WEBVTT

1
00:00:05.559 --> 00:00:09.480
<v Speaker 1>Hello everybody, Welcome to another exciting episode of JavaScript Jobber.

2
00:00:09.599 --> 00:00:11.679
<v Speaker 1>I am Steve Edwards, the host with the face for

3
00:00:11.800 --> 00:00:13.839
<v Speaker 1>radio and the voice for being a mine. But I'm

4
00:00:13.880 --> 00:00:17.719
<v Speaker 1>still your host. I am flying solo today on the

5
00:00:17.760 --> 00:00:21.719
<v Speaker 1>panel Checkscott an anniversary, who knows about AJ and Dan

6
00:00:22.000 --> 00:00:26.839
<v Speaker 1>Busy lives Anyway, I am here with Gilad Shoham. I

7
00:00:26.839 --> 00:00:31.280
<v Speaker 1>believe I said that right, right, yes, hopefully right? All right.

8
00:00:31.480 --> 00:00:35.479
<v Speaker 1>Gilad is coming to us from Israel, and we are

9
00:00:35.520 --> 00:00:40.439
<v Speaker 1>here to talk about AI and using AI to generate

10
00:00:40.799 --> 00:00:46.240
<v Speaker 1>enterprise infrastructure, I believe. So before we get started into

11
00:00:46.280 --> 00:00:48.079
<v Speaker 1>the topic, why don't you tell us a little bit

12
00:00:48.119 --> 00:00:51.359
<v Speaker 1>about yourself, Gilaud, your dev history and anything else you

13
00:00:51.359 --> 00:00:52.240
<v Speaker 1>want to tell us.

14
00:00:52.759 --> 00:00:57.759
<v Speaker 2>Sure. So, my name is Gilad Trump. I'm vipop engineering

15
00:00:57.759 --> 00:01:02.679
<v Speaker 2>at pitt Cloud, and apart from this, I'm also like

16
00:01:03.719 --> 00:01:08.040
<v Speaker 2>a mentor for start ups, for developers, for fiam deaders,

17
00:01:08.519 --> 00:01:12.719
<v Speaker 2>and also from doing some engine investments in startups. I

18
00:01:12.760 --> 00:01:15.719
<v Speaker 2>also have like a brand with a blog and podcast,

19
00:01:15.760 --> 00:01:22.840
<v Speaker 2>a YouTube channel about small homes in Hebrew and love coding.

20
00:01:23.040 --> 00:01:28.079
<v Speaker 2>Usually that's that's what I'm doing, No making transforming coffee

21
00:01:28.079 --> 00:01:28.640
<v Speaker 2>into code.

22
00:01:30.120 --> 00:01:31.640
<v Speaker 1>What do you say coffee in the code.

23
00:01:31.959 --> 00:01:34.280
<v Speaker 2>Yeah, but but usually for me it's a bit different.

24
00:01:34.319 --> 00:01:37.000
<v Speaker 2>Like during the day, I'm transforming coffee into code, and

25
00:01:37.079 --> 00:01:40.159
<v Speaker 2>at night I'm transforming code into coffee. So I'm connecting

26
00:01:40.280 --> 00:01:43.359
<v Speaker 2>my writing codes that build me a coffee.

27
00:01:43.519 --> 00:01:49.480
<v Speaker 1>That's great, Mede, Yeah, I prefer my caffeine in cold form.

28
00:01:49.519 --> 00:01:51.519
<v Speaker 1>But yeah, I get what you need, get what you

29
00:01:51.560 --> 00:01:55.879
<v Speaker 1>mean for sure. Okay, So tell us about uh bit.

30
00:01:56.040 --> 00:01:59.040
<v Speaker 1>What is Bit's purposes? Dot there I think it did

31
00:01:59.120 --> 00:02:00.000
<v Speaker 1>dot cloud.

32
00:01:59.760 --> 00:02:03.200
<v Speaker 2>Right, yeah, yeah, yeah, so biot cloud. It's like the

33
00:02:03.239 --> 00:02:05.680
<v Speaker 2>company we have, like a big open source called bit.

34
00:02:06.439 --> 00:02:08.759
<v Speaker 2>The website for the open source is bit oft dev,

35
00:02:09.199 --> 00:02:13.159
<v Speaker 2>and we are building a platform for composable software. We

36
00:02:13.280 --> 00:02:18.840
<v Speaker 2>help organizations to improve their develocity DEV quality by helping

37
00:02:18.879 --> 00:02:24.520
<v Speaker 2>them to compose applications from independent features and components, and

38
00:02:24.639 --> 00:02:27.560
<v Speaker 2>help them to manage and share and collaborate these features

39
00:02:27.560 --> 00:02:32.879
<v Speaker 2>and components between projects, between teams. By increasing reuse and

40
00:02:32.960 --> 00:02:37.639
<v Speaker 2>collaboration and discovery of existing code, we are improving the

41
00:02:37.800 --> 00:02:43.360
<v Speaker 2>quality and velocity. And now we are also building AI

42
00:02:43.439 --> 00:02:47.719
<v Speaker 2>on top of this approach that we will discuss in

43
00:02:47.759 --> 00:02:48.560
<v Speaker 2>this episode.

44
00:02:49.960 --> 00:02:54.000
<v Speaker 1>Okay, so a lot of that's pretty high level description

45
00:02:55.199 --> 00:02:57.039
<v Speaker 1>of what you're doing sounds something I would see in

46
00:02:57.080 --> 00:03:00.240
<v Speaker 1>a job description or company description. Can you give a

47
00:03:00.240 --> 00:03:04.719
<v Speaker 1>little more detail or maybe an example of a company

48
00:03:04.759 --> 00:03:09.240
<v Speaker 1>where or where you would use your UH, your tools,

49
00:03:09.719 --> 00:03:11.560
<v Speaker 1>your big tools, and then when you talk about AI

50
00:03:11.639 --> 00:03:14.199
<v Speaker 1>and how AI will on top of those.

51
00:03:14.400 --> 00:03:18.879
<v Speaker 2>Yes, sure so. So usually organizations come to us when

52
00:03:18.879 --> 00:03:22.639
<v Speaker 2>they want to UH to increase, increase or improve their

53
00:03:22.800 --> 00:03:28.719
<v Speaker 2>dev DEIR methodology and the environments. We we help them

54
00:03:28.759 --> 00:03:34.080
<v Speaker 2>to componentize their their code base and then help them

55
00:03:34.120 --> 00:03:39.560
<v Speaker 2>to share and reuse components. For example, the popular use

56
00:03:39.599 --> 00:03:44.400
<v Speaker 2>case is sharing design systems as individual components. So once

57
00:03:44.479 --> 00:03:48.520
<v Speaker 2>you have the ability to easily create individual components and

58
00:03:48.599 --> 00:03:52.400
<v Speaker 2>install them in different places and see history for each

59
00:03:52.599 --> 00:03:57.680
<v Speaker 2>component individually, plus a way to find these components too,

60
00:03:58.919 --> 00:04:05.400
<v Speaker 2>to experience disse components, it helps them to to improve

61
00:04:05.400 --> 00:04:10.919
<v Speaker 2>the reusability and collaboration. And we also have another project,

62
00:04:10.919 --> 00:04:16.399
<v Speaker 2>another open source we which we all start integrating into

63
00:04:16.560 --> 00:04:20.279
<v Speaker 2>large organizations. It's called it called Harmony. You can find

64
00:04:20.319 --> 00:04:23.600
<v Speaker 2>it in our homepages. One of the most in the

65
00:04:23.920 --> 00:04:27.399
<v Speaker 2>initial pages and how many is the project that helped

66
00:04:27.480 --> 00:04:33.800
<v Speaker 2>organization to build features that are individual. It uses principles

67
00:04:33.800 --> 00:04:37.800
<v Speaker 2>like in version of control, so so the platform team

68
00:04:38.240 --> 00:04:42.160
<v Speaker 2>is building the shell application, and each product team can

69
00:04:42.240 --> 00:04:47.319
<v Speaker 2>integrate itself to the platform. So this reduced the buttonneck

70
00:04:47.399 --> 00:04:51.639
<v Speaker 2>from the platform team. It helps the dev experience for

71
00:04:51.680 --> 00:04:57.319
<v Speaker 2>each team. So the so the platform team only provides

72
00:04:57.399 --> 00:05:01.560
<v Speaker 2>APIs what we call usually like slots for the other

73
00:05:01.639 --> 00:05:05.000
<v Speaker 2>teams to integrate into them. For example, this works both

74
00:05:05.000 --> 00:05:08.279
<v Speaker 2>influnted and back end. For example, let's say you have

75
00:05:08.439 --> 00:05:14.480
<v Speaker 2>like users features or users team. They will add a

76
00:05:14.600 --> 00:05:18.199
<v Speaker 2>logo in the like an avatar on the on the menubal,

77
00:05:18.279 --> 00:05:22.240
<v Speaker 2>they will register an icon. They will register a route

78
00:05:22.240 --> 00:05:24.439
<v Speaker 2>in the front end that is Slash a sign up

79
00:05:24.560 --> 00:05:28.360
<v Speaker 2>or Slash login or something like this. They will register

80
00:05:29.240 --> 00:05:32.120
<v Speaker 2>graph q l APIs or rest APIs on the back end,

81
00:05:32.680 --> 00:05:38.160
<v Speaker 2>and that's the way each feature is integrated itself to

82
00:05:38.199 --> 00:05:42.079
<v Speaker 2>the platform and can provide APIs for other features to

83
00:05:42.160 --> 00:05:45.360
<v Speaker 2>integrate into it. So for example, if I have like

84
00:05:45.600 --> 00:05:48.839
<v Speaker 2>an e commerce product and they have like the the

85
00:05:48.920 --> 00:05:53.720
<v Speaker 2>product team products teams that render a grade of products,

86
00:05:54.240 --> 00:05:58.240
<v Speaker 2>they grade of products and they can provide an API

87
00:05:58.439 --> 00:06:02.680
<v Speaker 2>for the for the billing team to add the d

88
00:06:02.720 --> 00:06:05.959
<v Speaker 2>to CUD button to each cloud. So this button is

89
00:06:06.000 --> 00:06:10.560
<v Speaker 2>now responsibility of the building team. And it's integrated into

90
00:06:10.639 --> 00:06:15.439
<v Speaker 2>the product team and not the opposite. And this helps

91
00:06:15.600 --> 00:06:20.839
<v Speaker 2>to increase velocity and increase like to scan the development

92
00:06:21.439 --> 00:06:25.560
<v Speaker 2>because now everything is standardized how you connect yourself to

93
00:06:25.600 --> 00:06:31.680
<v Speaker 2>the platform. And it also helped with the deployment and

94
00:06:31.959 --> 00:06:38.120
<v Speaker 2>making funding and back end as one atomic entity that

95
00:06:38.240 --> 00:06:40.519
<v Speaker 2>is part of it, so you have like one entity.

96
00:06:40.560 --> 00:06:43.759
<v Speaker 2>It's the feature that it's like a manifest or like

97
00:06:43.839 --> 00:06:47.560
<v Speaker 2>the API of your feature. And this contains both the

98
00:06:47.600 --> 00:06:50.399
<v Speaker 2>FUNTA and the back end, so now you can deploy

99
00:06:50.639 --> 00:06:52.879
<v Speaker 2>funding and back end together or roll back FUNTA and

100
00:06:52.959 --> 00:07:00.560
<v Speaker 2>backen together, which helped reduce issues on run time's derived

101
00:07:00.560 --> 00:07:05.839
<v Speaker 2>from inconsistency between Bacon and FONTA and or between versions

102
00:07:05.879 --> 00:07:12.040
<v Speaker 2>of of FUNTA and backen or different features. So that's

103
00:07:12.160 --> 00:07:15.240
<v Speaker 2>like a very high level and and on top of it,

104
00:07:15.319 --> 00:07:18.519
<v Speaker 2>for each component, we provide a set of tools like

105
00:07:19.560 --> 00:07:23.399
<v Speaker 2>discovery portals where you can see the dogs, the rendering,

106
00:07:23.639 --> 00:07:26.800
<v Speaker 2>the test results, the dependency graph, and we do version

107
00:07:26.879 --> 00:07:29.800
<v Speaker 2>management for it. We are kind of competing with Git

108
00:07:29.879 --> 00:07:34.560
<v Speaker 2>and gitub. Okay, we don't use Git and geitub internally

109
00:07:34.600 --> 00:07:38.600
<v Speaker 2>in our company because we are doing version management for

110
00:07:38.720 --> 00:07:44.199
<v Speaker 2>components and we have the entire features of the entire

111
00:07:44.240 --> 00:07:47.680
<v Speaker 2>life cycle of each component, so we don't need get

112
00:07:47.680 --> 00:07:51.279
<v Speaker 2>and git ub. Usually we just bring the components we

113
00:07:51.319 --> 00:07:54.800
<v Speaker 2>want to change into a workspace, edit them, and then

114
00:07:55.680 --> 00:07:59.079
<v Speaker 2>saw away this workspace. And then on the cloud we

115
00:07:59.120 --> 00:08:02.120
<v Speaker 2>have like the third we have c i FO components,

116
00:08:02.439 --> 00:08:07.639
<v Speaker 2>which is something unique. It's propagating ci which you can

117
00:08:08.879 --> 00:08:11.439
<v Speaker 2>change one component. Let's say a button. We will run

118
00:08:11.480 --> 00:08:13.720
<v Speaker 2>the test for this button, and then we'll run the

119
00:08:13.720 --> 00:08:15.759
<v Speaker 2>test of the card that uses this button with the

120
00:08:15.879 --> 00:08:19.120
<v Speaker 2>virtual version of the button, and then the test for

121
00:08:19.240 --> 00:08:22.120
<v Speaker 2>grid with a virtual version of the card with the

122
00:08:22.199 --> 00:08:25.160
<v Speaker 2>virtual version of the button. So we can propagate the

123
00:08:25.240 --> 00:08:28.920
<v Speaker 2>updates and test all the updates cause the graph in

124
00:08:29.000 --> 00:08:32.360
<v Speaker 2>parallel and give you, like the insights about what happens

125
00:08:32.440 --> 00:08:36.080
<v Speaker 2>with you changing the button. Now it affects any component,

126
00:08:36.440 --> 00:08:40.200
<v Speaker 2>any dependent in the graph, so we.

