Everyone Wants Copilot—but Is Your Data Ready: Microsoft Fabric Architecture with Walter Calcagno [MVP-MCT]

1
00:00:00,000 --> 00:00:03,880
Welcome back to the MC65FM podcast.

2
00:00:03,880 --> 00:00:06,680
The podcast where we explore the technologies,

3
00:00:06,680 --> 00:00:09,000
architectures and real world decision-chapings,

4
00:00:09,000 --> 00:00:10,880
the Microsoft ecosystem.

5
00:00:10,880 --> 00:00:13,080
Today we are talking about a problem

6
00:00:13,080 --> 00:00:16,400
that many organizations do not recognize.

7
00:00:16,400 --> 00:00:21,360
Usually, I project begins producing unreliable answers.

8
00:00:21,360 --> 00:00:22,960
Everyone wants co-pilot,

9
00:00:22,960 --> 00:00:24,800
everyone wants intelligent agents,

10
00:00:24,800 --> 00:00:28,640
everyone wants employees to ask natural language questions

11
00:00:28,640 --> 00:00:31,360
and immediately receive trustworthy business insights.

12
00:00:31,360 --> 00:00:34,120
But an high system cannot compensate

13
00:00:34,120 --> 00:00:38,000
or for fragment data conflicted the efficient week governance

14
00:00:38,000 --> 00:00:40,320
or as a semantic model nobody understands.

15
00:00:40,320 --> 00:00:45,200
So what must exist between the raw data inside a like house

16
00:00:45,200 --> 00:00:48,040
and AI experience to present to users?

17
00:00:48,040 --> 00:00:50,800
My guest is Walter Carlango,

18
00:00:50,800 --> 00:00:55,800
a data architect, Microsoft MVP in data platform since 2019.

19
00:00:58,040 --> 00:01:02,560
And Microsoft certified, okay, China, MCT,

20
00:01:02,560 --> 00:01:04,560
Walter Skofon, the OV data,

21
00:01:04,560 --> 00:01:08,000
consulted specially in Microsoft fabric and Power BI

22
00:01:08,000 --> 00:01:12,240
and unlearned me, unlearned me,

23
00:01:12,240 --> 00:01:14,840
that, okay, out of the world,

24
00:01:14,840 --> 00:01:17,840
in digital education, venture focused on analytics.

25
00:01:17,840 --> 00:01:20,280
He's also the author of architecture,

26
00:01:20,280 --> 00:01:22,640
a engineering of the titles,

27
00:01:22,640 --> 00:01:26,680
well, yeah, forgive me, forgive me,

28
00:01:26,680 --> 00:01:30,360
it's not my language, in which we have discussed the framework.

29
00:01:30,360 --> 00:01:32,720
He applies with clients,

30
00:01:32,720 --> 00:01:35,880
including seven layers architecture models,

31
00:01:35,880 --> 00:01:37,440
the metalympathetic,

32
00:01:37,440 --> 00:01:41,960
the mentioned modeling and five dimension AI readiness assessment.

33
00:01:41,960 --> 00:01:43,960
He teach at the university,

34
00:01:43,960 --> 00:01:47,440
a university that ECC in Columbia, Palazzo,

35
00:01:47,440 --> 00:01:50,360
and namaz data in Barcelona,

36
00:01:50,360 --> 00:01:55,360
and he co-hosts the Spanish language podcast La Bellesa de la

37
00:01:55,360 --> 00:01:57,040
de los datos.

38
00:01:57,040 --> 00:01:58,200
Yeah, yeah.

39
00:01:58,200 --> 00:01:59,480
(laughs)

40
00:01:59,480 --> 00:02:02,800
So, yeah, like, what was I, I'm sorry for my, yeah.

41
00:02:02,800 --> 00:02:06,240
- No, I was thinking, thank you, you, Mirko.

42
00:02:06,240 --> 00:02:07,880
I'm gonna say sorry for my English too,

43
00:02:07,880 --> 00:02:11,480
because it's not my first language,

44
00:02:11,480 --> 00:02:13,240
but I wouldn't find it like this.

45
00:02:13,240 --> 00:02:18,240
Yeah, you know, it's my last name, it's pronounced Calcano.

46
00:02:18,240 --> 00:02:21,560
It's coming from Italy.

47
00:02:21,560 --> 00:02:24,400
Yeah, my family is coming from Italy to Chile,

48
00:02:24,400 --> 00:02:29,400
since 100 years ago, almost 90 years ago.

