1
00:00:00,200 --> 00:00:01,720
Our next speaker is Dr.

2
00:00:01,720 --> 00:00:03,080
Hans Hoink.

3
00:00:03,560 --> 00:00:11,240
He brings more than 25 years of experience in animal science as both an industry innovator and practicing veterinarian.

4
00:00:11,560 --> 00:00:15,400
I'm also an animal person, so if we've got that in common, love animals.

5
00:00:16,760 --> 00:00:19,080
Really excited to hear his presentation today.

6
00:00:19,480 --> 00:00:30,040
He has built his career at the intersection of science, leadership, and technology with a strong focus on applying AI and business systems to streamline development and operations.

7
00:00:30,360 --> 00:00:42,600
In today's session, he will share a first-hand perspective on using AI as a non-coder to build custom automation tools, including key lessons learned and how standardized processes enable scalable solutions.

8
00:00:42,840 --> 00:00:44,280
Please join me in welcoming Hans.

9
00:00:50,520 --> 00:00:51,720
Thank you for the introduction.

10
00:00:51,720 --> 00:00:52,520
I appreciate it.

11
00:00:54,280 --> 00:01:04,440
So I'm the managing partner of Arco Laboratories, part of the ownership structure, and also I act as the director of research.

12
00:01:04,440 --> 00:01:06,360
So we're not a huge company.

13
00:01:06,680 --> 00:01:09,720
We're a small company becoming a medium-sized company.

14
00:01:09,720 --> 00:01:13,480
That's the context of where I'm coming from in terms of

15
00:01:14,040 --> 00:01:15,560
how we're using AI.

16
00:01:16,200 --> 00:01:20,840
So the last presentation obviously was much more technical than what we're doing.

17
00:01:21,560 --> 00:01:25,640
But in terms of what we are doing, we're staying very practical.

18
00:01:25,640 --> 00:01:32,360
So if you're looking for something that can be done by a small team, this is probably a good presentation for you.

19
00:01:34,360 --> 00:01:36,280
I'll tell this story kind of as a narrative.

20
00:01:36,280 --> 00:01:43,320
Last year I went to, came to this conference and didn't really know anything about AI whatsoever.

21
00:01:44,760 --> 00:01:46,520
learned quite a bit here.

22
00:01:47,000 --> 00:01:54,280
And then after that, after the meeting, I went up to talk to Paul Gormley and just said, hey, you know, there's something that we'd like to look at.

23
00:01:54,280 --> 00:02:00,600
We get POs orders in basically every day, purchase orders, and we get quite a few.

24
00:02:01,160 --> 00:02:04,920
From when we started till now, we're shipping a lot more product.

25
00:02:05,480 --> 00:02:13,560
And so it can get to be overwhelming a little bit for our staff in terms of processing all those orders, which we have perishable product that's to ship out

26
00:02:14,040 --> 00:02:16,280
by the time UPS hits our door at noon.

27
00:02:16,280 --> 00:02:18,920
So we've got to get all that stuff ready to go back in shipping.

28
00:02:19,720 --> 00:02:21,240
Some Mondays is crazy.

29
00:02:22,400 --> 00:02:28,840
And so there's that, but there's also processing all those orders and processing them accurately.

30
00:02:29,320 --> 00:02:31,480
That's the main point, right?

31
00:02:31,560 --> 00:02:33,960
You don't want to send your product to the wrong customer.

32
00:02:34,040 --> 00:02:35,160
That's not a good look.

33
00:02:35,560 --> 00:02:37,960
So we're really focused on that.

34
00:02:37,960 --> 00:02:38,840
We do a great job.

35
00:02:38,840 --> 00:02:41,000
We've got double, you know, double check.

36
00:02:41,400 --> 00:02:45,240
But we've got these people up front that are just so good at this.

37
00:02:45,320 --> 00:02:46,920
They're really, really good at this.

38
00:02:47,240 --> 00:02:54,760
I mean, they'll get an order from a customer and our people up front will be like, that person doesn't usually order that.