127
00:08:40.240 --> 00:08:43.039
<v Speaker 1>Have Okay, so that's that's a lot to unpack.

128
00:08:43.600 --> 00:08:47.960
<v Speaker 2>Yeah, a short version of the of it.

129
00:08:49.159 --> 00:08:51.279
<v Speaker 1>Okay, so let's go back. So let's go back. And

130
00:08:51.320 --> 00:08:55.039
<v Speaker 1>then in terms of you know, being the low level developer,

131
00:08:55.440 --> 00:08:59.960
<v Speaker 1>you know who is thinking about tools, is this length

132
00:09:00.080 --> 00:09:03.200
<v Speaker 1>with the agnostic I mean, can your infrastructure work with

133
00:09:04.960 --> 00:09:08.000
<v Speaker 1>any number of languages, say, for instance, Larra Belle, Ruby

134
00:09:08.080 --> 00:09:11.720
<v Speaker 1>node on the back end, View Angular, spelled React on

135
00:09:11.759 --> 00:09:18.000
<v Speaker 1>the front end. Are there specific maybe languages or frameworks

136
00:09:18.039 --> 00:09:21.519
<v Speaker 1>that you don't support or work with. How does that work?

137
00:09:22.120 --> 00:09:25.120
<v Speaker 2>Okay, good, great question. So the core of bit is

138
00:09:25.200 --> 00:09:30.720
<v Speaker 2>language agnostic. However, there are many places which are language specific.

139
00:09:30.799 --> 00:09:34.519
<v Speaker 2>For example, we know to recognize dependencies automatically from you

140
00:09:35.039 --> 00:09:37.600
<v Speaker 2>est from your source code, or we know to install

141
00:09:37.600 --> 00:09:42.120
<v Speaker 2>dependencies automatically, which are of course language specific. At the moment,

142
00:09:42.360 --> 00:09:46.679
<v Speaker 2>we are supporting all JavaScript types slip ecosystem, which means

143
00:09:46.720 --> 00:09:50.679
<v Speaker 2>no JS on the back end, JavaScript not typescript on

144
00:09:50.720 --> 00:09:53.799
<v Speaker 2>the front end, all the major frameworks React, View, Angular,

145
00:09:54.960 --> 00:10:00.039
<v Speaker 2>web components, frameworks like cleat and stuff like this, and

146
00:10:00.120 --> 00:10:03.679
<v Speaker 2>of course all the other stuff of the web like

147
00:10:03.919 --> 00:10:07.720
<v Speaker 2>htmils is this and stuff like this, sas says everything.

148
00:10:09.480 --> 00:10:13.039
<v Speaker 2>We do have plans to support more languages, but not

149
00:10:13.159 --> 00:10:15.360
<v Speaker 2>in the near future. I don't know when will it happen,

150
00:10:15.519 --> 00:10:19.519
<v Speaker 2>So I cannot commit on as languages with the moment.

151
00:10:20.799 --> 00:10:23.120
<v Speaker 1>Okay, so you know, so on the back end, is

152
00:10:23.159 --> 00:10:25.039
<v Speaker 1>it just no then? Is that correct?

153
00:10:25.600 --> 00:10:25.919
<v Speaker 2>Yes?

154
00:10:26.000 --> 00:10:29.919
<v Speaker 1>Okay? So there though Ruby, any any PHP based languages.

155
00:10:30.000 --> 00:10:32.000
<v Speaker 2>That's not supported, not at the moment.

156
00:10:32.080 --> 00:10:35.720
<v Speaker 1>No, okay, all right, that's good to know. Okay, So

157
00:10:35.799 --> 00:10:37.720
<v Speaker 1>that makes it a little more easier to understand in

158
00:10:37.799 --> 00:10:43.080
<v Speaker 1>terms of components, because most any JavaScript framework structure on

159
00:10:43.120 --> 00:10:45.879
<v Speaker 1>the front end is going to have support components by themselves, right,

160
00:10:46.000 --> 00:10:50.159
<v Speaker 1>or your components different than when you talk about components

161
00:10:50.159 --> 00:10:52.679
<v Speaker 1>that you're creating a component and that that's different than

162
00:10:52.759 --> 00:10:56.480
<v Speaker 1>say a view single file component or a reacting component.

163
00:10:56.519 --> 00:11:00.679
<v Speaker 2>Is that correct? Yes and no. So so it is

164
00:11:00.720 --> 00:11:03.919
<v Speaker 2>not touching your source code. So the act component of

165
00:11:03.960 --> 00:11:07.320
<v Speaker 2>your component is completely the same with or without bit

166
00:11:08.000 --> 00:11:12.840
<v Speaker 2>bit component is like it's like a wrapper around it

167
00:11:12.919 --> 00:11:15.320
<v Speaker 2>that manage all the meta data of this component. So

168
00:11:15.399 --> 00:11:18.360
<v Speaker 2>let's say you have the act component, I don't know,

169
00:11:18.399 --> 00:11:21.360
<v Speaker 2>a button, a card, whatever. The bit component of this

170
00:11:21.480 --> 00:11:25.600
<v Speaker 2>card will have different aspects of this component, so fist,

171
00:11:25.639 --> 00:11:28.759
<v Speaker 2>it will have the source files okay, maybe one file,

172
00:11:28.799 --> 00:11:33.240
<v Speaker 2>maybe more than one file. It will have artifacts of

173
00:11:33.320 --> 00:11:36.440
<v Speaker 2>this component for example the compiled files or the band

174
00:11:37.320 --> 00:11:40.600
<v Speaker 2>or the package the out that you install from NPM.

175
00:11:40.679 --> 00:11:43.679
<v Speaker 2>It's part of this component as well. It will have

176
00:11:44.000 --> 00:11:47.279
<v Speaker 2>the dependency graphs, so all of your dependencies, all the

177
00:11:47.360 --> 00:11:49.559
<v Speaker 2>three of dependencies you have it's also part of the

178
00:11:49.559 --> 00:11:56.279
<v Speaker 2>bit component and also as of meta data like description labels,

179
00:11:57.240 --> 00:12:00.159
<v Speaker 2>how to compile this component like to use typeestip you

180
00:12:00.240 --> 00:12:04.240
<v Speaker 2>use Babel, or which framework you used to test it

181
00:12:04.399 --> 00:12:07.679
<v Speaker 2>like jest or moca or v test and which configuration.

182
00:12:08.200 --> 00:12:10.399
<v Speaker 2>So all of this meta data is also part of

183
00:12:10.440 --> 00:12:13.559
<v Speaker 2>this component. And we take all of this meta data

184
00:12:13.720 --> 00:12:16.519
<v Speaker 2>with the dependency graph, the source falde, the artifact, and

185
00:12:16.720 --> 00:12:20.519
<v Speaker 2>we version this so you have a version of component

186
00:12:20.600 --> 00:12:24.480
<v Speaker 2>with all this meta data and each one is individual components.

187
00:12:25.879 --> 00:12:31.440
<v Speaker 1>Okay, so what is what languages is this BIT used

188
00:12:31.440 --> 00:12:35.080
<v Speaker 1>to do all this? What's under the bit codebase? Is

189
00:12:35.080 --> 00:12:38.039
<v Speaker 1>it c is it C plus plus? Is it JavaScript?

190
00:12:38.200 --> 00:12:41.000
<v Speaker 1>Is it node? Is it what I would assume it's

191
00:12:41.039 --> 00:12:41.639
<v Speaker 1>something like node?

192
00:12:41.720 --> 00:12:46.279
<v Speaker 2>Right, yes, correct, So it's it's node type script. And

193
00:12:46.440 --> 00:12:50.120
<v Speaker 2>we build everything in bit using bit and how many

194
00:12:50.440 --> 00:12:53.840
<v Speaker 2>we are doing radical dog footing. We are the largest

195
00:12:53.960 --> 00:12:57.000
<v Speaker 2>user of the bit ecosystem. We build everything with bit

196
00:12:57.039 --> 00:13:04.399
<v Speaker 2>components now cutting conels both like front end and back end,

197
00:13:05.000 --> 00:13:07.360
<v Speaker 2>and also the c l I. Okay, the c l

198
00:13:07.399 --> 00:13:09.639
<v Speaker 2>I as well. The c l is open source. It's

199
00:13:09.679 --> 00:13:13.120
<v Speaker 2>also built with BIT and with Harmony. So if you

200
00:13:13.200 --> 00:13:15.879
<v Speaker 2>look for example on the main file of the bit

201
00:13:15.960 --> 00:13:18.919
<v Speaker 2>c l I. You'll just see the Harmony manifest which

202
00:13:19.240 --> 00:13:22.759
<v Speaker 2>which mentioned which features uh the bitt l I have.

203
00:13:22.960 --> 00:13:25.200
<v Speaker 2>And if you want your own version of the bt I,

204
00:13:25.279 --> 00:13:27.399
<v Speaker 2>you can just remove lines from there and you get

205
00:13:27.519 --> 00:13:30.840
<v Speaker 2>another composition of the bit, the bit c l I.

206
00:13:31.600 --> 00:13:35.080
<v Speaker 2>And that's why everything is also extensible, so you can

207
00:13:35.360 --> 00:13:37.720
<v Speaker 2>the same poet you can apply on BIT. So if

208
00:13:37.720 --> 00:13:40.639
<v Speaker 2>you want a new commanding bit, you can register a

209
00:13:40.639 --> 00:13:42.840
<v Speaker 2>new command. If you want new tab in the U

210
00:13:42.879 --> 00:13:44.639
<v Speaker 2>I in the front end, you can register a tab

211
00:13:45.120 --> 00:13:48.320
<v Speaker 2>for yourself in in our UI, same for our backend.

212
00:13:50.080 --> 00:13:54.559
<v Speaker 2>So everything is built with bit internally.

213
00:13:56.399 --> 00:13:59.360
<v Speaker 1>Okay, Now the other thing I picked my interest was

214
00:13:59.440 --> 00:14:02.720
<v Speaker 1>you talked about get and get hub and not needing them.

215
00:14:03.600 --> 00:14:08.080
<v Speaker 1>So so in terms of versioning, the different your bit

216
00:14:08.159 --> 00:14:10.960
<v Speaker 1>components and all that, do you have like your own

217
00:14:11.039 --> 00:14:13.279
<v Speaker 1>version of you get written, or there's get under the

218
00:14:13.279 --> 00:14:15.840
<v Speaker 1>hood you just don't need getthub or do you just

219
00:14:15.919 --> 00:14:18.240
<v Speaker 1>use your own your eye or how how does that work?

220
00:14:18.720 --> 00:14:21.240
<v Speaker 2>Okay? So there is no GIT under the hood at all,

221
00:14:21.320 --> 00:14:24.519
<v Speaker 2>No GIT, no geit ub, nothing related to geit except

222
00:14:24.559 --> 00:14:29.000
<v Speaker 2>from some general ideas about like the how like the

223
00:14:29.200 --> 00:14:35.080
<v Speaker 2>distributed then database, but we build everything from scratch and

224
00:14:35.240 --> 00:14:37.720
<v Speaker 2>each component is like I said, it's like you can

225
00:14:37.720 --> 00:14:41.720
<v Speaker 2>think about each component is kind of like a mini repository, okay,

226
00:14:41.799 --> 00:14:44.320
<v Speaker 2>with all the stuff that we mentioned before, and it

227
00:14:44.399 --> 00:14:47.919
<v Speaker 2>it allow you to edit any component or set of

228
00:14:47.960 --> 00:14:52.639
<v Speaker 2>components from any fold there. So if you are now

229
00:14:52.720 --> 00:14:55.200
<v Speaker 2>working on a feature, let's say a head there, you're

230
00:14:55.240 --> 00:14:57.559
<v Speaker 2>bringing the components you need for these changes in the

231
00:14:57.559 --> 00:15:00.120
<v Speaker 2>head or you will bring logo, you'll bring the the

232
00:15:00.159 --> 00:15:03.120
<v Speaker 2>search box, you will bring menu items I don't know,

233
00:15:03.480 --> 00:15:05.840
<v Speaker 2>and you can change them, but you don't need the

234
00:15:05.879 --> 00:15:08.480
<v Speaker 2>code of the foot or the code of the products.