49
00:02:29,400 --> 00:02:32,160
They are coming from, you know,

50
00:02:32,160 --> 00:02:34,920
running out from the war,

51
00:02:34,920 --> 00:02:36,760
this typical European world,

52
00:02:36,760 --> 00:02:39,680
but they're running out, they came to Chile

53
00:02:39,680 --> 00:02:41,360
and they start this family.

54
00:02:41,360 --> 00:02:43,880
So, my last name is Bruno's in Italian.

55
00:02:43,880 --> 00:02:45,640
Calcano, you know, Capicci?

56
00:02:45,640 --> 00:02:47,680
(laughs)

57
00:02:50,680 --> 00:02:54,840
Well, yeah, yeah, and Italian is my third language too.

58
00:02:54,840 --> 00:02:58,640
So, I'd like to do my best way with this interview.

59
00:02:58,640 --> 00:03:03,640
So, yeah, I'm working in Della since 10 or 15 years

60
00:03:03,640 --> 00:03:08,000
because, you know, I used to be in a accountant.

61
00:03:08,000 --> 00:03:11,440
So, I work and study a accountant

62
00:03:11,440 --> 00:03:14,480
and all of it accounted in the university,

63
00:03:14,480 --> 00:03:19,480
when I go into the college at university,

64
00:03:19,800 --> 00:03:22,320
I started the thousand.

65
00:03:22,320 --> 00:03:25,880
So, that's five years I was studying accounting.

66
00:03:25,880 --> 00:03:29,280
So, my profession is, I am an accountant.

67
00:03:29,280 --> 00:03:32,280
And when I was working as an accountant,

68
00:03:32,280 --> 00:03:36,160
I see a lot of problems managing the level of data

69
00:03:36,160 --> 00:03:39,760
only with a spreadsheet like Excel

70
00:03:39,760 --> 00:03:42,840
and in some companies we have this,

71
00:03:42,840 --> 00:03:47,840
another open docs spreadsheet,

72
00:03:47,840 --> 00:03:50,040
yeah, this is, they are good,

73
00:03:50,040 --> 00:03:52,920
but yeah, this company don't want to pay a license.

74
00:03:52,920 --> 00:03:55,280
So, that is a really real thing

75
00:03:55,280 --> 00:03:57,600
in the Latin American people,

76
00:03:57,600 --> 00:03:59,760
that companies don't want to pay a license.

77
00:03:59,760 --> 00:04:04,760
So, yeah, we need to manage with the tools that we have.

78
00:04:04,760 --> 00:04:09,840
Yeah, after that, when I was in very trouble,

79
00:04:09,840 --> 00:04:12,920
trying to manage all the data in spreadsheets,

80
00:04:12,920 --> 00:04:13,920
I learned SQL.

81
00:04:14,960 --> 00:04:19,960
So, that was my first step into the data world,

82
00:04:19,960 --> 00:04:22,520
learning SQL when I was an accountant.

83
00:04:22,520 --> 00:04:26,080
So, I start to manage my own databases

84
00:04:26,080 --> 00:04:31,080
to prepare a lot of reports for the different

85
00:04:31,080 --> 00:04:34,000
accounting and financial perspective.

86
00:04:34,000 --> 00:04:38,240
And then, when the past of the years,

87
00:04:38,240 --> 00:04:40,760
Power BI checked live,

88
00:04:40,760 --> 00:04:44,440
the same day that I am a bird day, you know,

89
00:04:44,440 --> 00:04:47,600
Power BI released on July the 24th,

90
00:04:47,600 --> 00:04:50,480
and I am the bird day in July the 24th.

91
00:04:50,480 --> 00:04:55,480
So, yeah, was a very good bird gift.

92
00:04:55,480 --> 00:05:01,840
And I started with Power BI and then I left

93
00:05:01,840 --> 00:05:05,720
all the accountant practice and I start to dedicate

94
00:05:05,720 --> 00:05:09,360
100% of the time of data analytics.

95
00:05:09,360 --> 00:05:11,280
And then I learned all the things,

96
00:05:11,280 --> 00:05:16,280
like, big data, Spark and all the technologies

97
00:05:16,280 --> 00:05:18,320
across the big data.

98
00:05:18,320 --> 00:05:21,760
And now, apply it to the artificially.

99
00:05:21,760 --> 00:05:26,760
So, my vocation with the data is to deliver

100
00:05:26,760 --> 00:05:31,840
all this knowledge into Spanish,

101
00:05:31,840 --> 00:05:36,840
because there is a bunch of content in English,

102
00:05:38,240 --> 00:05:43,240
all the people want to make content in English.