39
00:02:54,760 --> 00:02:58,520
Maybe I should call them and make sure that that's what they meant to order.

40
00:02:58,840 --> 00:02:59,960
And a lot of times they're right.

41
00:03:00,120 --> 00:03:01,640
Like they send in the wrong order.

42
00:03:02,120 --> 00:03:04,600
Our customers love us because of that.

43
00:03:04,840 --> 00:03:09,080
Okay, that's something that we do that a big company not going to do.

44
00:03:09,160 --> 00:03:10,600
They're just going to send you the order.

45
00:03:11,000 --> 00:03:12,040
They're going to blame it on you.

46
00:03:12,040 --> 00:03:14,280
They're not going to refund it, you know, that sort of thing.

47
00:03:14,280 --> 00:03:16,600
So it's kind of our ace in the hole.

48
00:03:16,760 --> 00:03:29,240
Now, let's say somebody, you know, this is always, I don't want to get morbid, but you know, just the old adage is what if somebody gets hit by a truck and we lose that, you know, the redundancy of it.

49
00:03:29,520 --> 00:03:38,040
And so what we wanted to look at was could we model that into some sort of automated process using AI.

50
00:03:38,400 --> 00:03:40,160
And so I talked to Paul Gormley

51
00:03:40,920 --> 00:03:44,760
And initially he just said, hey, can you guys do this at Cirrus for us?

52
00:03:45,560 --> 00:03:46,920
And he said, yeah, we can do that.

53
00:03:47,520 --> 00:03:49,880
And this was, so this is about this time last year.

54
00:03:50,280 --> 00:03:54,680
And so we kind of went through the summer and the fall and he called me back.

55
00:03:54,680 --> 00:03:56,760
He said, hey, you know, I got a lot going on.

56
00:03:56,840 --> 00:03:58,920
I don't know if, he said, you can do this.

57
00:03:58,920 --> 00:04:00,360
He goes, you guys can do this.

58
00:04:00,520 --> 00:04:02,360
You just get an AI and ask him how to do it.

59
00:04:02,360 --> 00:04:04,600
I'll write you up the architecture for it.

60
00:04:05,160 --> 00:04:08,920
You dump it in AI and it tells you how, it'll tell you how to do that.

61
00:04:09,880 --> 00:04:11,400
And so that's what he did.

62
00:04:11,800 --> 00:04:14,440
And I'm a Gemini guy, like I've drank the Kool-Aid.

63
00:04:14,440 --> 00:04:17,240
So that's what we used.

64
00:04:17,800 --> 00:04:21,480
And it was amazingly smooth.

65
00:04:21,480 --> 00:04:24,200
I had a team of myself and two other people.

66
00:04:24,360 --> 00:04:25,640
We were working on this.

67
00:04:27,160 --> 00:04:32,600
In the winter, we didn't get a whole lot done until New Year's Eve day.

68
00:04:34,080 --> 00:04:37,560
And that's one of those days that not much is going on, at most businesses.

69
00:04:37,560 --> 00:04:42,360
And a lot of people are, the people that are there are the people that haven't taken their vacation, or to have taken all their vacation.

70
00:04:42,760 --> 00:04:45,400
Those are the people that are there, but I made sure we had the team there.

71
00:04:46,040 --> 00:04:58,120
And so we wanted to do with this PO reader, I call it, or purchase order reader, was to be able to bring these purchase orders in that come by e-mail, read it, be very accurate about putting it into the system.

72
00:04:58,120 --> 00:05:02,600
So taking that and moving it to QuickBooks, which is our accounting software.

73
00:05:03,320 --> 00:05:05,080
And I learned a lot of lessons along the way.

74
00:05:05,480 --> 00:05:07,240
So this story has a twist in it, okay?

75
00:05:07,240 --> 00:05:10,520
It's not as juicy as Dateline, but it's got a twist in it.

76
00:05:10,520 --> 00:05:12,840
So anyway, we're going along here.

77
00:05:12,840 --> 00:05:15,760
We've got this, we're, we've got this plan.

