and how we actually operate the business internally would be a two-way St.

212
00:28:47,674 --> 00:28:55,834
So while you're typing these questions, I just wanted to say that when you're asking your bot questions, let's say that you're asking, hey, how does this

213
00:28:57,354 --> 00:28:58,514
how did we do last month?

214
00:28:58,554 --> 00:29:00,954
Or how did this product launch go?

215
00:29:01,354 --> 00:29:16,394
If the answer comes back, and let's say it's not producing the information you would like, you can ask your bot, hey, since you have rights to this repo, please ask the robots to add data around this topic.

216
00:29:16,594 --> 00:29:19,514
And maybe the answer wasn't what you would anticipate getting back.

217
00:29:20,074 --> 00:29:38,554
If you're asking your bot to say, hey, ask running robots a question, it's feeding information back up into the GitHub repo that will allow our bots to ingest that information and say, hey, Manny asked a question that really didn't get answered very well, or maybe we didn't have data around that information.

218
00:29:39,194 --> 00:29:44,874
next month or next week, we would add information or work with Manny to get access.

219
00:29:44,874 --> 00:29:50,474
Maybe it's about their ERP or other things within their business that maybe we don't have access to within the repo.

220
00:29:50,954 --> 00:29:59,154
By asking that type of question and saying, hey, here's what I wanted to see, here's what I didn't see, we're able to get that feedback, complete that loop,

221
00:29:59,594 --> 00:30:05,434
add the data, and then next report, or next time that question is asked, that repos isn't updated.

222
00:30:05,674 --> 00:30:15,514
So it's a very fast, continuous feedback loop for how you're interacting with the business and how the business ingests the data to make educated discussions.

223
00:30:15,914 --> 00:30:21,354
So with that being said, we do have live questions coming in.

224
00:30:21,674 --> 00:30:24,794
So we've got our first one that's currently running, but if you want to...

225
00:30:24,874 --> 00:30:26,354
Okay, yeah, I'll go ahead and

226
00:30:27,154 --> 00:30:28,754
I'll share an example real quick here.

227
00:30:28,754 --> 00:30:32,114
And on the bottom of this, it's may the prompting gods be with us.

228
00:30:32,114 --> 00:30:35,674
So whatever comes out of this, we'll see here.

229
00:30:35,674 --> 00:30:38,234
So let me just change the display here.

230
00:30:44,244 --> 00:30:48,884
So I'm going to mirror what I've got on my screen.

231
00:30:51,284 --> 00:30:51,684
Okay.

232
00:30:52,724 --> 00:30:55,604
So this is a predefined example.

233
00:30:55,684 --> 00:30:56,884
We can kind of

234
00:30:57,274 --> 00:31:00,874
asked these questions to start while we're getting questions from customers.

235
00:31:01,594 --> 00:31:12,074
But essentially what we've got here is a, please answer the question using the following data with just a straight link to the GitHub repo.

236
00:31:12,314 --> 00:31:14,234
And then how did we do last month?

237
00:31:14,234 --> 00:31:15,354
That's all they typed in.

238
00:31:15,834 --> 00:31:16,314
That's it.

239
00:31:16,634 --> 00:31:23,114
But with that, the bot is actually understanding the context because it knows, hey, Manny is asking the question.

240
00:31:23,354 --> 00:31:26,474
Manny is an advanced marketing data user.

241
00:31:26,794 --> 00:31:28,954
And we got this information back.

242
00:31:29,194 --> 00:31:35,914
So we're basically looking at the headline matrix of the number of sessions, the RFQs.

243
00:31:36,874 --> 00:31:40,234
We can really kind of go down, and I can go deep into the data here.

244
00:31:40,874 --> 00:31:49,634
But essentially, what we're getting is a top-to-bottom understanding from, let's say, Manny's bot's perspective, how they did last month.

245
00:31:49,634 --> 00:31:54,394
What are the things that maybe they asked in the previous months that caused this data to come up?

246
00:31:54,714 --> 00:31:57,834
So it's an ever-evolving way of communication.

247
00:31:58,634 --> 00:32:04,474
So let's look at, so this is the advanced marketing background bot.

248
00:32:04,794 --> 00:32:10,634
But let's look at the, maybe the CEO that thinks they know marketing, but they really don't.

249
00:32:11,594 --> 00:32:14,234
The, let me see here.

250
00:32:15,194 --> 00:32:18,794
So this would be the algorithm.