103
00:05:43,240 --> 00:05:45,400
Actually, you know, there is a big job

104
00:05:45,400 --> 00:05:47,720
when you are trying to learn something.

105
00:05:47,720 --> 00:05:51,600
Always said there is an Indian guy speaking in English,

106
00:05:51,600 --> 00:05:53,600
teaching you, so, you know,

107
00:05:53,600 --> 00:05:56,280
all the people is delivering content in English,

108
00:05:56,280 --> 00:06:00,720
but there is no people delivering content in Spanish.

109
00:06:00,720 --> 00:06:04,880
So, with a bunch of Mbps from Spain,

110
00:06:04,880 --> 00:06:06,240
from all Latin America.

111
00:06:07,240 --> 00:06:12,240
We get this mission to create content only in Spanish

112
00:06:12,240 --> 00:06:17,200
for the Spanish people because we don't want

113
00:06:17,200 --> 00:06:19,160
to be only a translator.

114
00:06:19,160 --> 00:06:21,560
We want to create content in Spanish.

115
00:06:21,560 --> 00:06:24,760
That's for taking this knowledge from all the people

116
00:06:24,760 --> 00:06:28,080
like you, like the Mbps and the Microsoft

117
00:06:28,080 --> 00:06:31,720
and the people from Google, from Amazon web service

118
00:06:31,720 --> 00:06:34,720
because they are very, very good people.

119
00:06:34,720 --> 00:06:39,720
Create a lot of content and we are not that delivered in Spanish.

120
00:06:39,720 --> 00:06:43,600
So, I think we have a very, very critical community

121
00:06:43,600 --> 00:06:44,800
in the Spanish language,

122
00:06:44,800 --> 00:06:49,640
delivering this content and delivering the knowledge

123
00:06:49,640 --> 00:06:52,880
about AI, about data,

124
00:06:52,880 --> 00:06:57,840
and about a lot of things, but that is the purpose

125
00:06:57,840 --> 00:07:00,240
of why I am creating things

126
00:07:00,240 --> 00:07:02,680
and why all my culture is in Spanish,

127
00:07:02,680 --> 00:07:04,160
not because I don't know English.

128
00:07:04,160 --> 00:07:07,880
It's because it's my mission to create Spanish content

129
00:07:07,880 --> 00:07:10,760
for the people who don't speak English.

130
00:07:10,760 --> 00:07:12,880
Yeah, that is a little bit to think about me.

131
00:07:12,880 --> 00:07:19,240
So, yeah, you also co-host the "La Bellesa de los Dacos".

132
00:07:19,240 --> 00:07:21,960
- La Valleesa de los Dacos.

133
00:07:21,960 --> 00:07:23,560
- La Valleesa de los Dacos.

134
00:07:23,560 --> 00:07:24,960
- Yeah, la Valle.

135
00:07:24,960 --> 00:07:25,800
- Yeah, something like that.

136
00:07:25,800 --> 00:07:30,480
- Sounds so, what do the beauty of data mean to you personally?

137
00:07:30,480 --> 00:07:31,920
- Yeah, the beauty of data.

138
00:07:31,920 --> 00:07:36,200
- Yeah, it's a podcast where started with Janina Cohen,

139
00:07:36,200 --> 00:07:41,200
she's a Argentinian MVP of the data platform.

140
00:07:41,200 --> 00:07:48,720
The idea of this podcast is to make a conversation

141
00:07:48,720 --> 00:07:52,360
about a lot of things around the data world.

142
00:07:52,360 --> 00:07:57,360
It's, we start the first chapter in the Microsoft Studios,

143
00:07:59,040 --> 00:08:02,080
in this MVP Summit in March.

144
00:08:02,080 --> 00:08:07,120
And then the second one, we make it online.

145
00:08:07,120 --> 00:08:11,240
Now we're gonna make the third chapter in Argentina

146
00:08:11,240 --> 00:08:15,640
because I'm coming into Argentina this in a few weeks.

147
00:08:15,640 --> 00:08:21,360
And the idea is to take, yeah, we're going to participate

148
00:08:21,360 --> 00:08:23,400
in the data south of La Danda,

149
00:08:23,400 --> 00:08:25,600
it's an data event.

150
00:08:25,600 --> 00:08:29,760
Only for Latin American people from Spanish speaking people

151
00:08:29,760 --> 00:08:34,760
on these three days with 60 speakers,

152
00:08:34,760 --> 00:08:40,600
it's gonna be a very, very great event.