78
00:05:15,760 --> 00:05:20,360
What we want to do, we've got the architecture from Cirrus, so we feel like we're going in the right direction.

79
00:05:20,680 --> 00:05:22,440
We dump all that into AI.

80
00:05:24,280 --> 00:05:29,400
And essentially how it was built was we followed this roadmap.

81
00:05:29,560 --> 00:05:30,600
Does this have a pointer on it?

82
00:05:30,760 --> 00:05:30,920
No.

83
00:05:31,560 --> 00:05:35,240
And so we use Python, which is essentially the engine of the car.

84
00:05:35,560 --> 00:05:40,440
We use VS Code, which is our dashboard, which shows you everything that you're doing with that code.

85
00:05:41,000 --> 00:05:47,720
And we use something called Tesseract OCR, which is a, I think it's an open source optical recognition.

86
00:05:47,720 --> 00:05:58,040
So when we get these POs in, sometimes they're scanned, sometimes they're digitized, but the machine has to be able to recognize them no matter what kind of format they come in.

87
00:05:59,080 --> 00:06:06,080
So that Tesseract was actually that part of the program that looked at it, said, is this scanned or is this digitized?

88
00:06:06,080 --> 00:06:07,520
Okay, I can read it either way.

89
00:06:07,520 --> 00:06:12,200
It's going to take me a little longer if it's scanned, but it can do it.

90
00:06:12,600 --> 00:06:13,720
So that's how it was built.

91
00:06:15,720 --> 00:06:17,960
So New Year's Day, the 10 and a half hour sprint.

92
00:06:18,360 --> 00:06:21,040
So we started, I basically got everybody together.

93
00:06:21,040 --> 00:06:22,760
I said, let's see if we can do this in one day.

94
00:06:22,920 --> 00:06:24,280
Let's see if we can do it in one day.

95
00:06:24,280 --> 00:06:24,600
Okay.

96
00:06:24,600 --> 00:06:25,560
So we sat down.

97
00:06:25,880 --> 00:06:26,920
We worked.

98
00:06:27,080 --> 00:06:28,120
We did not take lunch.

99
00:06:28,120 --> 00:06:29,040
We just kept going.

100
00:06:29,720 --> 00:06:31,960
And I was like, we're going to have fun tonight.

101
00:06:31,960 --> 00:06:32,560
We're going to party.

102
00:06:32,560 --> 00:06:33,320
It's New Year's Eve.

103
00:06:33,480 --> 00:06:35,000
So we kept going.

104
00:06:35,000 --> 00:06:35,640
We kept going.

105
00:06:35,640 --> 00:06:39,560
We actually got it done to the point where

106
00:06:40,360 --> 00:06:47,560
we could get the PO reader to read the PO and put it into a format that would go into QuickBooks.

107
00:06:47,880 --> 00:06:50,520
And that's where we hit a wall.

108
00:06:52,120 --> 00:06:58,480
Because as I found out, as we found out, all of this software has security around it, right?

109
00:06:58,680 --> 00:07:00,600
So I'm not a coder.

110
00:07:01,800 --> 00:07:05,800
So if I would have been a coder or a designer, I would have known this from the beginning, right?

111
00:07:06,120 --> 00:07:09,240
So this was a lesson we learned, but sometimes these are the best lessons.

112
00:07:09,720 --> 00:07:14,520
because this is how you, I'm not going to forget that one, because we put a lot of work in.

113
00:07:15,560 --> 00:07:19,320
But we got this, it's a certificate revoked, and we couldn't do it.

114
00:07:19,320 --> 00:07:21,800
I talked to our IT people, they couldn't figure it out.

115
00:07:22,960 --> 00:07:27,000
And so it's New Year's Eve, the hell with it, let's get out of here, let's go have fun.

116
00:07:27,720 --> 00:07:33,080
So we did, but this is kind of, let's see if I can, oh good, the sound does work.

117
00:07:33,400 --> 00:07:38,560
This is kind of what I was thinking later that night, like as I was imbibing and having fun on New Year's Eve.