251
00:32:20,034 --> 00:32:22,874
And so we're getting some data here.

252
00:32:22,874 --> 00:32:29,354
So it's maybe a little bit more streamlined as far as how it's articulating the information.

253
00:32:29,674 --> 00:32:34,634
But if we look at the top line snapshot between the two, so if I just go kind of, I'm going to go back and forth here.

254
00:32:35,114 --> 00:32:45,834
You know, we've got a lot of acronym soup on the advanced side, where if we switch over to the pay-per-click,

255
00:32:46,354 --> 00:32:51,754
It's again, bringing that information down to the level of where that makes sense for that person.

256
00:32:52,554 --> 00:32:55,914
You guys see the difference in how those responses work?

257
00:32:56,154 --> 00:32:59,994
Same data, just different profile, different person, different response.

258
00:33:01,314 --> 00:33:01,474
Okay.

259
00:33:01,514 --> 00:33:04,314
Let me pull up...

260
00:33:05,074 --> 00:33:11,394
I sent your first 5-1, which is from...

261
00:33:11,954 --> 00:33:17,194
So which channels saw the biggest increases slash decreases month over month and why?

262
00:33:18,154 --> 00:33:28,034
So direct fetching, before I dig in, got context, Prairie Ridge manufacturing, demo client, channel data lives and websites.

263
00:33:28,034 --> 00:33:29,034
Let me check there.

264
00:33:29,514 --> 00:33:31,194
April is the most recent.

265
00:33:31,314 --> 00:33:34,234
I'll pull April plus March, month over month comparison.

266
00:33:34,554 --> 00:33:40,634
So let me open up the MD file here, and we can just take a look at what we got back for that question.

267
00:33:41,114 --> 00:33:45,754
So Prairie Ridge Manufacturing, month over month, April versus March source.

268
00:33:46,594 --> 00:33:52,554
And so we can see here, the biggest gainer was organic search with a 24% increase.

269
00:33:52,954 --> 00:34:02,994
So I don't know who asked that question, but you could see how that simple, let's say, month over month change was highlighted instantly within the results.

270
00:34:02,994 --> 00:34:05,634
And it's, let's say, articulating that answer really well.

271
00:34:05,634 --> 00:34:08,834
We're working on the second one here.

272
00:34:08,834 --> 00:34:09,554
Working on the second one.

273
00:34:09,554 --> 00:34:09,674
OK.

274
00:34:10,194 --> 00:34:11,834
Let me go into one of these other ones here.

275
00:34:11,834 --> 00:34:17,914
So the, which pay-per-click campaign is wasting the most money.

276
00:34:18,154 --> 00:34:30,554
So this is again into the Manny side of the scenario, but this is highlighting, okay, going into that specific MD file around pay-per-click marketing.

277
00:34:30,794 --> 00:34:32,234
And so it's not necessarily

278
00:34:32,954 --> 00:34:43,994
scanning or let's say looking at the other areas of the repo, because of the way we've designed it, it's specifically looking at the pay-per-click marketing MD file and what's contained within that.

279
00:34:45,114 --> 00:34:52,474
So the response, PPC waste analysis, verdict competitor, tier one fabrication was wasting the most money.

280
00:34:53,514 --> 00:34:58,634
So we've got spend, clicks, leads, CVR, and Cpl.

281
00:34:58,634 --> 00:35:00,714
So it's worst offender,

282
00:35:01,594 --> 00:35:04,954
The account average, 24, let's see here.

283
00:35:07,514 --> 00:35:11,194
So A 5.2% bounce rate on landing page rate.

284
00:35:11,194 --> 00:35:20,594
So you guys can really understand or start to see the granularity that you can get into on a particular department or as broad as how did we do last month.

285
00:35:20,634 --> 00:35:25,194
That's a very different response or a different approach.

286
00:35:25,874 --> 00:35:26,114
Okay.

287
00:35:26,114 --> 00:35:27,914
We've got 10 minutes left.

288
00:35:27,994 --> 00:35:28,314
Got it.

289
00:35:30,074 --> 00:35:30,354
Okay.

290
00:35:31,274 --> 00:35:31,994
We have another one.

291
00:35:32,554 --> 00:35:33,514
I just sent you one more.

292
00:35:33,514 --> 00:35:34,234
Just sent one more.

293
00:35:34,314 --> 00:35:34,514
Okay.