153
00:08:40,600 --> 00:08:43,680
And that, in that occasion, we're gonna record

154
00:08:43,680 --> 00:08:46,040
and deliver the third chapter of this podcast.

155
00:08:46,040 --> 00:08:48,240
So the idea is, yeah, with the distance,

156
00:08:48,240 --> 00:08:52,320
we need to manage that from one way or another

157
00:08:52,320 --> 00:08:53,760
and start to deliver.

158
00:08:53,760 --> 00:08:58,320
Yeah, we have a 1,000 subscribers of the podcast.

159
00:08:58,320 --> 00:09:01,040
So it's, yeah, it's very good numbers.

160
00:09:01,040 --> 00:09:04,200
For the Latin American, you know, for the Spanish speaking world.

161
00:09:04,200 --> 00:09:06,440
So we're very happy with that.

162
00:09:06,440 --> 00:09:08,760
That is the view of the data.

163
00:09:08,760 --> 00:09:10,640
Yeah, this is awesome, yeah.

164
00:09:10,640 --> 00:09:16,720
And I also see the community in Spanish,

165
00:09:16,720 --> 00:09:19,480
the Spanish community is also fast growing

166
00:09:19,480 --> 00:09:21,720
and on the Microsoft ecosystem.

167
00:09:21,720 --> 00:09:23,080
That's really interesting.

168
00:09:23,080 --> 00:09:26,440
So we plan all to do, but yeah, we are a little team.

169
00:09:26,440 --> 00:09:29,240
No one speaks really Spanish, but we plan all to do

170
00:09:29,240 --> 00:09:35,680
a conference in Spanish, the MDR 64 connet also

171
00:09:35,680 --> 00:09:37,040
in Spanish next year.

172
00:09:37,040 --> 00:09:40,240
So we hope that we'll be able to be in binding.

173
00:09:40,240 --> 00:09:48,480
But let's, let's a little bit talk at the Microsoft staff.

174
00:09:48,480 --> 00:09:52,880
You work with many different aspects in the Microsoft data ecosystem.

175
00:09:52,880 --> 00:09:56,360
When did Power BI become an important part of your work?

176
00:09:56,360 --> 00:10:06,000
You know, business questions, business question is the main issue,

177
00:10:06,000 --> 00:10:08,480
is the main problem in all the companies?

178
00:10:08,480 --> 00:10:11,920
No, they want to answer for make decisions.

179
00:10:11,920 --> 00:10:16,280
So that is the very important thing to answer business questions.

180
00:10:16,280 --> 00:10:21,720
That is, and for answers the business question, there's a lot of tools

181
00:10:21,720 --> 00:10:27,520
for that. Yeah, you can use a Python code, you can use R,

182
00:10:27,520 --> 00:10:33,160
you can use, yeah, a lot of, a lot of products from Tableau,

183
00:10:33,160 --> 00:10:35,640
from Google, from, yeah, yeah, yeah, yeah,

184
00:10:35,640 --> 00:10:36,960
and it does have reality.

185
00:10:36,960 --> 00:10:44,080
Open is once to use people's, our companies want to answer

186
00:10:44,080 --> 00:10:45,200
this business question.

187
00:10:45,200 --> 00:10:51,600
So the real thing in the, in the,

188
00:10:51,600 --> 00:10:58,600
in the company who are, there is only three big brands making all the

189
00:10:58,600 --> 00:11:01,080
90% of the tools.

190
00:11:01,080 --> 00:11:06,800
So we have Google tools in the third place, Microsoft tools in the second place,

191
00:11:06,800 --> 00:11:12,160
and Amazon Web Server tools in the first place, you know, delivering all the data

192
00:11:12,160 --> 00:11:13,440
technology for all the companies.

193
00:11:13,440 --> 00:11:19,640
So, but in data, Amazon has quick side, but quick side is not so,

194
00:11:19,640 --> 00:11:22,600
you know, easy for business people.

195
00:11:22,600 --> 00:11:25,400
Yeah, you need to know about our code.

196
00:11:25,400 --> 00:11:32,600
It's, it's a tool for, for, for, I.T. people,

197
00:11:32,600 --> 00:11:34,840
not for business people.

198
00:11:34,840 --> 00:11:42,440
So, but our BI has this particular advantage because it's a tool for non-I.T. people,

199
00:11:42,440 --> 00:11:46,240
you know, is for these people is a pretty easy to make a last word, you know,

200
00:11:46,240 --> 00:11:54,840
you take a, a, a, a, a, takeable, pick up the data, deliver to the, to the screen,

201
00:11:54,840 --> 00:11:58,720
and you're going to have our, our graphic and is in, and is interactive.