118
00:07:39,800 --> 00:07:40,920
About 3 or four seasons?

119
00:07:41,160 --> 00:07:42,760
They're up for sale if you want them.

120
00:07:43,560 --> 00:07:44,920
Let me see your identification.

121
00:07:45,640 --> 00:07:47,200
You don't need to see your identification.

122
00:07:47,200 --> 00:07:50,040
Obi-Wan Kenobi, the Jedi mind trick?

123
00:07:50,920 --> 00:07:52,840
These aren't the droids you're looking for.

124
00:07:53,800 --> 00:07:55,400
These aren't the droids we're looking for.

125
00:07:56,600 --> 00:07:58,040
He can go about his business.

126
00:07:58,040 --> 00:08:00,200
You can go about your business.

127
00:08:00,920 --> 00:08:01,400
Move along.

128
00:08:01,400 --> 00:08:02,920
Move along.

129
00:08:03,640 --> 00:08:04,600
So that's what I needed.

130
00:08:04,840 --> 00:08:10,680
That's what I needed was Obi-Wan Kenobi to help me get through the security wall, right?

131
00:08:11,000 --> 00:08:12,120
Some kind of magic.

132
00:08:13,960 --> 00:08:15,320
Here's what was actually going on.

133
00:08:15,720 --> 00:08:17,720
So another hard lesson learned.

134
00:08:19,400 --> 00:08:21,400
Software is not static.

135
00:08:21,400 --> 00:08:22,040
It's fluid.

136
00:08:22,360 --> 00:08:24,840
That's why we're constantly updating our computers, right?

137
00:08:25,320 --> 00:08:26,600
Well, this is one of the reasons.

138
00:08:26,600 --> 00:08:29,000
Python is a moving target.

139
00:08:29,720 --> 00:08:30,800
So this was the

140
00:08:31,480 --> 00:08:34,840
This was the version of Python I was using, which Gemini told me to use.

141
00:08:35,480 --> 00:08:38,920
And you can see it's hit its expiration date.

142
00:08:38,920 --> 00:08:41,960
Basically, its security certificate is revoked.

143
00:08:42,520 --> 00:08:45,560
So this is something that's going to happen.

144
00:08:45,560 --> 00:08:49,320
If we set up this software, this is going to happen over and over again.

145
00:08:49,320 --> 00:08:52,000
We're going to be dependent on it, and then it's going to break down.

146
00:08:52,000 --> 00:08:53,240
We're not going to know how to fix it.

147
00:08:53,880 --> 00:08:56,280
So at this point, I talked to Paul again.

148
00:08:56,920 --> 00:09:04,680
And he just said, hey, this is the point where you need to talk to a professional, a designer to think about like how to deal with this.

149
00:09:04,880 --> 00:09:05,160
Okay.

150
00:09:05,800 --> 00:09:07,640
So lessons learned.

151
00:09:08,440 --> 00:09:11,000
Again, talking to our upfront people.

152
00:09:11,400 --> 00:09:15,960
Is this DIY project really worth like corrupting all of our financial data?

153
00:09:15,960 --> 00:09:16,280
No.

154
00:09:19,080 --> 00:09:23,200
The stuff we were getting into is not very standardized.

155
00:09:23,720 --> 00:09:35,720
So it was going to be difficult for that to read that on every single PO we get and put it in correctly, maybe without an AI agent overseeing it, having a bunch of things that are set up.

156
00:09:36,200 --> 00:09:38,440
And it's a high risk, right?

157
00:09:38,440 --> 00:09:39,640
This isn't for a tinkerer.

158
00:09:39,640 --> 00:09:41,240
This is for a designer to do.

159
00:09:41,800 --> 00:09:49,800
So we did learn a whole bunch of stuff, though, in doing this, and this is the pivot, kind of the shift of the story,

160
00:09:50,280 --> 00:09:56,280
about how to do this, about how to use Gemini to code essentially.