294
00:35:34,514 --> 00:35:37,034
See if I can whip one more up here.

295
00:35:42,914 --> 00:35:43,754
Let's go with that one.

296
00:35:45,594 --> 00:35:46,154
Okay.

297
00:35:46,874 --> 00:35:53,554
How do we standardize our components with our custom engineering engineered customer orders?

298
00:35:53,554 --> 00:35:54,274
This is a good one.

299
00:35:54,274 --> 00:35:54,714
I like this.

300
00:35:54,714 --> 00:35:55,434
Who did this one?

301
00:35:56,514 --> 00:35:56,674
Okay.

302
00:35:57,754 --> 00:35:58,314
Awesome.

303
00:35:58,554 --> 00:35:59,194
That's a very...

304
00:36:00,154 --> 00:36:07,434
We get this question a lot, and we have a lot of customers that are very, let's say, customized in how they're delivering product.

305
00:36:07,914 --> 00:36:15,834
And one of the things that we struggle with from an e-commerce perspective is, okay, if you customize every order, your SKU numbers are infinite.

306
00:36:16,314 --> 00:36:25,274
And the ability for a bot to understand your information and how you operate as a business, adding that context into marketing,

307
00:36:25,554 --> 00:36:27,514
and adding that context from your ERP.

308
00:36:27,674 --> 00:36:36,794
So like in our previous talk last year, I was talking about, okay, connect your CRM to your ERP to your website and have that information flow effectively.

309
00:36:37,274 --> 00:36:46,794
And for somebody like yourself that has, let's say, customized parts across the board, it becomes difficult for that information to fit within a bot context window.

310
00:36:47,194 --> 00:36:56,234
And you get a lot of hallucinations when you get over a large number of product or how to, let's say, this component fits with this component fits with that component.

311
00:36:56,714 --> 00:37:03,354
And by segmenting the information, understanding how the maybe components are fit together.

312
00:37:03,354 --> 00:37:09,914
So in this case, we would potentially build out the repo so that maybe we had attributes of those products.

313
00:37:09,914 --> 00:37:12,634
Instead of trying to list every SKU known to man,

314
00:37:13,034 --> 00:37:17,754
It would be, okay, these are the different parts of their manufacturing process.

315
00:37:17,754 --> 00:37:19,514
Here's how their business works.

316
00:37:19,914 --> 00:37:26,314
And we can specialize the responses or specialize the marketing approach based on those different attributes.

317
00:37:26,314 --> 00:37:32,554
So it's not always just, here's my product list, ingest the product list, here's my marketing data, how did we do?

318
00:37:32,874 --> 00:37:40,394
It's really, how does this specific instance for this business equate to a LLM's context window?

319
00:37:41,274 --> 00:37:43,114
So I'm interested to see what comes back here.

320
00:37:43,114 --> 00:37:47,994
So let me pull up the MD file here.

321
00:37:52,634 --> 00:37:53,434
So this is a good one.

322
00:37:53,434 --> 00:37:57,514
So right now we do not have a documented component standardization program repo.

323
00:37:57,754 --> 00:38:05,714
So it's actually calling out, and this is one of the things that we put within the repo, that we help the bot not hallucinate.

324
00:38:06,034 --> 00:38:10,114
I'm not saying that we've solved it, like, okay, we've made it so that bots don't hallucinate.

325
00:38:10,114 --> 00:38:10,874
They still will.

326
00:38:11,314 --> 00:38:13,274
And we have to cross-check this information.

327
00:38:13,354 --> 00:38:22,394
But one of the things that we try and do in this structured data is state that if the information isn't within the repo, don't answer the question.

328
00:38:22,674 --> 00:38:30,154
Don't try and philosophize on how they could do it or pull numbers out of thin air, which they do.

329
00:38:30,394 --> 00:38:37,674
But we're trying to steer them in a direction that says, the customer asked a question that didn't exist within the repo,

330
00:38:38,794 --> 00:38:45,354
Would you like me to flag that to go back to running robots to say, hey, maybe we're incomplete on our ERP data.

331
00:38:45,594 --> 00:38:49,674
Let's pull that in for the next month's report or the next repo commit.

332
00:38:50,114 --> 00:38:57,514
And then we can ask that same question again and see how those responses compare and see if we're asking the right questions.

333
00:38:58,954 --> 00:38:59,074
Okay.

334
00:38:59,274 --> 00:39:06,394
Before we go to the next one, does anybody have any questions that they would like to ask to us instead of just our bots or other things?