235
00:15:08.480 --> 00:15:11.399
<v Speaker 2>If you're working on a header, so you bring set

236
00:15:11.440 --> 00:15:14.960
<v Speaker 2>of components, you put them on what we called a lane.

237
00:15:15.360 --> 00:15:18.360
<v Speaker 2>A lane is kind of similar to git brench in

238
00:15:18.399 --> 00:15:22.320
<v Speaker 2>some sense, but it's like cross components, so you can

239
00:15:22.320 --> 00:15:25.039
<v Speaker 2>think about it like a cross rip a branch kind of.

240
00:15:27.279 --> 00:15:30.320
<v Speaker 2>And then you make a change request in our in

241
00:15:30.320 --> 00:15:34.279
<v Speaker 2>our cloud platform, and there you can do a review

242
00:15:34.320 --> 00:15:37.080
<v Speaker 2>process which is similar to GitHub but a bit more

243
00:15:37.120 --> 00:15:42.080
<v Speaker 2>advanced because on gitub you're only reviewing source code changes.

244
00:15:42.200 --> 00:15:45.200
<v Speaker 2>And then bit because we have all of this, you

245
00:15:45.240 --> 00:15:47.519
<v Speaker 2>can review and we can give you side by side

246
00:15:47.559 --> 00:15:51.480
<v Speaker 2>the source code of course, and also the rendered examples,

247
00:15:51.480 --> 00:15:54.080
<v Speaker 2>so you can see how the button, how the example

248
00:15:54.120 --> 00:15:57.720
<v Speaker 2>of the button renders before and after the docommentation side

249
00:15:57.720 --> 00:16:01.639
<v Speaker 2>by side, the testing side by side, the dependencies side

250
00:16:01.679 --> 00:16:03.919
<v Speaker 2>by side, and then you can review all of it,

251
00:16:04.360 --> 00:16:08.159
<v Speaker 2>then merge it and we have we implement this branching mechanism,

252
00:16:08.320 --> 00:16:12.799
<v Speaker 2>merge mechanism, conflict resolution everything from sketch.

253
00:16:15.080 --> 00:16:20.919
<v Speaker 1>Okay, So then if I'm it sounds like this is

254
00:16:20.919 --> 00:16:24.000
<v Speaker 1>is it almost a no code solution in terms of

255
00:16:24.159 --> 00:16:30.200
<v Speaker 1>a non coder can create these bit components to place wherever?

256
00:16:30.320 --> 00:16:33.240
<v Speaker 1>Or is this a is still a developer tool? You

257
00:16:33.279 --> 00:16:35.879
<v Speaker 1>said something about using an example of the building department.

258
00:16:36.000 --> 00:16:38.919
<v Speaker 1>Having worked in building departments, usually there's not coders in there,

259
00:16:39.639 --> 00:16:41.879
<v Speaker 1>so they need some sort of drag and drop tool.

260
00:16:41.919 --> 00:16:45.600
<v Speaker 1>Is it still just a developer tool for managing components

261
00:16:45.600 --> 00:16:47.279
<v Speaker 1>and then you can, you know, put it as needed

262
00:16:47.360 --> 00:16:48.759
<v Speaker 1>or is it like a no code tool that a

263
00:16:48.840 --> 00:16:49.960
<v Speaker 1>non developer to use.

264
00:16:50.519 --> 00:16:53.879
<v Speaker 2>Okay, so it's it's completely a tool for developers. It's

265
00:16:54.080 --> 00:16:58.519
<v Speaker 2>not a no code tool at all. It's like regular codes.

266
00:16:58.559 --> 00:17:01.720
<v Speaker 2>It's written by developers and we help them just to

267
00:17:02.559 --> 00:17:07.079
<v Speaker 2>wiring everything, sharing it so for example, creating one other

268
00:17:07.200 --> 00:17:12.240
<v Speaker 2>packages manually, it's a long process. And to try to

269
00:17:12.359 --> 00:17:16.160
<v Speaker 2>change someone else code. If you're using like a design

270
00:17:16.200 --> 00:17:19.079
<v Speaker 2>system component from some other team and you want to

271
00:17:19.200 --> 00:17:23.240
<v Speaker 2>change it, it's a complicated process. If you want to

272
00:17:23.279 --> 00:17:26.640
<v Speaker 2>search code search component in your organization, you have no

273
00:17:26.720 --> 00:17:31.680
<v Speaker 2>Google inside your organization, it's complicated. So we are helping

274
00:17:31.680 --> 00:17:36.759
<v Speaker 2>the developers to manage all these complexities and help them

275
00:17:36.920 --> 00:17:41.240
<v Speaker 2>not only with tech but also with methodologies. We help

276
00:17:41.279 --> 00:17:44.559
<v Speaker 2>you to get insight about if you're doing stuff right

277
00:17:44.680 --> 00:17:48.839
<v Speaker 2>and help to form not only with tech, like how

278
00:17:49.279 --> 00:17:52.880
<v Speaker 2>stuff should be formulated in the organization, for example, the

279
00:17:52.880 --> 00:17:56.119
<v Speaker 2>world component. Is this something related to R and D

280
00:17:57.039 --> 00:18:02.799
<v Speaker 2>to product to designer? This is a question, okay, Like

281
00:18:02.960 --> 00:18:06.839
<v Speaker 2>how you name stuff, how you put boundaries and split

282
00:18:07.119 --> 00:18:11.119
<v Speaker 2>the organization into teams, and we help you to standardize

283
00:18:11.160 --> 00:18:13.920
<v Speaker 2>this entire process and make it effective.

284
00:18:15.480 --> 00:18:18.480
<v Speaker 1>Okay, So this all managed from you mentioned a cli?

285
00:18:18.599 --> 00:18:20.759
<v Speaker 1>Is this all managed from a CLI? Is or sort

286
00:18:20.759 --> 00:18:24.000
<v Speaker 1>of a UI for managing components and the tendencies? Or

287
00:18:24.079 --> 00:18:26.319
<v Speaker 1>is it all done from the from the command line?

288
00:18:27.039 --> 00:18:30.240
<v Speaker 2>So we have a CLI that you can do all

289
00:18:30.240 --> 00:18:33.599
<v Speaker 2>the base operations. We also have like a vis Code extension,

290
00:18:33.680 --> 00:18:35.799
<v Speaker 2>so we don't need the cl I if you don't

291
00:18:35.839 --> 00:18:38.640
<v Speaker 2>want to mess with the CLI. Similar to it's similar

292
00:18:38.680 --> 00:18:41.680
<v Speaker 2>to like the GIT extension for viscode. We even like

293
00:18:41.839 --> 00:18:44.680
<v Speaker 2>using the same tubs on the VS code. So if

294
00:18:44.680 --> 00:18:47.359
<v Speaker 2>you go to the version control tabs that you use

295
00:18:47.440 --> 00:18:51.119
<v Speaker 2>for Git, you will see bit components for example, and

296
00:18:51.200 --> 00:18:54.039
<v Speaker 2>you will see not only code differences, you will see

297
00:18:54.039 --> 00:18:57.359
<v Speaker 2>dependencies differences. We can put them on inside viscode side

298
00:18:57.359 --> 00:19:01.079
<v Speaker 2>by side for example. So we have the c alliance

299
00:19:01.119 --> 00:19:03.839
<v Speaker 2>and we have the cloud where we host your component,

300
00:19:03.960 --> 00:19:05.920
<v Speaker 2>and then you can see for each component, you can

301
00:19:05.920 --> 00:19:09.960
<v Speaker 2>see the documentation. You can see example and how it's rendered.

302
00:19:10.000 --> 00:19:13.359
<v Speaker 2>If it's a UI component, you can see the test.

303
00:19:13.400 --> 00:19:15.839
<v Speaker 2>You can see a graph visual graph of all your

304
00:19:15.880 --> 00:19:20.720
<v Speaker 2>dependencies and dependence you know, filter it by teams or

305
00:19:20.880 --> 00:19:22.680
<v Speaker 2>by levels or stuff like this.

306
00:19:25.400 --> 00:19:29.119
<v Speaker 1>Okay, now you mentioned your vs code extension. Do you

307
00:19:29.119 --> 00:19:34.000
<v Speaker 1>have extensions for other tools like in Talents, heads, PhD.

308
00:19:34.480 --> 00:19:37.160
<v Speaker 2>Okay, at the moment, it's on our roadmap. But we

309
00:19:37.160 --> 00:19:40.880
<v Speaker 2>are a small startup working on this for like almost

310
00:19:40.880 --> 00:19:45.200
<v Speaker 2>ten years right now. But since we're still a small team,

311
00:19:45.359 --> 00:19:47.519
<v Speaker 2>then right now we have god.

312
00:19:47.359 --> 00:19:51.359
<v Speaker 1>Only Okay, all right, I know as an intelligent user,

313
00:19:51.400 --> 00:19:54.480
<v Speaker 1>I can say we're almost always discriminated against the vs

314
00:19:54.519 --> 00:19:56.960
<v Speaker 1>code users that always get the first plug ins and stuff.

315
00:19:56.960 --> 00:19:58.119
<v Speaker 1>But that's okay, we're used to it.

316
00:19:58.160 --> 00:20:02.079
<v Speaker 2>We do have a feature which called cloud Walkspace, which

317
00:20:02.119 --> 00:20:06.400
<v Speaker 2>allow you to edit any component from the cloud. It's

318
00:20:06.440 --> 00:20:08.799
<v Speaker 2>like opening like a viscode on the cloud, but this

319
00:20:08.920 --> 00:20:11.440
<v Speaker 2>is like a real vis code, so you can have

320
00:20:11.640 --> 00:20:13.880
<v Speaker 2>you have like a docal container behind it, so you

321
00:20:13.920 --> 00:20:17.720
<v Speaker 2>can develop like no gs or beacon stuff from the

322
00:20:17.759 --> 00:20:22.240
<v Speaker 2>browser as well. But it's also like a viscode on

323
00:20:22.279 --> 00:20:26.039
<v Speaker 2>the browser. So if you used to intelligence or something

324
00:20:26.119 --> 00:20:29.480
<v Speaker 2>like as of shortcuts and you need to set it up.

325
00:20:30.880 --> 00:20:35.079
<v Speaker 1>Okay, so let's say so, then so you've got your

326
00:20:35.240 --> 00:20:37.759
<v Speaker 1>bit component creer, you know of a header or a

327
00:20:37.759 --> 00:20:42.960
<v Speaker 1>button or something like that that you're using. I don't

328
00:20:42.960 --> 00:20:45.480
<v Speaker 1>know if this is something you can go into detail about,

329
00:20:45.480 --> 00:20:48.839
<v Speaker 1>but how is that implemented into my actual view app

330
00:20:49.000 --> 00:20:52.440
<v Speaker 1>or my React app or some on is this is

331
00:20:52.480 --> 00:20:56.319
<v Speaker 1>like an important statement you know in a component imported this,

332
00:20:56.480 --> 00:20:59.799
<v Speaker 1>but you're importing your bit component that and has everything,

333
00:21:00.440 --> 00:21:02.920
<v Speaker 1>or how is that implemented in your application?

334
00:21:03.720 --> 00:21:07.039
<v Speaker 2>So so behind the scene, bit can bit transforms any

335
00:21:07.039 --> 00:21:10.279
<v Speaker 2>component you have into a regular NPM package, so you

336
00:21:10.279 --> 00:21:13.640
<v Speaker 2>can just install it even even without installing BIT. You

337
00:21:13.680 --> 00:21:16.200
<v Speaker 2>can just install it with NPM like any other package

338
00:21:16.200 --> 00:21:21.559
<v Speaker 2>from NPMGS. And if you have and if you create

339
00:21:21.559 --> 00:21:23.759
<v Speaker 2>a work special, BIT works best. You can bring all

340
00:21:23.799 --> 00:21:26.559
<v Speaker 2>the components of any components you want and BIT will

341
00:21:26.599 --> 00:21:29.240
<v Speaker 2>know to kind of sim link it to the package

342
00:21:29.319 --> 00:21:31.759
<v Speaker 2>name behind the scene, so you have like you can

343
00:21:31.799 --> 00:21:35.480
<v Speaker 2>change the source code and it will reflect into your

344
00:21:36.079 --> 00:21:40.920
<v Speaker 2>consumer components that uses it. From the node models similar

345
00:21:41.000 --> 00:21:45.200
<v Speaker 2>to like monoiple tools like like NX or something like this.

346
00:21:45.559 --> 00:21:48.759
<v Speaker 2>BIT will do the the wiring from the node models

347
00:21:48.799 --> 00:21:53.400
<v Speaker 2>to your source code. If you're on an editing mode, okay.

348
00:21:53.000 --> 00:21:55.519
<v Speaker 1>But you're not using the main NPM repository right, this

349
00:21:55.599 --> 00:21:59.000
<v Speaker 1>is using your own BIT repository. You're just using the

350
00:21:59.079 --> 00:21:59.720
<v Speaker 1>NPM tool.