161
00:09:56,520 --> 00:10:08,800
And what we were doing, which was crazy now when I look back on it, was we were letting Gemini coding partner code, you know, you whatever, cut and paste it and throw it in and then run the thing and see if it works.

162
00:10:08,800 --> 00:10:11,320
If it didn't work, then you go iteration, iteration, right?

163
00:10:13,960 --> 00:10:15,880
So the pivot was to go to this.

164
00:10:15,960 --> 00:10:19,320
There's another project that we were working on called a Google Sheets

165
00:10:19,720 --> 00:10:21,000
management system.

166
00:10:21,480 --> 00:10:26,600
And this was a system where we're in a very highly regulated industry.

167
00:10:26,840 --> 00:10:37,960
So we've got to validate all this equipment every year, sometimes by month, or sorry, by yearly, sometimes yearly, sometimes every six months, sometimes every quarter.

168
00:10:38,600 --> 00:10:48,680
But these are things that we do, and they're technical, but people forget how to do them because they haven't done it for a year, right?

169
00:10:49,160 --> 00:10:54,120
So there's SOPs on how to do that, but people forget about doing it.

170
00:10:54,120 --> 00:11:02,040
And we're very dependent on one person that knows exactly this schedule, and has it written out.

171
00:11:02,520 --> 00:11:10,840
But we don't have an automated process for reminding people and then having a feedback loop for those people to put in that they attest that they did it.

172
00:11:10,840 --> 00:11:12,600
Because you have, it's a legal record.

173
00:11:12,760 --> 00:11:14,280
You have to attest that you did it.

174
00:11:14,800 --> 00:11:17,000
And so what we did was

175
00:11:17,320 --> 00:11:28,600
We used a lot of this information that we learned on our kind of our failure with our PO reader to design this Google Sheets management system.

176
00:11:29,320 --> 00:11:39,400
And essentially what it does is it uses Google Forms, Gmail, and Google Sheets all together, essentially, to send out reminders.

177
00:11:39,800 --> 00:11:41,560
It's really kind of simple, actually.

178
00:11:41,680 --> 00:11:43,720
I mean, it's not as simple as I make it sound, but

179
00:11:44,520 --> 00:11:47,160
It uses an ecosystem that's already there.

180
00:11:47,440 --> 00:11:48,360
Does that make sense?

181
00:11:48,600 --> 00:11:54,200
Before, I was trying to create my own ecosystem that needed updated, that needed to do all that stuff.

182
00:11:54,680 --> 00:11:58,360
Now my designer is Google, and they're pretty damn good at it, right?

183
00:11:58,840 --> 00:12:03,640
So we got to thinking, okay, this is a better way to go.

184
00:12:03,640 --> 00:12:10,600
This is something that will last, you know, because we've got the kind of the built-in ecosystem already.

185
00:12:13,200 --> 00:12:19,160
And then the big breakthrough from this was, as I was saying, we were copying and pasting code.

186
00:12:20,520 --> 00:12:25,320
As we got close to the end of this PO project, we discovered this thing called Cursor.

187
00:12:25,720 --> 00:12:27,920
And Cursor is a heck of a tool.

188
00:12:27,920 --> 00:12:33,080
I don't know if anybody's familiar with it, but it is basically VS code.

189
00:12:33,240 --> 00:12:34,440
It's your dashboard.

190
00:12:34,920 --> 00:12:37,640
But it incorporates anthropic,

191
00:12:38,600 --> 00:12:45,560
OpenAI, you can incorporate all the LLMs into it, and it will pick the best one to write that code.

192
00:12:46,680 --> 00:12:48,120
And it's really good.

193
00:12:48,200 --> 00:12:49,160
It's really good.

194
00:12:49,400 --> 00:12:53,800
So what I had before was I had this spreadsheet that had a whole bunch of...

195
00:12:54,360 --> 00:13:04,520
Gemini was telling me, well, put this formula here in this spreadsheet, in this cell, but we'll also put in some coding, like app script, it's called, on Google Sheets.

196
00:13:04,840 --> 00:13:17,400
So it was this mishmash of formulas and code, and the more things we tried to put in it, the more it failed, basically, because it was becoming more and more complex.