202
00:11:58,720 --> 00:12:04,040
So it's a very good tool, very, very, treated, with a very user experience.

203
00:12:04,040 --> 00:12:11,160
So, to me, that is the reason because power base is the lead of, of these business

204
00:12:11,160 --> 00:12:14,720
intelligence questions, you know, what's, what's happened with the data?

205
00:12:15,200 --> 00:12:18,680
And why this is, is happening?

206
00:12:18,680 --> 00:12:26,560
So that is the, the, the thing that I think are, they are, they are leading.

207
00:12:26,560 --> 00:12:34,160
Then you have a blow, a blow is a very good tool, but to me, with the sale, to sale force,

208
00:12:34,160 --> 00:12:39,040
yeah, you know, come up, it's like a, um, start to,

209
00:12:39,560 --> 00:12:46,400
the love, the, wake up balloon, we start to go down. So that, that is the thing I think

210
00:12:46,400 --> 00:12:53,160
with the, the, the, the, the, the, the, the, the north of the, of the, the root.

211
00:12:53,160 --> 00:13:01,800
And yeah, Google is working hard in, in his tool, they, like, always in Google,

212
00:13:01,800 --> 00:13:06,480
they changed them third for five times, they start with data, something,

213
00:13:06,480 --> 00:13:12,600
then it was lookered, now it's data, something again. So, yeah, I think they are working in

214
00:13:12,600 --> 00:13:18,600
a very good tool, very, pretty, uh, yeah, but the steel, they don't have the, the, all the

215
00:13:18,600 --> 00:13:26,040
markets. So companies go to the tool that the, your main, uh, IT provider offers.

216
00:13:26,040 --> 00:13:30,400
So that is, that is the reality, you know, power base, the lead because Microsoft is the

217
00:13:30,400 --> 00:13:33,120
lead in, in data analytics in the company.

218
00:13:33,120 --> 00:13:38,720
So that is the main reason. And actually, there is a very easy and intuitive tool.

219
00:13:38,720 --> 00:13:45,960
Yeah, you know, say, uh, to start what is really interesting, I see a lot of companies,

220
00:13:45,960 --> 00:13:51,920
they do more, yeah, they, they do reports, but they don't ask business questions.

221
00:13:51,920 --> 00:13:57,400
What, what tips can you give to, to ask good business questions to the nature?

222
00:14:00,640 --> 00:14:06,400
Yeah, yeah, the, the original question is, the original answer to that question is, uh,

223
00:14:06,400 --> 00:14:17,080
go to your KPI, you okay, R, but to me, the, the very, very, very good business questions are

224
00:14:17,080 --> 00:14:22,080
the first one, they're, therefore, the first one, what happened with that?

225
00:14:22,080 --> 00:14:27,960
That is, that is the main, the, the real first question, what happened with the sales?

226
00:14:27,960 --> 00:14:31,080
What happened with, uh, with the cost?

227
00:14:31,080 --> 00:14:34,240
What happened with whatever company is doing?

228
00:14:34,240 --> 00:14:36,120
And that is the first business question.

229
00:14:36,120 --> 00:14:39,360
And then what happened with that is business intelligence.

230
00:14:39,360 --> 00:14:43,160
When you answer that question, you're getting business intelligence.

231
00:14:43,160 --> 00:14:45,760
And then you have the second business question.

232
00:14:45,760 --> 00:14:47,160
Why this happened?

233
00:14:47,160 --> 00:14:53,120
And that is a very interesting question because you need a lot of math to answer that because

234
00:14:53,120 --> 00:14:57,000
you need to see correlations, you need to see what's going on.

235
00:14:57,000 --> 00:15:01,560
What is the probability about these when this other thing happened?

236
00:15:01,560 --> 00:15:05,200
So that is a very interesting, why this is happening?

237
00:15:05,200 --> 00:15:09,240
But answer that with no, be us.

238
00:15:09,240 --> 00:15:11,040
You need to answer that with the numbers.

239
00:15:11,040 --> 00:15:14,080
So that is a very second big business question.

240
00:15:14,080 --> 00:15:21,600
And the third one is, how this is going to happen?

241
00:15:22,880 --> 00:15:30,160
Or what's, what we're going on with this data? That is the third business question because

242
00:15:30,160 --> 00:15:37,360
we all wants to be at, you know, this, uh, a crystal ball to see the future.