335
00:39:09,034 --> 00:39:09,274
No?

336
00:39:10,034 --> 00:39:10,194
Okay.

337
00:39:10,394 --> 00:39:10,874
Yeah, go ahead.

338
00:39:11,994 --> 00:39:19,074
I teach engineering instruction for like a couple of years at Des Moines Area Community College before they transfer to Iowa State.

339
00:39:19,074 --> 00:39:27,314
And so I'm here to kind of figure out how to help my students be prepared for the workforce where AI is going to be prevalent.

340
00:39:28,914 --> 00:39:39,514
from an engineering perspective, which tasks are they going to be able to perform that are kind of AI agent ready and which ones need the most human oversight at this point in time?

341
00:39:40,794 --> 00:39:41,914
That's a really good question.

342
00:39:42,394 --> 00:39:52,874
I think that the best way that I've found to prepare someone for using AI is to use AI.

343
00:39:53,274 --> 00:39:56,234
It's a very simple answer to that question, but

344
00:39:56,874 --> 00:40:00,314
in your interactions with the information.

345
00:40:00,394 --> 00:40:12,474
So one, giving it and knowing what structured data looks like, and to understand what context you're giving the bot is, let's say, one aspect of that.

346
00:40:12,874 --> 00:40:21,514
But then asking it the different questions or different phrases of that question, even just changing little bits and pieces

347
00:40:22,034 --> 00:40:30,394
of that question, you start to learn how to communicate to that thing or to that entity to get the output that you desire.

348
00:40:30,394 --> 00:40:37,674
So using AI, the only way to get better at it, in my opinion, is to use AI and continue to ask questions.

349
00:40:38,314 --> 00:40:48,154
The cool part about it is what we're doing here is that I don't feel dumb when I'm asking my bot to explain something to me that I don't know, whereas I would a human.

350
00:40:48,394 --> 00:40:54,154
So the barrier to feeling stupid has been dropped by using these things.

351
00:40:55,674 --> 00:40:59,034
As I was preparing for this presentation, I just have to share one quick story.

352
00:41:01,234 --> 00:41:03,954
pouring a new concrete pad on our inner front yard.

353
00:41:03,954 --> 00:41:08,674
And I couldn't really spend all the time I wanted to prepare for the presentation this weekend.

354
00:41:09,034 --> 00:41:14,794
So I put my headphones on and just started asking my bot about my presentation.

355
00:41:14,794 --> 00:41:20,394
My neighbors thought I was crazy just talking, like going through my presentation in my head and carrying cement bags.

356
00:41:20,714 --> 00:41:31,034
But that use and that use case of basically just putting your headphones in, turning on Claude, saying, here's my presentation, help me walk through it, that use case

357
00:41:31,314 --> 00:41:41,994
of learning with AI and just stepping through the process is, I think, the best way to learn and how these, let's say, articulate or how they work together with us.

358
00:41:43,514 --> 00:41:43,674
Yeah.

359
00:41:44,394 --> 00:41:44,954
I got one.

360
00:41:44,954 --> 00:41:50,634
So you talked about storing a lot of vendor knowledge, you know, all your client knowledge and all that kind of stuff.

361
00:41:51,114 --> 00:41:55,074
There was a comment earlier in the opening about tribal knowledge.

362
00:41:55,914 --> 00:42:02,554
How do you, have you found a good way of going through and getting stuff that's not already on a piece of paper that lives in people's heads?

363
00:42:03,514 --> 00:42:05,834
That's a, again, another really good question.

364
00:42:06,714 --> 00:42:20,154
What I would say there is, as an organization, one of the things that we do internally is every Friday, we're meeting as a team and going through the use cases of how we're using AI.

365
00:42:20,714 --> 00:42:23,994
And one of the things that we're stressing in those

366
00:42:24,314 --> 00:42:33,354
group sessions or those work sessions is looking at your daily output and saying, okay, what is it that you've done in the last week?

367
00:42:33,394 --> 00:42:34,714
What are the things that you're doing?

368
00:42:34,714 --> 00:42:36,154
What are the projects you're working on?

369
00:42:36,634 --> 00:42:41,354
And asking our bots to help us understand what commits they've made.