197
00:13:17,800 --> 00:13:18,120
Well,

198
00:13:19,160 --> 00:13:27,320
I put in cursor and then there's this class tool that essentially pushes the software, pushes the code into Google Sheets.

199
00:13:27,640 --> 00:13:30,360
So I didn't have to cut and paste anymore, which was really nice.

200
00:13:31,480 --> 00:13:41,640
But what it did was I told it, literally, I just said, this thing is full of, you know, this thing's a mess.

201
00:13:41,640 --> 00:13:46,040
Like this thing has all these formulas in it.

202
00:13:46,920 --> 00:13:49,080
tied with code and it doesn't work.

203
00:13:49,560 --> 00:13:53,560
And it went in and replaced all of those formulas with code.

204
00:13:53,800 --> 00:13:55,200
So it's now it's completely coded.

205
00:13:55,200 --> 00:13:56,280
It did it in 10 minutes.

206
00:13:57,000 --> 00:13:57,960
10 minutes.

207
00:13:58,600 --> 00:14:00,360
This was like weeks of work.

208
00:14:00,840 --> 00:14:02,400
And it just made it better in 10 minutes.

209
00:14:02,400 --> 00:14:03,640
It was unbelievable.

210
00:14:04,520 --> 00:14:06,600
So I'm A cursor believer.

211
00:14:07,960 --> 00:14:11,480
But now we're using this tool as a very effective way.

212
00:14:12,400 --> 00:14:16,200
And we're depending on this tool now because it's extremely effective.

213
00:14:16,600 --> 00:14:19,240
in reminding people there's a feedback loop.

214
00:14:19,800 --> 00:14:29,400
It is a legal record because there's an attestation that goes along with it that says you attest that you did it, and it's linked to your, basically your digital signature.

215
00:14:29,920 --> 00:14:32,360
And so we can show a regulator, here it is.

216
00:14:33,320 --> 00:14:35,080
So it's a really, really nice tool.

217
00:14:35,880 --> 00:14:37,600
This is what the dashboard looks like.

218
00:14:37,600 --> 00:14:40,160
I mean, it's very basic, but it

219
00:14:40,240 --> 00:14:43,720
tells you, oh shoot, sorry.

220
00:14:44,760 --> 00:14:51,360
Like up here, it'll tell you what tasks are pending, what's upcoming, and most importantly, what hasn't been done.

221
00:14:51,360 --> 00:14:55,480
And in our industry, if it's not written down, it wasn't done.

222
00:14:55,800 --> 00:15:05,800
That's how we look at it in terms of highly regulated industries as we are, because we have to be able to show somebody that we did it.

223
00:15:09,240 --> 00:15:16,360
So the lessons learned from the PO reader, basically you can't automate a mess.

224
00:15:16,680 --> 00:15:19,960
Like it was, especially with just code.

225
00:15:21,240 --> 00:15:26,680
There was just too much craziness going on in terms of the difference of all the POs we get in.

226
00:15:27,280 --> 00:15:35,720
And so one thing we realized is we don't, I didn't realize this, but we don't have individual numbers for each product.

227
00:15:36,200 --> 00:15:38,840
People were just sending in the names of the products.

228
00:15:38,840 --> 00:15:41,720
I didn't realize this, but it brought it to light.

229
00:15:41,720 --> 00:15:48,360
It was like, we got to get some things in place here before we start automating, before we ever do that.

230
00:15:48,360 --> 00:15:57,000
So end of 2026 is our goal for getting unique numbers, training all our distributors on how to order our products so that we can do that.

231
00:15:57,240 --> 00:15:59,480
But without that, this isn't going to work.

232
00:15:59,640 --> 00:16:01,080
The PO reader isn't going to work.

233
00:16:01,080 --> 00:16:02,400
So that's a longer term project.

234
00:16:04,520 --> 00:16:06,760
So essentially that was with the PO reader.