351
00:22:00.480 --> 00:22:02.880
<v Speaker 2>So we have we have like our registry on the

352
00:22:02.920 --> 00:22:05.480
<v Speaker 2>cloud that you can use or you can you can

353
00:22:05.599 --> 00:22:08.759
<v Speaker 2>use NPMGS or artifactory. We have guides for it. We

354
00:22:08.799 --> 00:22:11.640
<v Speaker 2>don't care if you're hosting the packages on our register

355
00:22:11.799 --> 00:22:16.000
<v Speaker 2>or other registry. So you can definitely do this. And

356
00:22:16.119 --> 00:22:19.000
<v Speaker 2>behind the scene for client and installation and everything, we're

357
00:22:19.079 --> 00:22:23.880
<v Speaker 2>using pm PM. Sultan, the creator of pn PM, is

358
00:22:23.920 --> 00:22:27.359
<v Speaker 2>part of the company, is full time employee in Beat

359
00:22:27.880 --> 00:22:30.920
<v Speaker 2>and so we are kind of maintaining pn PM as

360
00:22:30.960 --> 00:22:35.799
<v Speaker 2>well as a company. So we have Sultan for pn PM,

361
00:22:35.880 --> 00:22:38.599
<v Speaker 2>and we have jj who is part of the View

362
00:22:38.640 --> 00:22:42.200
<v Speaker 2>gs code team working on all the view integration. And

363
00:22:42.279 --> 00:22:45.279
<v Speaker 2>we have Olivier which was part of the Angular core

364
00:22:45.359 --> 00:22:49.519
<v Speaker 2>team working on all the Angular integration. So we have

365
00:22:49.640 --> 00:22:51.960
<v Speaker 2>like kind of nice team here.

366
00:22:53.079 --> 00:22:56.839
<v Speaker 1>Wow heavy hitters. Okay, excuse me. Now in terms of

367
00:22:56.880 --> 00:23:00.200
<v Speaker 1>hosting before we move into the AI, so is this

368
00:23:00.279 --> 00:23:02.759
<v Speaker 1>something you can self host if you want to sell

369
00:23:02.880 --> 00:23:04.960
<v Speaker 1>host bit or you can host in the bit cloud.

370
00:23:05.039 --> 00:23:08.880
<v Speaker 2>Is that correct? So we have like the SaaS product

371
00:23:09.400 --> 00:23:13.480
<v Speaker 2>and you can we also have we offer different different

372
00:23:13.799 --> 00:23:18.079
<v Speaker 2>ways to host, like the remote server, so either our

373
00:23:18.200 --> 00:23:23.480
<v Speaker 2>SaaS platform, we have a way to manage a dedicated

374
00:23:23.519 --> 00:23:26.599
<v Speaker 2>server for you as a company, and we have like

375
00:23:27.039 --> 00:23:31.240
<v Speaker 2>a full on prem solution. And also we have like

376
00:23:31.400 --> 00:23:34.680
<v Speaker 2>part of our open source is a simplified version of

377
00:23:34.720 --> 00:23:37.839
<v Speaker 2>the austing platform, so you can even do sell host

378
00:23:38.599 --> 00:23:43.000
<v Speaker 2>without bit cloud and host like remote bit server so

379
00:23:43.039 --> 00:23:46.400
<v Speaker 2>you can export components into it and see them. But

380
00:23:46.559 --> 00:23:50.519
<v Speaker 2>this will not have like many features like the AI,

381
00:23:51.039 --> 00:23:54.440
<v Speaker 2>the cloud walk space, the CI that we described before,

382
00:23:55.319 --> 00:23:59.319
<v Speaker 2>permission stuff like all the enterprise feature like SSL permissions

383
00:23:59.720 --> 00:24:02.480
<v Speaker 2>or not part of the open source. But there are

384
00:24:02.559 --> 00:24:05.759
<v Speaker 2>companies we are doing sellf host and and it's enough

385
00:24:05.759 --> 00:24:08.440
<v Speaker 2>for them.

386
00:24:08.480 --> 00:24:11.720
<v Speaker 1>Okay, all right, So that's the platform as a whole.

387
00:24:11.799 --> 00:24:15.640
<v Speaker 1>So let's talk about AI. So if I understand correctly,

388
00:24:15.720 --> 00:24:18.920
<v Speaker 1>So you've got your base platform that we just talked about,

389
00:24:19.640 --> 00:24:22.200
<v Speaker 1>that's installed. So now you're adding AI on top of

390
00:24:22.240 --> 00:24:25.160
<v Speaker 1>that or integrating AI into it as a sort of

391
00:24:25.200 --> 00:24:25.759
<v Speaker 1>a second phase.

392
00:24:25.880 --> 00:24:29.640
<v Speaker 2>Is that correct? Yes? So basically, if you look on

393
00:24:30.279 --> 00:24:33.799
<v Speaker 2>all thee itols today for developers, okay, o AI. In

394
00:24:33.839 --> 00:24:36.400
<v Speaker 2>this context of AI FO code generation. I'm not talking

395
00:24:36.440 --> 00:24:41.799
<v Speaker 2>about image generation, video generation, but on e itols today

396
00:24:42.440 --> 00:24:47.680
<v Speaker 2>are are splitting into kind of let's say, two families. Okay,

397
00:24:47.920 --> 00:24:52.680
<v Speaker 2>if you think about like let's talk kind of the child,

398
00:24:52.680 --> 00:24:55.480
<v Speaker 2>the simple child. And I know this is like voice only,

399
00:24:55.599 --> 00:24:58.039
<v Speaker 2>but it's it's an easy one which we have like

400
00:24:58.119 --> 00:25:01.000
<v Speaker 2>let's say on the y axis, we have the code size. Okay,

401
00:25:01.880 --> 00:25:06.880
<v Speaker 2>small code base or luge code base in this large

402
00:25:06.960 --> 00:25:10.720
<v Speaker 2>here I'm talking about like not not Google large, Okay,

403
00:25:11.079 --> 00:25:14.240
<v Speaker 2>even like a small startup like three four developers working

404
00:25:14.240 --> 00:25:18.839
<v Speaker 2>for year. It's kind of large like company code base.

405
00:25:19.039 --> 00:25:22.039
<v Speaker 2>And on the X axis you have like the complexity

406
00:25:22.079 --> 00:25:24.599
<v Speaker 2>of the task you ask from the AI from a

407
00:25:24.640 --> 00:25:29.400
<v Speaker 2>small snippet like a function to build me a real

408
00:25:29.440 --> 00:25:34.200
<v Speaker 2>feature on the right side, so only I todays today

409
00:25:34.279 --> 00:25:37.880
<v Speaker 2>are either good in it on one of these axes,

410
00:25:38.160 --> 00:25:41.319
<v Speaker 2>so you can either use tools like love a Bell,

411
00:25:41.559 --> 00:25:45.240
<v Speaker 2>Bold wind self many of them. Probably during other sessions

412
00:25:45.240 --> 00:25:49.079
<v Speaker 2>there will be a new one which can help you

413
00:25:49.480 --> 00:25:52.680
<v Speaker 2>build a full project from a prompt. If it's like

414
00:25:52.759 --> 00:25:56.079
<v Speaker 2>you know, a poc a side project you build in

415
00:25:56.119 --> 00:25:59.599
<v Speaker 2>the weekend, and the I would do pretty good job

416
00:26:00.000 --> 00:26:03.799
<v Speaker 2>building this initial version for you for a hobby project.

417
00:26:04.319 --> 00:26:06.799
<v Speaker 2>On the other side, we have tools that are more

418
00:26:06.839 --> 00:26:12.160
<v Speaker 2>for organization or existing code bases, which are help you

419
00:26:12.559 --> 00:26:15.359
<v Speaker 2>like caresee or get up co pilot which help you

420
00:26:15.799 --> 00:26:20.079
<v Speaker 2>to do some autocomplete or snippets for existing code base,

421
00:26:20.160 --> 00:26:23.960
<v Speaker 2>which is great, okay exist in case productivity. It saved

422
00:26:23.960 --> 00:26:27.759
<v Speaker 2>time from you know, googling and copy paste from stack overflow,

423
00:26:27.799 --> 00:26:30.960
<v Speaker 2>which is amazing. But what we really want to do

424
00:26:31.440 --> 00:26:34.920
<v Speaker 2>and no way I can do today is build real

425
00:26:34.960 --> 00:26:38.920
<v Speaker 2>features for real code based for organization code based. If

426
00:26:38.920 --> 00:26:41.480
<v Speaker 2>you're trying to take now new product, no matter which

427
00:26:41.480 --> 00:26:44.440
<v Speaker 2>company you're working on, and you will ask a co

428
00:26:44.599 --> 00:26:49.240
<v Speaker 2>pilot adding analytics features to my product, it will not

429
00:26:49.359 --> 00:26:52.200
<v Speaker 2>work at all, Like you cannot. There is no even

430
00:26:52.200 --> 00:26:57.839
<v Speaker 2>point to try it because it's not there yet. And

431
00:26:58.400 --> 00:27:00.880
<v Speaker 2>the reason it's not there yet it's because we are

432
00:27:01.319 --> 00:27:04.680
<v Speaker 2>looking at AI and we are asking AI. We are

433
00:27:04.880 --> 00:27:08.200
<v Speaker 2>using using AI in the wrong way, not using by

434
00:27:08.240 --> 00:27:12.359
<v Speaker 2>the end user, using by the AI developers, like the

435
00:27:12.400 --> 00:27:16.000
<v Speaker 2>people who develop these tools. We're doing it, I think

436
00:27:16.000 --> 00:27:19.680
<v Speaker 2>in the wrong way. We are trying to teach the

437
00:27:19.720 --> 00:27:22.559
<v Speaker 2>AI to read code and ask it to write code.

438
00:27:22.839 --> 00:27:25.359
<v Speaker 2>It's like you know, it's like you know to read books,

439
00:27:25.640 --> 00:27:27.799
<v Speaker 2>but do you know to write a best seller? Best seller?

440
00:27:28.359 --> 00:27:33.599
<v Speaker 2>Probably no, It's different stuff, and we think that you

441
00:27:33.759 --> 00:27:35.880
<v Speaker 2>need to change. We need to change. And in steath

442
00:27:36.319 --> 00:27:38.839
<v Speaker 2>asking the I to write code, we need to ask

443
00:27:38.920 --> 00:27:42.400
<v Speaker 2>the I to play lego. Okay, not just a general lego.

444
00:27:42.519 --> 00:27:45.200
<v Speaker 2>We need to play your lego, your lego bricks. It

445
00:27:45.240 --> 00:27:50.279
<v Speaker 2>needs to do composition. In stealth generation, generation of code

446
00:27:50.680 --> 00:27:55.480
<v Speaker 2>is just the last step in the process of building software. Right,

447
00:27:55.559 --> 00:28:00.440
<v Speaker 2>we are not getting paid by writing lines of code rights,

448
00:28:00.480 --> 00:28:03.000
<v Speaker 2>getting more money if he write small lines of code,

449
00:28:03.480 --> 00:28:07.480
<v Speaker 2>even the opposite. Usually we are our task is not

450
00:28:08.039 --> 00:28:10.839
<v Speaker 2>to build code to write code. Our task is to

451
00:28:10.839 --> 00:28:16.200
<v Speaker 2>build features for our software. And we and with AI

452
00:28:16.319 --> 00:28:19.440
<v Speaker 2>we kind of moving backward. We are asking you to

453
00:28:19.599 --> 00:28:22.519
<v Speaker 2>just write code every time from a clean slate. So

454
00:28:22.559 --> 00:28:26.000
<v Speaker 2>what happens is that the E is duplicating God again

455
00:28:26.000 --> 00:28:28.799
<v Speaker 2>and again. You ask it for something today, it will

456
00:28:28.799 --> 00:28:31.799
<v Speaker 2>generate a button. Tomorrow, you ask something else, it will

457
00:28:31.839 --> 00:28:35.720
<v Speaker 2>generate another button, and the day after. So if you

458
00:28:35.759 --> 00:28:38.799
<v Speaker 2>do it for some time, you will get such inflation

459
00:28:38.880 --> 00:28:43.119
<v Speaker 2>in a code base that you cannot maintain it anymore

460
00:28:43.119 --> 00:28:47.279
<v Speaker 2>as a human developers, because it will go from I

461
00:28:47.279 --> 00:28:49.640
<v Speaker 2>don't know ten times lines of code to a million

462
00:28:49.640 --> 00:28:51.000
<v Speaker 2>lines of code if you just do it for a

463
00:28:51.079 --> 00:28:55.200
<v Speaker 2>month with few developers. And this is one of the

464
00:28:55.240 --> 00:28:59.240
<v Speaker 2>major blockers from really making a I use the BELL

465
00:29:00.039 --> 00:29:07.559
<v Speaker 2>for organizations enterprises because of this, and and what we

466
00:29:07.640 --> 00:29:11.480
<v Speaker 2>are doing is we are changing it from the base.

467
00:29:12.039 --> 00:29:16.599
<v Speaker 2>We are giving the AI your dependency graph. Like I said,

468
00:29:16.640 --> 00:29:19.640
<v Speaker 2>we have big components, we have the graph, we have

469
00:29:19.680 --> 00:29:24.400
<v Speaker 2>the relationship in a structured way, and we ask the AI.