370
00:42:41,594 --> 00:42:49,514
So by, and I sound like a GitHub salesman up here, I apologize, but by using GitHub and allowing us to basically say,

371
00:42:49,994 --> 00:43:03,034
Tiffany made 25 commits last week, and she worked on these seven projects by understanding how they're communicating with the bot or they're communicating with our customers and having that information within a repo.

372
00:43:03,434 --> 00:43:16,314
As an organization, we're starting to look deeper into those individual roles and get that context maybe out of our brains and into a written form that we can ingest and see the trend over time.

373
00:43:16,314 --> 00:43:16,634
So

374
00:43:17,354 --> 00:43:21,754
To answer your question shortly, GitHub has helped us see that version control.

375
00:43:22,074 --> 00:43:35,434
And by adding things that you typically wouldn't say are code that needs to be on GitHub into those repositories for our clients or for our employees has really helped us start to get into the granularity of how they're working.

376
00:43:35,434 --> 00:43:39,754
How do you scale into a business?

377
00:43:40,074 --> 00:43:45,034
You're going to introduce yourself to a company that hasn't embraced this.

378
00:43:46,354 --> 00:43:46,714
question.

379
00:43:46,714 --> 00:43:52,354
So the onboarding piece is really one, as soon as we meet you, we're going to be creating an avatar.

380
00:43:52,354 --> 00:44:01,314
We're going to be looking at you, looking at your knowledge, looking at the business, and starting to grab at the different pieces that you use to operate that business.

381
00:44:01,314 --> 00:44:13,754
So your CRM, your ERP, your inbox, maybe your chat history, just all of the things that we can actually pull from you that you feel comfortable sharing.

382
00:44:14,394 --> 00:44:17,514
would be basically a way that we're onboarding.

383
00:44:17,514 --> 00:44:26,354
So by asking for access to those systems, we can start to build the map, but it's an evolving process.

384
00:44:26,354 --> 00:44:32,554
So it's asking for information up front, but that's really the start of the process.

385
00:44:32,554 --> 00:44:42,554
Because there's going to be questions that you or others would ask in that onboarding process or in using the data that'll come back as, hey, we don't have that yet.

386
00:44:42,994 --> 00:44:53,754
And so if it comes back and tells us, hey, they don't, that information isn't included in the repo, we'll come into the next meeting saying, hey, can we connect to this random piece of software that you've got on the shop floor?

387
00:44:53,754 --> 00:44:57,354
Because that would really help us understand your question over here.

388
00:44:59,074 --> 00:44:59,434
Okay.

389
00:45:00,154 --> 00:45:00,954
One minute left.

390
00:45:01,114 --> 00:45:02,154
Got one more question.

391
00:45:02,154 --> 00:45:02,274
Yeah.

392
00:45:03,914 --> 00:45:11,474
I think we're talking about a lot of data here, and even in the organization, there are some data which is, I think, almost some data is sensitive.

393
00:45:11,634 --> 00:45:20,074
So, how do you ensure that space is data security and that the data is not going to the wrong and not going outside to the organization?

394
00:45:20,394 --> 00:45:22,234
Yes, a very, very good question.

395
00:45:22,634 --> 00:45:33,274
So, one of the things that, and I'll go back to the N8N example, the way that we're actually pulling information down from your business

396
00:45:33,674 --> 00:45:51,914
The reason that we've chosen to use N8N instead of Make.com or Zapier or other, let's say, cloud-hosted applications is that N8N can be put on a local machine and spun up on a local server and be fed this information or you can query that information without leaving your corporate network.

397
00:45:52,154 --> 00:45:57,754
So if it is, let's say, confidential information that you don't want to leave the premise,

398
00:45:58,154 --> 00:46:09,914
We put an NAN installation on site, on your network, and we lock that down so that it's really only accessible from a certain set of computers or things on your network.

399
00:46:09,914 --> 00:46:24,074
So, like we talked about this stuff, or maybe using some other AI tools, most of the time people are having concern that maybe this data is going outside.

400
00:46:25,314 --> 00:46:33,634
So, using GitHub, you have that capability that the data will be given the organization is not exposed to...

401
00:46:34,554 --> 00:46:38,474
Yeah, GitLab is another option.

402
00:46:38,474 --> 00:46:52,714
So if GitHub is, you know, if you don't like Microsoft and their GitHub options, GitLab can be hosted locally on that same many-to-end server, and then you would just have your repo stored there locally instead of actually on the cloud.

403
00:46:53,914 --> 00:46:58,074
With that, we'll say thank you for your time and listening today, and wish you the best.