235
00:16:07,920 --> 00:16:14,760
And then in my industry, we always have practice tips at our CE, for veterinarians, practice tips.

236
00:16:14,760 --> 00:16:18,840
These are my practice tips for using AI.

237
00:16:20,520 --> 00:16:22,520
The screenshot is your best friend.

238
00:16:23,000 --> 00:16:25,720
So if you're looking at something and

239
00:16:26,200 --> 00:16:33,320
you and the LLM aren't, you aren't talking the same language or it's trying to tell you one thing and you're like, no, that's not what I'm telling you.

240
00:16:33,560 --> 00:16:36,520
Just take a screenshot and throw it in there.

241
00:16:36,520 --> 00:16:44,280
Because what happens a lot of times is you'll be looking at something on that screen and you think that's the problem.

242
00:16:44,280 --> 00:16:50,680
You take a shot of the entire screen and Gemini will be like, no, look over here, like up here on the left.

243
00:16:50,680 --> 00:16:51,720
That's your problem.

244
00:16:51,880 --> 00:16:52,840
You don't have that.

245
00:16:53,720 --> 00:16:57,080
So it's extremely intuitive in terms of solving those problems.

246
00:16:57,400 --> 00:17:00,120
If you take that screenshot, you say, here's what I'm looking at.

247
00:17:00,520 --> 00:17:01,800
Now you look at it too.

248
00:17:02,760 --> 00:17:03,960
That was really helpful.

249
00:17:03,960 --> 00:17:04,840
Accept your role.

250
00:17:04,880 --> 00:17:11,000
I'm not a coder, and I shouldn't be messing with data that could sink our whole business.

251
00:17:11,000 --> 00:17:12,640
Like now we can't take orders, right?

252
00:17:12,640 --> 00:17:17,400
Because I just messed up the, whatever, the QuickBooks system.

253
00:17:18,040 --> 00:17:19,480
And I did get a lot of

254
00:17:21,560 --> 00:17:23,160
guff about that from our upfront.

255
00:17:23,160 --> 00:17:24,680
People are like, do not do that.

256
00:17:24,680 --> 00:17:25,240
We'll quit.

257
00:17:27,640 --> 00:17:28,680
Thinking ecosystems.

258
00:17:28,680 --> 00:17:35,720
So if you want to keep things simple, you know, my first example is how not to do it, kind of.

259
00:17:36,280 --> 00:17:41,240
The second example, we got a little smarter because we knew this was more

260
00:17:41,800 --> 00:17:42,520
robust.

261
00:17:42,520 --> 00:17:49,960
I guess they say that a lot in the computer world, but it was more robust because Google has the ecosystem set up.

262
00:17:50,360 --> 00:18:03,160
And it also has Gemini, which is so now we can possibly start to use Gemini to weave it into our management system as well, because all of that is already integrated.

263
00:18:05,240 --> 00:18:06,840
Don't climb walls alone.

264
00:18:06,840 --> 00:18:08,360
So again, on the PO system,

265
00:18:09,160 --> 00:18:13,400
don't get stubborn because you can get yourself a lot of trouble and then protect the core.

266
00:18:13,560 --> 00:18:18,040
So critical, critical data is critical for a reason.

267
00:18:18,440 --> 00:18:31,320
And so you don't want to start doing DIY projects on stuff that you got to think about what you're working on and then think about what would happen if you ruined it and what repercussions would have.

268
00:18:31,360 --> 00:18:34,120
I mean, you can back things up, but when we're getting

269
00:18:35,000 --> 00:18:43,880
tons of orders every 5 minutes on Monday morning, that's not the time to be down, even if you have everything backed up, because that can be a mess.

270
00:18:44,040 --> 00:18:46,320
So you always have to think about that.

271
00:18:46,320 --> 00:18:47,560
You have to be in beta mode.

272
00:18:47,560 --> 00:18:52,440
And when you get to that point, it's good to hire somebody, hire a professional.

273
00:18:52,680 --> 00:18:57,160
So that's my presentation.

274
00:18:58,120 --> 00:18:58,600
Thank you.