470
00:29:24.440 --> 00:29:27.640
<v Speaker 2>When you ask the OURI to build a feature. His

471
00:29:27.880 --> 00:29:33.559
<v Speaker 2>task internally is to see and which nodes in the

472
00:29:33.640 --> 00:29:37.319
<v Speaker 2>graph he needs to add, or to modify or to

473
00:29:37.400 --> 00:29:41.599
<v Speaker 2>reuse in order to implement this feature. So it's all

474
00:29:41.640 --> 00:29:52.440
<v Speaker 2>the time work and prioritizing reuse other than generation. Okay.

475
00:29:52.160 --> 00:29:57.519
<v Speaker 2>So for example, if we take like an example flow

476
00:29:57.720 --> 00:29:59.519
<v Speaker 2>of how it looks like text, a U ask for

477
00:29:59.640 --> 00:30:02.319
<v Speaker 2>AI to generate a header. I need a header, a

478
00:30:02.319 --> 00:30:06.319
<v Speaker 2>new header for my company what it What will happen

479
00:30:06.359 --> 00:30:08.920
<v Speaker 2>is that I will go to the graph search for header.

480
00:30:09.920 --> 00:30:12.680
<v Speaker 2>It will not find any header. It will. We will

481
00:30:12.720 --> 00:30:18.000
<v Speaker 2>ask the I to generate a potential dependency graph of

482
00:30:18.079 --> 00:30:24.279
<v Speaker 2>header okay, stuff like logo, avatar, search box, menu okay,

483
00:30:25.119 --> 00:30:28.240
<v Speaker 2>and then the I will reclusively do the same. It

484
00:30:28.319 --> 00:30:31.240
<v Speaker 2>will go and search for logo if it found it,

485
00:30:31.240 --> 00:30:33.960
<v Speaker 2>it will use it. If it found it and it

486
00:30:34.039 --> 00:30:37.759
<v Speaker 2>needs modification like a new API to be in the

487
00:30:37.799 --> 00:30:40.640
<v Speaker 2>context of header, it will add a new API to

488
00:30:40.720 --> 00:30:44.759
<v Speaker 2>the existing logo or to existing search box. If it

489
00:30:44.960 --> 00:30:47.839
<v Speaker 2>cannot find it, let's say it didn't find search box,

490
00:30:48.279 --> 00:30:51.279
<v Speaker 2>it will again build a virtual graph of search box.

491
00:30:51.920 --> 00:30:54.599
<v Speaker 2>Will understand that search box is built from I don't

492
00:30:54.640 --> 00:30:57.200
<v Speaker 2>know an input and the button, and then it will

493
00:30:57.240 --> 00:30:59.880
<v Speaker 2>search for input and a button a new company and

494
00:31:00.079 --> 00:31:05.039
<v Speaker 2>will use them. Once you use them or generate them,

495
00:31:05.519 --> 00:31:07.880
<v Speaker 2>it will move up one level above. And now we

496
00:31:07.920 --> 00:31:11.319
<v Speaker 2>can generate the search box from the input and the button,

497
00:31:11.880 --> 00:31:15.279
<v Speaker 2>and then after we get all the dependencies of the header,

498
00:31:15.640 --> 00:31:18.759
<v Speaker 2>it will generate the header from all of this. And

499
00:31:19.839 --> 00:31:29.440
<v Speaker 2>this this concept implement few very important principles in order

500
00:31:29.480 --> 00:31:34.519
<v Speaker 2>to make AI work for enterprises. Okay, so.

501
00:31:35.960 --> 00:31:38.920
<v Speaker 1>Okay, So let's step back for a minute. So I

502
00:31:38.960 --> 00:31:41.480
<v Speaker 1>think I understand what you're saying in that. You know,

503
00:31:42.559 --> 00:31:45.799
<v Speaker 1>even for a developer coming into a new application, you

504
00:31:45.839 --> 00:31:48.039
<v Speaker 1>can't just say, okay, they one, okay, go write this

505
00:31:48.119 --> 00:31:51.119
<v Speaker 1>feature without understanding the underlying application.

506
00:31:51.279 --> 00:31:51.400
<v Speaker 2>Right.

507
00:31:51.440 --> 00:31:53.519
<v Speaker 1>You got to know how it's built, how it's worked.

508
00:31:53.559 --> 00:31:55.839
<v Speaker 1>There's you can have a view component, but you could

509
00:31:55.880 --> 00:31:58.759
<v Speaker 1>have a bazillion different ways that your view component is

510
00:31:58.759 --> 00:32:01.240
<v Speaker 1>is written. Right, you need to know how your app

511
00:32:01.319 --> 00:32:03.880
<v Speaker 1>uses it, how your company uses it. So that leads

512
00:32:03.920 --> 00:32:07.759
<v Speaker 1>me to this question, does does bit have to be

513
00:32:07.799 --> 00:32:11.400
<v Speaker 1>implemented from the beginning of your application? In other words,

514
00:32:11.720 --> 00:32:14.519
<v Speaker 1>could I have a large view application that uses a

515
00:32:14.640 --> 00:32:17.519
<v Speaker 1>note on the back end. It's been up and running

516
00:32:17.559 --> 00:32:19.680
<v Speaker 1>for a while, and then I can I implement BIT

517
00:32:19.759 --> 00:32:23.240
<v Speaker 1>on top of that? Will that work or do BIT

518
00:32:23.359 --> 00:32:25.960
<v Speaker 1>need to be part of the structure, part of the

519
00:32:25.960 --> 00:32:28.599
<v Speaker 1>process from the very beginning in order for it to

520
00:32:30.000 --> 00:32:30.839
<v Speaker 1>work efficiently.

521
00:32:31.799 --> 00:32:35.480
<v Speaker 2>Okay, so of course if you already have BIT components,

522
00:32:35.519 --> 00:32:38.880
<v Speaker 2>it will be much easier for the I to to

523
00:32:38.920 --> 00:32:43.359
<v Speaker 2>do this because it can finally reuse what you have. Unfortunately,

524
00:32:43.440 --> 00:32:46.799
<v Speaker 2>most organizations have large code bases which don't use BIT

525
00:32:47.039 --> 00:32:51.359
<v Speaker 2>at the moment because they started a long time ago whatever.

526
00:32:52.680 --> 00:32:54.920
<v Speaker 2>So so usually what we see is like a kind

527
00:32:54.960 --> 00:32:58.720
<v Speaker 2>of a graduate graduate programs. So you ask AI to

528
00:32:58.759 --> 00:33:01.920
<v Speaker 2>build the new fictionals tomorrow, and as part of it,

529
00:33:02.519 --> 00:33:05.960
<v Speaker 2>the AI will create reusable components. Because the II will

530
00:33:06.039 --> 00:33:09.160
<v Speaker 2>create like, it will not just put terms of code

531
00:33:09.200 --> 00:33:12.920
<v Speaker 2>that implement an analytics stashboard. It if you ask it

532
00:33:12.960 --> 00:33:16.720
<v Speaker 2>for analytics stashboard, it will create components for a line chart,

533
00:33:16.799 --> 00:33:20.640
<v Speaker 2>and components for bou ch out, and components for card

534
00:33:21.039 --> 00:33:23.759
<v Speaker 2>that render a child and component for grid of card.

535
00:33:24.440 --> 00:33:26.839
<v Speaker 2>You will get like, I don't know, fifty components as

536
00:33:27.160 --> 00:33:31.480
<v Speaker 2>a result of this prompt, and these components are reusable components.

537
00:33:31.519 --> 00:33:34.480
<v Speaker 2>So now you can take these components and install them

538
00:33:34.839 --> 00:33:38.799
<v Speaker 2>on your existing code base, and then you can start

539
00:33:38.839 --> 00:33:44.240
<v Speaker 2>removing like you not componentize code base, and you can

540
00:33:44.400 --> 00:33:48.799
<v Speaker 2>like modernize its architecture. You are always thinking about how

541
00:33:48.880 --> 00:33:54.160
<v Speaker 2>to architecture, how to architect the features and the relationship

542
00:33:54.240 --> 00:33:57.599
<v Speaker 2>between the components. And then you can also use this

543
00:33:57.839 --> 00:34:01.079
<v Speaker 2>AI output to to kind of like eating the legacy

544
00:34:01.119 --> 00:34:03.880
<v Speaker 2>piece by piece. Tomorrow you will have another feature you

545
00:34:03.920 --> 00:34:08.039
<v Speaker 2>will get It will recognize the fifty components for yesterday,

546
00:34:08.280 --> 00:34:11.599
<v Speaker 2>it will generate twenty new ones, and then you can

547
00:34:11.679 --> 00:34:15.000
<v Speaker 2>use them in the legacy. So after some time, your

548
00:34:15.320 --> 00:34:20.719
<v Speaker 2>existing codebase will become will become modular. Okay, So even

549
00:34:20.760 --> 00:34:23.559
<v Speaker 2>regardless of the AI. Okay, even if you at this

550
00:34:23.639 --> 00:34:26.840
<v Speaker 2>point you're just not using the AI anymore, your code

551
00:34:26.880 --> 00:34:30.639
<v Speaker 2>base is now much more modular and much more clear

552
00:34:30.679 --> 00:34:35.079
<v Speaker 2>to understand, much more clear and easy to extend and

553
00:34:35.159 --> 00:34:43.599
<v Speaker 2>maintain because the clear components and boundaries that composing your application.

554
00:34:44.800 --> 00:34:48.800
<v Speaker 1>Okay. So I so if I'm an existing large enterprise application,

555
00:34:48.960 --> 00:34:51.840
<v Speaker 1>right and I bring in in it, I've been around

556
00:34:51.840 --> 00:34:54.760
<v Speaker 1>for two or three years, ten years, whatever, Right, So

557
00:34:54.800 --> 00:34:59.280
<v Speaker 1>I'm going to implement bits. So that's a manual process

558
00:34:59.280 --> 00:35:01.360
<v Speaker 1>to go through and GA rate all your bit components.

559
00:35:01.400 --> 00:35:03.519
<v Speaker 1>It's not something that did this automatically, right, You need

560
00:35:03.559 --> 00:35:05.239
<v Speaker 1>to go, okay, I need to create a bad component

561
00:35:05.280 --> 00:35:06.880
<v Speaker 1>for this, and a bit component for this and a

562
00:35:06.920 --> 00:35:07.880
<v Speaker 1>bit component for this.

563
00:35:07.960 --> 00:35:12.239
<v Speaker 2>Is that right? Yes, So we we know to help organizations,

564
00:35:12.800 --> 00:35:16.719
<v Speaker 2>especially loge organizations, to do this process with us together

565
00:35:17.119 --> 00:35:21.159
<v Speaker 2>and help them to like better like internal tools to

566
00:35:21.320 --> 00:35:24.599
<v Speaker 2>kind of spitting it up, not in THEI tools at

567
00:35:24.599 --> 00:35:27.039
<v Speaker 2>the moment they're doing it, but for example, a bit

568
00:35:27.159 --> 00:35:30.480
<v Speaker 2>note to take like a folder which like twenty subfolders

569
00:35:30.840 --> 00:35:34.360
<v Speaker 2>and in one line can make them twenty components. Okay,

570
00:35:35.000 --> 00:35:38.159
<v Speaker 2>So of course it depends on how you existing products

571
00:35:38.239 --> 00:35:42.159
<v Speaker 2>is structured at the moment, but you can do this migration.

572
00:35:42.320 --> 00:35:46.840
<v Speaker 2>It's not that long to do sometimes, and I believe

573
00:35:46.960 --> 00:35:50.360
<v Speaker 2>soon we will start working on some AI features that

574
00:35:50.480 --> 00:35:53.679
<v Speaker 2>will help you take existing code based and kind of

575
00:35:53.719 --> 00:35:57.639
<v Speaker 2>componentize it. This is something that we don't yet provide

576
00:35:57.679 --> 00:36:00.480
<v Speaker 2>at the moment, but we do help and we do

577
00:36:00.679 --> 00:36:07.119
<v Speaker 2>this process of componentizing projects with many organizations, very loud organizations,

578
00:36:07.679 --> 00:36:11.519
<v Speaker 2>even before AI starts and AI going to the mixed

579
00:36:11.719 --> 00:36:13.760
<v Speaker 2>because there is a lot of value of doing it

580
00:36:14.159 --> 00:36:20.559
<v Speaker 2>regardless of AI. So you're already doing it for many organizations.

581
00:36:21.280 --> 00:36:24.199
<v Speaker 1>Yeah, that would that considering that you know, like you said,

582
00:36:24.239 --> 00:36:26.000
<v Speaker 1>you have to build a structure from the ground up,

583
00:36:26.000 --> 00:36:29.119
<v Speaker 1>it would seem like that would be the primary benefit

584
00:36:29.119 --> 00:36:32.000
<v Speaker 1>of AI is to be able to componentize your existing

585
00:36:32.039 --> 00:36:35.960
<v Speaker 1>application right, so that you have bit components right, and

586
00:36:36.000 --> 00:36:38.840
<v Speaker 1>then from there, once it's componentized and AI has that

587
00:36:38.920 --> 00:36:41.480
<v Speaker 1>information stored, then you can use it to start generating

588
00:36:41.480 --> 00:36:44.159
<v Speaker 1>new features because it has the knowledge of your code

589
00:36:44.159 --> 00:36:45.800
<v Speaker 1>base right exactly.

590
00:36:45.920 --> 00:36:48.280
<v Speaker 2>Then if you start from stretch now with the II

591
00:36:48.440 --> 00:36:53.440
<v Speaker 2>that knows to build correct architecture, then you're kind of

592
00:36:53.480 --> 00:36:57.960
<v Speaker 2>flipping the equition. So if you're using most tools of

593
00:36:57.960 --> 00:37:00.599
<v Speaker 2>the I today, you will get like the inflation effected

594
00:37:00.639 --> 00:37:03.559
<v Speaker 2>we discussed, like, you'll get duplications again and again. You'll

595
00:37:03.599 --> 00:37:07.000
<v Speaker 2>get after a week, you will have fifty buttons. What

596
00:37:07.119 --> 00:37:10.519
<v Speaker 2>will happen with with our AI is that you're building

597
00:37:10.719 --> 00:37:13.440
<v Speaker 2>these lego pieces again and again. So the I in

598
00:37:13.480 --> 00:37:16.639
<v Speaker 2>a week from now will be much more powerful because

599
00:37:16.639 --> 00:37:19.119
<v Speaker 2>you have already a week like kind of compounding effect

600
00:37:19.239 --> 00:37:23.400
<v Speaker 2>like a Fibonacci. The I today is equal TODAI yesterday

601
00:37:23.440 --> 00:37:26.280
<v Speaker 2>plus d I two days ago because it uses the

602
00:37:26.320 --> 00:37:29.559
<v Speaker 2>components from yesterday and two days ago. So now it

603
00:37:29.599 --> 00:37:33.519
<v Speaker 2>can build better feature and faster because it's already had

604
00:37:33.599 --> 00:37:36.920
<v Speaker 2>the lego bricks. So like like as a human developer, Okay,

605
00:37:36.920 --> 00:37:39.920
<v Speaker 2>if you have a good building blocks the human developers

606
00:37:39.920 --> 00:37:41.760
<v Speaker 2>and you need to build a new feature, you will

607
00:37:41.800 --> 00:37:45.159
<v Speaker 2>did quickly and the II will do the same. It's

608
00:37:45.199 --> 00:37:47.840
<v Speaker 2>not only about building, it's also about like the quality.

609
00:37:48.239 --> 00:37:51.760
<v Speaker 2>So for example AI today is one of the main

610
00:37:51.840 --> 00:37:55.079
<v Speaker 2>issues is the code quality. Like a I needs to

611
00:37:55.119 --> 00:37:58.559
<v Speaker 2>write test, but you know it puts like you ask

612
00:37:58.639 --> 00:38:02.239
<v Speaker 2>for a feature, it wrote you ten like thousand lines

613
00:38:02.280 --> 00:38:05.760
<v Speaker 2>of code and you can test it. It's it's how

614
00:38:05.880 --> 00:38:09.280
<v Speaker 2>task for human also for AI. But if you take

615
00:38:09.320 --> 00:38:13.039
<v Speaker 2>this and break it into fifty components, each one is small,

616
00:38:13.480 --> 00:38:16.239
<v Speaker 2>it's focused, it's reusable, and then you ask the I

617
00:38:16.400 --> 00:38:19.280
<v Speaker 2>to build test for each one of these, it will

618
00:38:19.320 --> 00:38:22.920
<v Speaker 2>do much better job because it's much easier for human

619
00:38:23.000 --> 00:38:25.239
<v Speaker 2>and for AI to write test for a small components.

620
00:38:26.840 --> 00:38:29.719
<v Speaker 2>Then you when you combine this also with like the

621
00:38:30.800 --> 00:38:37.320
<v Speaker 2>bit infrastructures and the bit CI which knows to add

622
00:38:37.480 --> 00:38:41.360
<v Speaker 2>meta data and to standardize this built pipeline for each

623
00:38:41.400 --> 00:38:45.440
<v Speaker 2>component individually, then eventually what you get. And this is

624
00:38:45.440 --> 00:38:49.199
<v Speaker 2>not fully fully implemented at the moment like partially yeah,

625
00:38:49.840 --> 00:38:52.719
<v Speaker 2>but will be soon. Think about this today you are

626
00:38:52.719 --> 00:38:56.119
<v Speaker 2>getting code from there. You asked, you get pumped. I

627
00:38:56.199 --> 00:38:58.440
<v Speaker 2>give you tons of code. Now what you're doing, okay,

628
00:38:58.519 --> 00:39:01.000
<v Speaker 2>Like after the l lamp out, you have like a

629
00:39:01.159 --> 00:39:06.280
<v Speaker 2>very long manual process of integration. You need to rename it,

630
00:39:06.400 --> 00:39:09.440
<v Speaker 2>you need to put it and move stuff around, and

631
00:39:09.480 --> 00:39:12.199
<v Speaker 2>then you need to start review it and start testing it.

632
00:39:12.280 --> 00:39:14.880
<v Speaker 2>You need to make I don't know, a pull request,

633
00:39:15.000 --> 00:39:19.639
<v Speaker 2>so it depends on like on your existing CI and tooling,

634
00:39:20.079 --> 00:39:24.119
<v Speaker 2>which are not part of the AI. But tomorrow what

635
00:39:24.199 --> 00:39:28.079
<v Speaker 2>you can do is AI generate components the right test

636
00:39:28.119 --> 00:39:30.800
<v Speaker 2>for each component. We have the power to run the

637
00:39:30.840 --> 00:39:34.920
<v Speaker 2>test for all these components in parallel CD issues gives

638
00:39:34.960 --> 00:39:37.280
<v Speaker 2>them back to the AI. I will fix them, will

639
00:39:37.360 --> 00:39:40.079
<v Speaker 2>run them again. It runs fast because it's parallelized everything.

640
00:39:40.639 --> 00:39:45.599
<v Speaker 2>And then the linking, the linking configuration or the formatting

641
00:39:45.599 --> 00:39:49.840
<v Speaker 2>configuration is also part of the meta data. So AI

642
00:39:49.960 --> 00:39:53.920
<v Speaker 2>is started doing review to itself, getting issues, fix them,

643
00:39:53.920 --> 00:39:56.559
<v Speaker 2>getting issues, fix them. And when you as a human

644
00:39:56.639 --> 00:39:59.440
<v Speaker 2>get the code, it's already being reviewed by the AI

645
00:39:59.559 --> 00:40:02.800
<v Speaker 2>and fixed five times. So now the show now that

646
00:40:03.079 --> 00:40:08.519
<v Speaker 2>the path from this point to use it, it's much easier.

647
00:40:08.559 --> 00:40:13.960
<v Speaker 2>It's already in much better quality than today because of

648
00:40:14.000 --> 00:40:14.519
<v Speaker 2>this process.

649
00:40:15.440 --> 00:40:18.360
<v Speaker 1>Okay, I would imagine you still want a human to

650
00:40:18.440 --> 00:40:22.079
<v Speaker 1>review it, though, I mean AI is only effective as

651
00:40:22.599 --> 00:40:24.760
<v Speaker 1>how well it's created. You know, good stuff in, good

652
00:40:24.800 --> 00:40:27.880
<v Speaker 1>stuff out, garbage in, garbage out. So I know my

653
00:40:28.079 --> 00:40:30.239
<v Speaker 1>tendency is, as someone who does a lot of debop

654
00:40:30.280 --> 00:40:33.239
<v Speaker 1>stuff would be, I'd want to be eyeballing it as

655
00:40:33.239 --> 00:40:35.519
<v Speaker 1>a human, you know, have a human look at it

656
00:40:35.599 --> 00:40:38.119
<v Speaker 1>first before it's actually deployed. But I would assume that

657
00:40:38.280 --> 00:40:40.400
<v Speaker 1>you know, you could easily implement that as part of

658
00:40:40.440 --> 00:40:41.039
<v Speaker 1>your process.

659
00:40:41.079 --> 00:40:44.360
<v Speaker 2>Correct, Yes, so for sure you still need the human

660
00:40:45.079 --> 00:40:51.519
<v Speaker 2>equivalent review for sure. But the question is how how

661
00:40:51.639 --> 00:40:54.199
<v Speaker 2>how long did this human needs to to like how

662
00:40:54.280 --> 00:40:56.000
<v Speaker 2>much work you need to do, Like it gets like

663
00:40:56.000 --> 00:40:59.840
<v Speaker 2>a fifty percent or it gets like eight or ninety percent. Okay,

664
00:41:00.159 --> 00:41:03.119
<v Speaker 2>big difference, and we are trying, you know, we're not

665
00:41:03.480 --> 00:41:06.559
<v Speaker 2>at one hundred percent, probably will not be there anytime soon.

666
00:41:08.000 --> 00:41:11.119
<v Speaker 1>What in terms of test cabbaging quality, one.

667
00:41:11.559 --> 00:41:13.639
<v Speaker 2>Like that you can take the code of for the

668
00:41:13.719 --> 00:41:15.639
<v Speaker 2>I and not doing a review at all because it's

669
00:41:15.639 --> 00:41:20.920
<v Speaker 2>like perfect confidence, right Okay, yes, okay, so most of

670
00:41:20.920 --> 00:41:23.960
<v Speaker 2>AI today is give you like I don't know fifty percent,

671
00:41:24.280 --> 00:41:27.519
<v Speaker 2>and we're trying to give you like ninety percent, okay,

672
00:41:27.639 --> 00:41:29.599
<v Speaker 2>which is a lot of time and a lot oft

673
00:41:29.719 --> 00:41:33.519
<v Speaker 2>to say. And another thing that you described and it's

674
00:41:33.920 --> 00:41:37.760
<v Speaker 2>important and interesting is like the albage in garbage out okay.

675
00:41:38.599 --> 00:41:43.639
<v Speaker 2>Out of the main issues of how AI generating god

676
00:41:43.679 --> 00:41:46.280
<v Speaker 2>and the quality of the code even before like writing

677
00:41:46.400 --> 00:41:50.039
<v Speaker 2>tests and everything is like what you give the AI

678
00:41:50.079 --> 00:41:53.639
<v Speaker 2>as the input? Okay. And let's talk about like, let's

679
00:41:53.639 --> 00:41:58.719
<v Speaker 2>say three main principles of how the AI, what do

680
00:41:58.840 --> 00:42:02.519
<v Speaker 2>I get as an imput and how it uses it?

681
00:42:03.159 --> 00:42:07.079
<v Speaker 2>So the first principle is that we want a YI

682
00:42:07.800 --> 00:42:12.840
<v Speaker 2>to get an input a higher level, higher level of structure, okay,

683
00:42:13.119 --> 00:42:16.679
<v Speaker 2>like a composite instead of atom. A EI today is

684
00:42:16.719 --> 00:42:21.679
<v Speaker 2>walk with tokens. Right, they get like English or language tokens.

685
00:42:21.800 --> 00:42:24.599
<v Speaker 2>It can be like the world if or like four

686
00:42:25.119 --> 00:42:28.159
<v Speaker 2>and it knows like it equal signs or stuff like this.

687
00:42:29.159 --> 00:42:32.679
<v Speaker 2>But as a human, we don't read the code like this.

688
00:42:33.079 --> 00:42:37.280
<v Speaker 2>We have boundaries, right, we're working with higher structure. We

689
00:42:37.320 --> 00:42:43.599
<v Speaker 2>are working with business parts with features with product boundaries. Okay.

690
00:42:43.679 --> 00:42:47.199
<v Speaker 2>If we take an example from let's say you're looking

691
00:42:47.280 --> 00:42:50.280
<v Speaker 2>on a map. Okay, if AI look on this map,

692
00:42:51.000 --> 00:42:53.679
<v Speaker 2>you see like I don't know, pixels or mountains and

693
00:42:54.400 --> 00:42:57.480
<v Speaker 2>sand and water. If you look on the map, you

694
00:42:57.519 --> 00:43:00.440
<v Speaker 2>see countries, right, you see this in Spain. You know

695
00:43:00.559 --> 00:43:05.400
<v Speaker 2>that Spain has like different characters. And you see French

696
00:43:05.480 --> 00:43:08.320
<v Speaker 2>and you see like countries and each country has like

697
00:43:08.599 --> 00:43:13.480
<v Speaker 2>meaning with it. Okay. And this true not for not

698
00:43:13.519 --> 00:43:16.760
<v Speaker 2>only for code generation, for even for architecture. Right, we

699
00:43:16.800 --> 00:43:20.119
<v Speaker 2>have like templates that we combine together to build like

700
00:43:21.039 --> 00:43:26.840
<v Speaker 2>bigger structure. And we want the EI to understand not tokens,

701
00:43:26.880 --> 00:43:33.119
<v Speaker 2>but to get components with meaning instead of tokens. And

702
00:43:33.480 --> 00:43:38.559
<v Speaker 2>this is the first principles, Like components is better than tokens. Okay.

703
00:43:40.239 --> 00:43:46.199
<v Speaker 2>The second is what the EI can can see, which components,

704
00:43:46.280 --> 00:43:50.440
<v Speaker 2>which part of the code base it can see. For example,

705
00:43:51.000 --> 00:43:57.400
<v Speaker 2>the when we developers, let's let's think about like an

706
00:43:57.519 --> 00:44:00.760
<v Speaker 2>architect or like very productive developers in the company. Okay,

707
00:44:00.840 --> 00:44:04.360
<v Speaker 2>anyone knows someone like this, someone who is smart as

708
00:44:04.360 --> 00:44:07.960
<v Speaker 2>a general, who is very good on the tech on

709
00:44:08.039 --> 00:44:11.079
<v Speaker 2>the specific tech stack. Is like I don't know, great

710
00:44:11.199 --> 00:44:14.880
<v Speaker 2>view developers, a great no JS developer whatever. And the yie,

711
00:44:15.000 --> 00:44:18.360
<v Speaker 2>by the way, is smart and knows pretty much any

712
00:44:18.360 --> 00:44:23.199
<v Speaker 2>framework better than any human. Okay, but these developers also

713
00:44:23.239 --> 00:44:26.000
<v Speaker 2>have like a big advantage that he knows all the

714
00:44:26.039 --> 00:44:28.639
<v Speaker 2>code base in and out has been there from day one.

715
00:44:29.400 --> 00:44:33.159
<v Speaker 2>When he is trying to build a feature, then he

716
00:44:33.400 --> 00:44:38.159
<v Speaker 2>thinks about different stuff like what can I use where

717
00:44:38.239 --> 00:44:41.679
<v Speaker 2>is it? Who can I discuss about how to use it?

718
00:44:42.119 --> 00:44:44.880
<v Speaker 2>And is focusing like on the input statement and you

719
00:44:45.000 --> 00:44:49.320
<v Speaker 2>see the entire picture. He can go and open another repository, okay,

720
00:44:49.400 --> 00:44:51.920
<v Speaker 2>or the Becket repository. It can open like the Design

721
00:44:51.920 --> 00:44:55.400
<v Speaker 2>System repository. But what we do is a YI is

722
00:44:55.440 --> 00:44:59.159
<v Speaker 2>we give it a very small context. And why we

723
00:44:59.199 --> 00:45:02.280
<v Speaker 2>give it a small gold because because of different stuff.

724
00:45:02.400 --> 00:45:06.079
<v Speaker 2>One is the window size. Okay, we cannot We are

725
00:45:06.719 --> 00:45:11.079
<v Speaker 2>technical limitation with AI about how many code you can read.

726
00:45:11.360 --> 00:45:14.760
<v Speaker 2>This is one issue and it's improved all the time. Okay.

727
00:45:15.840 --> 00:45:20.239
<v Speaker 2>The second issue is availability. Okay, maybe today tomorrow AI

728
00:45:20.360 --> 00:45:23.039
<v Speaker 2>can read like a full rippo. But what if our

729
00:45:23.559 --> 00:45:25.840
<v Speaker 2>implementation is on a different repot. We have a font

730
00:45:25.880 --> 00:45:28.880
<v Speaker 2>and ripple and the bacon ripple. AI now to need

731
00:45:28.920 --> 00:45:31.159
<v Speaker 2>to build a feature on the front end that uses

732
00:45:31.199 --> 00:45:33.639
<v Speaker 2>the back and API. Even if you can read the

733
00:45:33.840 --> 00:45:36.679
<v Speaker 2>entire ripple of the front end. The back end is

734
00:45:36.719 --> 00:45:39.639
<v Speaker 2>a different place. You cannot read it. You cannot read

735
00:45:39.639 --> 00:45:44.320
<v Speaker 2>the design system REPO. So the availability is also a problem.

736
00:45:44.679 --> 00:45:46.719
<v Speaker 2>What we want to do is to give the AI

737
00:45:47.239 --> 00:45:51.360
<v Speaker 2>like holistic visibility. We want to give the EI the

738
00:45:51.400 --> 00:45:55.159
<v Speaker 2>power to see the entire code base. And the way

739
00:45:55.239 --> 00:45:58.159
<v Speaker 2>we do it is by we are taking these components,

740
00:45:58.519 --> 00:46:01.599
<v Speaker 2>no matter which report it to is they are coming from.

741
00:46:02.239 --> 00:46:05.400
<v Speaker 2>We model them as a graph. So we have the

742
00:46:05.599 --> 00:46:08.239
<v Speaker 2>notes which is components with the meta data and we

743
00:46:08.280 --> 00:46:11.159
<v Speaker 2>don't even need implementation. We will discuss it in a second.

744
00:46:11.440 --> 00:46:13.400
<v Speaker 2>And we have made a data on the relationship like

745
00:46:13.440 --> 00:46:16.800
<v Speaker 2>which API this component is using from a different component,

746
00:46:17.199 --> 00:46:19.280
<v Speaker 2>how they are connected, it's a dev dependency, it's a

747
00:46:19.320 --> 00:46:22.840
<v Speaker 2>random dependency, whatever, whatever. And we want to give the

748
00:46:22.880 --> 00:46:27.760
<v Speaker 2>AI this full picture and not only like asking him

749
00:46:27.800 --> 00:46:30.079
<v Speaker 2>to look under the lamp, because even if it's not

750
00:46:30.199 --> 00:46:32.760
<v Speaker 2>to reuse, if you don't have access to read this

751
00:46:33.360 --> 00:46:36.320
<v Speaker 2>relevant code base, we will not know how to reuse.

752
00:46:36.800 --> 00:46:39.599
<v Speaker 2>This is like the second principle is like relistic is

753
00:46:39.679 --> 00:46:42.000
<v Speaker 2>better than local. I think we want to give the

754
00:46:42.400 --> 00:46:47.400
<v Speaker 2>realistic view. And the third principle is we have this

755
00:46:47.599 --> 00:46:51.119
<v Speaker 2>race about like increasing the window side of the context

756
00:46:51.800 --> 00:46:54.920
<v Speaker 2>make it bigger, bigger, bigger. Great. But we all know

757
00:46:55.119 --> 00:47:01.679
<v Speaker 2>that if you put more context, which is context to

758
00:47:01.840 --> 00:47:05.360
<v Speaker 2>get wose results. Right, we don't want to give the

759
00:47:05.480 --> 00:47:09.679
<v Speaker 2>I all the context in the world because it will

760
00:47:09.719 --> 00:47:13.119
<v Speaker 2>confuse them. We want to give them only the relevant

761
00:47:13.119 --> 00:47:16.960
<v Speaker 2>and most important part. So the principle is about accurate

762
00:47:17.039 --> 00:47:23.280
<v Speaker 2>context is better than bigger context. Okay, And what we

763
00:47:23.360 --> 00:47:28.440
<v Speaker 2>do is we have this we have this graph, for example,

764
00:47:28.800 --> 00:47:32.679
<v Speaker 2>and then we ask the I to make a virtual

765
00:47:32.760 --> 00:47:36.239
<v Speaker 2>graph or potential graph, and then we go to the graph.

766
00:47:36.400 --> 00:47:38.920
<v Speaker 2>And before the II is not talking directly to the graph,

767
00:47:39.320 --> 00:47:43.199
<v Speaker 2>is going through a semantic search. And this semantic search

768
00:47:43.360 --> 00:47:46.960
<v Speaker 2>is looking for these specific components that might be related

769
00:47:47.440 --> 00:47:51.039
<v Speaker 2>and give only these components to THEI as like an input,

770
00:47:51.119 --> 00:47:53.880
<v Speaker 2>so we can read this API. And it also don't

771
00:47:53.920 --> 00:47:57.800
<v Speaker 2>contain the implementation because all the implementation of components. When

772
00:47:57.840 --> 00:48:00.880
<v Speaker 2>you try to build a new component, you don't care

773
00:48:01.400 --> 00:48:04.320
<v Speaker 2>about the implementation of the component you're using, right, You

774
00:48:04.400 --> 00:48:09.000
<v Speaker 2>only care about what it does, the description and the API,

775
00:48:09.559 --> 00:48:12.199
<v Speaker 2>like what is the public API this component? If I

776
00:48:12.320 --> 00:48:15.679
<v Speaker 2>give the AI all the full and if statement inside

777
00:48:15.719 --> 00:48:18.480
<v Speaker 2>of it, of the entire code base. First I will

778
00:48:18.519 --> 00:48:22.000
<v Speaker 2>get the context, window size issues, and second I will

779
00:48:22.119 --> 00:48:25.239
<v Speaker 2>just put a lot of not relevant information for him.

780
00:48:25.639 --> 00:48:28.679
<v Speaker 2>So what we do We provide the AI only with

781
00:48:28.719 --> 00:48:33.239
<v Speaker 2>the signatures, with the description, with the labels for example.

782
00:48:33.760 --> 00:48:36.480
<v Speaker 2>So then we can give the I much better and

783
00:48:36.519 --> 00:48:39.480
<v Speaker 2>we filter it only the relevant component. So we give

784
00:48:39.519 --> 00:48:43.480
<v Speaker 2>the EI an realistic view of everything it needs, but

785
00:48:43.679 --> 00:48:48.519
<v Speaker 2>only the necessary information of each of it. So the

786
00:48:48.559 --> 00:48:51.320
<v Speaker 2>results you get are much higher quality.

787
00:48:52.840 --> 00:48:57.400
<v Speaker 1>Yes, I think you can shorten that to quality or quantity. Yeah,

788
00:48:57.599 --> 00:49:01.039
<v Speaker 1>you only want a good step and not everything. Okay,

789
00:49:01.079 --> 00:49:04.000
<v Speaker 1>So last question list that I can think of, is

790
00:49:04.039 --> 00:49:07.719
<v Speaker 1>your LLLM, your models that you're using. What are you

791
00:49:07.800 --> 00:49:11.280
<v Speaker 1>using your own lll ms, are using chat, GPT four,

792
00:49:11.480 --> 00:49:14.800
<v Speaker 1>chat gpt zer A one or a cloud or what

793
00:49:14.840 --> 00:49:17.360
<v Speaker 1>are you using for your l models?

794
00:49:17.639 --> 00:49:20.679
<v Speaker 2>Yes, so first we don't have our own LM our

795
00:49:20.760 --> 00:49:24.000
<v Speaker 2>own model we are using At the moment, we're using

796
00:49:24.480 --> 00:49:28.719
<v Speaker 2>Gemini two, but we're playing with it, so we're changing

797
00:49:28.719 --> 00:49:34.880
<v Speaker 2>it and test different models. What interesting is that if

798
00:49:34.920 --> 00:49:38.679
<v Speaker 2>you give the AIS today, all the models today the

799
00:49:38.800 --> 00:49:41.880
<v Speaker 2>correct and small task, they are doing a great job

800
00:49:42.079 --> 00:49:44.239
<v Speaker 2>any of them. If you're asking any of the models

801
00:49:44.239 --> 00:49:47.639
<v Speaker 2>no matter which one of them to build a cloud

802
00:49:47.639 --> 00:49:51.719
<v Speaker 2>component and react or in view, they will do great job. Today.

803
00:49:52.360 --> 00:49:55.400
<v Speaker 2>The problem is that we want we don't want to

804
00:49:55.960 --> 00:49:58.760
<v Speaker 2>ask them to build the car. We want them to

805
00:49:58.880 --> 00:50:01.960
<v Speaker 2>build the future. So what we do is we are

806
00:50:02.039 --> 00:50:04.480
<v Speaker 2>breaking it kind of like a kind of like an

807
00:50:04.519 --> 00:50:08.239
<v Speaker 2>agent method. It's like it's an engineering problem, not an

808
00:50:08.280 --> 00:50:13.039
<v Speaker 2>EI problem. We're asking thei AI, what components do you need?

809
00:50:13.559 --> 00:50:16.360
<v Speaker 2>Then for each one of these components were we're doing

810
00:50:16.400 --> 00:50:19.599
<v Speaker 2>some manipulations, and then we separate it, like if you

811
00:50:19.960 --> 00:50:24.079
<v Speaker 2>put one pompt asking for an application in our a GUI.

812
00:50:24.400 --> 00:50:26.840
<v Speaker 2>Behind the scenes, we will probably send like four hundred

813
00:50:26.920 --> 00:50:30.559
<v Speaker 2>prompts or something like this behind one prompt of yours

814
00:50:30.880 --> 00:50:33.480
<v Speaker 2>because we're splitting it and then you're splitting it again.

815
00:50:33.800 --> 00:50:35.840
<v Speaker 2>And then for each component, we're asking to build a

816
00:50:35.840 --> 00:50:40.119
<v Speaker 2>component to describe the responsibility and then to write test

817
00:50:40.159 --> 00:50:44.400
<v Speaker 2>for this components specifically. And then even with the existing

818
00:50:45.000 --> 00:50:50.559
<v Speaker 2>AI today, the existing NLMs, we get really really good components,

819
00:50:50.639 --> 00:50:55.559
<v Speaker 2>a component that probably built better than many human developers

820
00:50:55.599 --> 00:50:59.079
<v Speaker 2>will do, and then you can use it by AI

821
00:50:59.199 --> 00:51:02.159
<v Speaker 2>or by develop post tomorrow, combination of both of them.

822
00:51:02.199 --> 00:51:08.119
<v Speaker 1>Probably yeah, okay, yeah, that makes sense. That makes sense

823
00:51:08.159 --> 00:51:10.559
<v Speaker 1>for sure. All right, So before we move on the pics,

824
00:51:10.760 --> 00:51:12.599
<v Speaker 1>is there anything else you wanted to cover that we

825
00:51:12.960 --> 00:51:15.559
<v Speaker 1>regarding bit or AI that you want to talk about.

826
00:51:17.039 --> 00:51:21.480
<v Speaker 2>Just want to share that this AI is getting into

827
00:51:21.920 --> 00:51:25.559
<v Speaker 2>review version a few days ago at the moment with

828
00:51:25.679 --> 00:51:30.280
<v Speaker 2>recording recording today it's about ten I'm not sure when

829
00:51:30.280 --> 00:51:32.840
<v Speaker 2>we'll be released, but it's it's pretty new. Probably it

830
00:51:32.920 --> 00:51:36.840
<v Speaker 2>will be still pretty new when you tried, so feel

831
00:51:36.880 --> 00:51:39.079
<v Speaker 2>free to try it. It's like just go to bid

832
00:51:39.159 --> 00:51:43.199
<v Speaker 2>dot cloud and you can write a prompt. Keep in

833
00:51:43.199 --> 00:51:47.239
<v Speaker 2>mind that this is a different type of AI, like

834
00:51:47.920 --> 00:51:50.880
<v Speaker 2>the difference between writing a question to GPT or to

835
00:51:51.000 --> 00:51:55.440
<v Speaker 2>deep search to deep research, which takes an hour. It's

836
00:51:55.480 --> 00:51:59.679
<v Speaker 2>the same with our REI. It's breaking the problems sending

837
00:51:59.719 --> 00:52:03.840
<v Speaker 2>a lot of a lot of prompts. It takes some times.

838
00:52:04.360 --> 00:52:08.079
<v Speaker 2>So don't expect like a bold experience of after twenty

839
00:52:08.119 --> 00:52:12.159
<v Speaker 2>seconds you get something running. It's much bigger. And keep

840
00:52:12.199 --> 00:52:16.039
<v Speaker 2>in mind that in return you get like a platform

841
00:52:16.079 --> 00:52:19.400
<v Speaker 2>that is enterprise eddy. It build a real backoned by

842
00:52:19.400 --> 00:52:22.400
<v Speaker 2>the way, it's not like connecting to super base or

843
00:52:22.440 --> 00:52:25.400
<v Speaker 2>something like this like beacons for ward. It's building also

844
00:52:25.440 --> 00:52:29.840
<v Speaker 2>Bacon like real micro services, Real Express or grap cuel

845
00:52:30.599 --> 00:52:35.679
<v Speaker 2>micro services. It gives you test and connect everything together,

846
00:52:36.480 --> 00:52:38.559
<v Speaker 2>but it of course takes some time to generate and

847
00:52:38.599 --> 00:52:42.480
<v Speaker 2>it's probably won't walk out of the box on the field.

848
00:52:42.559 --> 00:52:45.440
<v Speaker 2>Try so you get like I don't know, seventy components.

849
00:52:45.880 --> 00:52:47.519
<v Speaker 2>Some of them will have some issues that we will

850
00:52:47.519 --> 00:52:50.880
<v Speaker 2>probably into ask AI to fix or manual fix them.

851
00:52:51.400 --> 00:52:55.199
<v Speaker 2>But after this process of one hour of generation and

852
00:52:55.480 --> 00:52:58.400
<v Speaker 2>one or two hours of fixing, you get something that

853
00:52:58.559 --> 00:53:02.239
<v Speaker 2>is really ready for for for scale and for using

854
00:53:02.440 --> 00:53:09.800
<v Speaker 2>in real organization. So just like expectations about what you

855
00:53:09.880 --> 00:53:13.760
<v Speaker 2>get and how it works, and don't expect the same

856
00:53:13.800 --> 00:53:16.960
<v Speaker 2>because it's not the same as other tools.

857
00:53:18.519 --> 00:53:23.440
<v Speaker 1>All right, all right, So we mentioned bit dot cloud

858
00:53:23.679 --> 00:53:27.840
<v Speaker 1>and bid dot dev as the websites to get more information.

859
00:53:27.960 --> 00:53:32.079
<v Speaker 1>Is there any other channels like x, Twitter, blue Sky

860
00:53:32.159 --> 00:53:32.719
<v Speaker 1>anything else?

861
00:53:32.760 --> 00:53:33.039
<v Speaker 2>Word?

862
00:53:33.559 --> 00:53:34.960
<v Speaker 1>Yes, people can follow you.

863
00:53:35.639 --> 00:53:38.559
<v Speaker 2>Yes, So first if you want to follow me or

864
00:53:38.639 --> 00:53:42.840
<v Speaker 2>talking to me directly, just go to gilad dot dev

865
00:53:42.880 --> 00:53:45.199
<v Speaker 2>gilad g I l A d dot dev. It's my

866
00:53:45.239 --> 00:53:49.199
<v Speaker 2>personal website. You can find many podcasts and talks and

867
00:53:49.239 --> 00:53:53.400
<v Speaker 2>whatever and all the socials, bitter linking whatever that you

868
00:53:53.400 --> 00:53:55.920
<v Speaker 2>can reach out to me if you want. Uh, if

869
00:53:55.960 --> 00:53:58.840
<v Speaker 2>you go to bit cloud, you'll find all the like

870
00:53:58.920 --> 00:54:02.760
<v Speaker 2>the socials of the comp and the our slick community

871
00:54:02.800 --> 00:54:05.440
<v Speaker 2>community slack that you can reach out to our team

872
00:54:05.880 --> 00:54:07.760
<v Speaker 2>and then talk to us if you have any questions

873
00:54:07.800 --> 00:54:10.800
<v Speaker 2>and stuff like this. Everything you can find on a

874
00:54:10.920 --> 00:54:16.639
<v Speaker 2>bit bit dev find all the communication each other with beat.

875
00:54:19.960 --> 00:54:23.199
<v Speaker 1>Alrighty sounds good. All right, well, thank you for coming

876
00:54:23.440 --> 00:54:26.599
<v Speaker 1>and enlightening. It's about bid and AI sounds like quite

877
00:54:26.639 --> 00:54:31.360
<v Speaker 1>the the tool for managing an enterprise size app. I

878
00:54:31.400 --> 00:54:33.400
<v Speaker 1>work in one every day, so I can appreciate how

879
00:54:34.119 --> 00:54:37.239
<v Speaker 1>nice that would be to have something like that. All right,

880
00:54:37.320 --> 00:54:39.119
<v Speaker 1>We'll move on to picks picks, the part of the

881
00:54:39.119 --> 00:54:42.239
<v Speaker 1>show where we get to talk about anything we want

882
00:54:42.280 --> 00:54:46.400
<v Speaker 1>to talk about. I'll go first and do you. I

883
00:54:46.440 --> 00:54:49.360
<v Speaker 1>don't really have anything other off topic other than I'm

884
00:54:49.360 --> 00:54:51.639
<v Speaker 1>in Arizona and I'm loving the warmth and sunshine as

885
00:54:51.719 --> 00:54:54.239
<v Speaker 1>compared to my Oregon where it's a little cooler and rainier.

886
00:54:54.280 --> 00:54:55.920
<v Speaker 1>So I'll do that for my pick of the day,

887
00:54:56.920 --> 00:55:00.039
<v Speaker 1>visiting my parents, and then we'll move on to the

888
00:55:00.079 --> 00:55:04.199
<v Speaker 1>dad jokes of the week. Yeah, my mind, the high

889
00:55:04.199 --> 00:55:06.920
<v Speaker 1>point of any podcast episode. But I might be alone

890
00:55:06.960 --> 00:55:10.360
<v Speaker 1>in thinking that, so start out, so my doctor. I

891
00:55:10.360 --> 00:55:11.840
<v Speaker 1>went and see my doctor the other day and he

892
00:55:11.880 --> 00:55:15.159
<v Speaker 1>only gave me six months to live, so I shot him,

893
00:55:15.159 --> 00:55:16.519
<v Speaker 1>and the judge gave me twenty years.

894
00:55:18.760 --> 00:55:18.960
<v Speaker 2>Nice.

895
00:55:20.440 --> 00:55:21.880
<v Speaker 1>The end of the day, a detective shut up my

896
00:55:21.920 --> 00:55:24.119
<v Speaker 1>door and asked me where I was between five and six.

897
00:55:24.159 --> 00:55:27.119
<v Speaker 1>I said, well, I was probably at school, you know,

898
00:55:28.199 --> 00:55:33.079
<v Speaker 1>five and six years of age, right? And then did

899
00:55:33.119 --> 00:55:35.960
<v Speaker 1>you know I love cow jokes? Did you know that

900
00:55:36.079 --> 00:55:40.000
<v Speaker 1>cows kill more people than sharks. I'm surprised that cows

901
00:55:40.079 --> 00:55:41.119
<v Speaker 1>killed any sharks at all?

902
00:55:43.920 --> 00:55:44.239
<v Speaker 2>All right?

903
00:55:45.000 --> 00:55:49.159
<v Speaker 1>Oh, a little double whammy there, double all right? Those

904
00:55:49.159 --> 00:55:50.800
<v Speaker 1>are the dad jokes of the week, do you lie?

905
00:55:50.840 --> 00:55:51.920
<v Speaker 1>Do you have any picks for us?

906
00:55:52.719 --> 00:55:58.239
<v Speaker 2>Yes? Actually I want to to building English, but to

907
00:55:59.239 --> 00:56:05.000
<v Speaker 2>pick kind of competitor to us. It's uh, it's a

908
00:56:05.039 --> 00:56:10.079
<v Speaker 2>new tool from an Israeli guy. It's called base forty four.

909
00:56:10.599 --> 00:56:12.480
<v Speaker 2>And you can try it like just a little based

910
00:56:12.519 --> 00:56:16.440
<v Speaker 2>forty four like the number. And this is like a

911
00:56:16.559 --> 00:56:19.519
<v Speaker 2>kind of a competitor to to bold and lovable and everything,

912
00:56:20.280 --> 00:56:23.320
<v Speaker 2>which is great if you're doing like a side project,

913
00:56:23.360 --> 00:56:27.480
<v Speaker 2>a weekend project, and it can build you also like

914
00:56:27.559 --> 00:56:31.199
<v Speaker 2>kind of taking the authentication and every and some other

915
00:56:31.320 --> 00:56:34.800
<v Speaker 2>aspects of the application right away from you for from

916
00:56:34.840 --> 00:56:39.920
<v Speaker 2>your prompt and this is built by one guy from Israel.

917
00:56:40.800 --> 00:56:45.360
<v Speaker 2>So it's like a great uh, it's it's it's great

918
00:56:45.400 --> 00:56:49.639
<v Speaker 2>to see like someone alone today is kind of competing

919
00:56:49.800 --> 00:56:55.360
<v Speaker 2>with all these giants that raised tons of money and

920
00:56:55.440 --> 00:56:57.920
<v Speaker 2>you have like large teams and it is like building

921
00:56:57.960 --> 00:57:00.719
<v Speaker 2>this like a side project for a few months, is

922
00:57:01.239 --> 00:57:05.400
<v Speaker 2>studied like a few months ago and uh, seeing really

923
00:57:05.400 --> 00:57:09.360
<v Speaker 2>good results. So if you're doing like a site logic

924
00:57:09.519 --> 00:57:12.400
<v Speaker 2>or something, you should try it. If you're trying to

925
00:57:12.480 --> 00:57:20.440
<v Speaker 2>use the if enterprises, probably just use tool. But is

926
00:57:21.000 --> 00:57:25.639
<v Speaker 2>really great and deserve like all the respect of building

927
00:57:25.679 --> 00:57:30.880
<v Speaker 2>it like alone and also like a national crowd of

928
00:57:31.039 --> 00:57:31.480
<v Speaker 2>his dual.

929
00:57:32.840 --> 00:57:35.559
<v Speaker 1>Yeah, it looks yeah, it's not necessarily in your space.

930
00:57:36.280 --> 00:57:38.320
<v Speaker 1>I've heard of some tools like this looks pretty interesting,

931
00:57:38.400 --> 00:57:41.840
<v Speaker 1>especially looking at the website. It's really pretty. But one

932
00:57:41.840 --> 00:57:44.599
<v Speaker 1>person doing that, that's that's pretty amazing. So it's base

933
00:57:44.719 --> 00:57:48.840
<v Speaker 1>for for the digits for Ford dot com. Yeah right,

934
00:57:49.039 --> 00:57:51.800
<v Speaker 1>alrighty well, thank you Giloud for coming and talking to

935
00:57:51.880 --> 00:57:54.920
<v Speaker 1>us today. Great to hear about what you got going on,

936
00:57:55.719 --> 00:57:58.400
<v Speaker 1>and thanks everybody for watching listening and we'll talk to

937
00:57:58.400 --> 00:57:59.760
<v Speaker 1>you next time on job ascript Ever