243
00:15:37,360 --> 00:15:41,280
So, uh, when you get that, you can use it.

244
00:15:41,280 --> 00:15:47,360
So that business question, you can answer with probabilistic models and probabilistic

245
00:15:47,360 --> 00:15:53,680
models. We are getting into AI, you know, that is what you learn to understand the data to

246
00:15:53,680 --> 00:15:56,200
project to the future that behavior.

247
00:15:56,200 --> 00:15:58,360
So that is that is the third one.

248
00:15:58,360 --> 00:16:03,840
And the fourth one is, what we do for this would happen.

249
00:16:03,840 --> 00:16:10,240
And, you know, and you get that with the recommendation models, you know,

250
00:16:10,240 --> 00:16:14,560
like when you go to Netflix or whatever, another streaming channel and they offered you

251
00:16:14,560 --> 00:16:17,680
a series, they offered you a movie, they offered you something.

252
00:16:17,680 --> 00:16:22,360
Yeah. And you go to this algorithmic and you say, wow, it's magic.

253
00:16:22,360 --> 00:16:24,800
How does no, what I like it?

254
00:16:24,800 --> 00:16:25,120
Yeah.

255
00:16:25,120 --> 00:16:28,040
That is a probabilistic models.

256
00:16:28,040 --> 00:16:34,280
They are mathematical advances models applied to your, your, your natural behavior with the

257
00:16:34,280 --> 00:16:34,600
tool.

258
00:16:34,600 --> 00:16:37,320
So that is the fourth business question.

259
00:16:37,320 --> 00:16:43,520
So when the company is stuck to answer business question, they are going to adopt

260
00:16:43,640 --> 00:16:45,120
that nearly the need.

261
00:16:45,120 --> 00:16:48,760
So companies don't need to make more dashboard.

262
00:16:48,760 --> 00:16:55,400
They need to answer more business question because the real business is on the street,

263
00:16:55,400 --> 00:17:01,200
you know, they need to sell the need to page, you need to hire, they need to make

264
00:17:01,200 --> 00:17:06,640
whatever thing because the market is hard and for and to survive in the market because

265
00:17:06,640 --> 00:17:08,480
it's hard, you need to answer this question.

266
00:17:08,480 --> 00:17:14,160
So I think the, the real question is that what is the very good business question?

267
00:17:14,160 --> 00:17:15,440
Not the, what is the best tool?

268
00:17:15,440 --> 00:17:17,320
The tool, yeah, tool is a tool.

269
00:17:17,320 --> 00:17:23,840
The way this is tool are going to disappear, you know, a few years ago, we have a visual

270
00:17:23,840 --> 00:17:29,720
fox, bro, feature fox, bro, it was a very good business database tool and disappeared.

271
00:17:29,720 --> 00:17:31,880
There is no visual fox, bro.

272
00:17:31,880 --> 00:17:32,280
Yeah.

273
00:17:32,280 --> 00:17:34,600
We have a lot of time with Cobalt.

274
00:17:34,600 --> 00:17:36,600
All the people are programming in Cobalt.

275
00:17:36,600 --> 00:17:41,000
Now Cobalt is not anymore, you know, tools are going to evolve, you need,

276
00:17:41,000 --> 00:17:42,160
it's going to disappear.

277
00:17:42,160 --> 00:17:46,440
But the business question are the same here and then 18,000.

278
00:17:46,440 --> 00:17:51,440
So the, the real thing is how we answer that business question.

279
00:17:51,440 --> 00:17:52,920
Yeah.

280
00:17:52,920 --> 00:17:53,640
Yeah.

281
00:17:53,640 --> 00:17:54,400
Yeah.

282
00:17:54,400 --> 00:18:01,400
Yeah, I think that's, yeah, that's, that's, I think that's, that's the magic to ask good

283
00:18:01,400 --> 00:18:08,000
questions, and I think that's also makes for me good leaders, they, they, they can ask

284
00:18:08,000 --> 00:18:09,320
good questions.

285
00:18:09,320 --> 00:18:15,320
And yeah, that's, I see a lot of people report because they have to report.

286
00:18:15,320 --> 00:18:22,720
And you say we, a lot of, yeah, the stuff is, is, is going.

287
00:18:22,720 --> 00:18:28,520
So I think we have, a lot of companies have started for years with Axel, then they have

288
00:18:28,520 --> 00:18:33,480
built their data platforms, I see your SQL databases.

289
00:18:33,480 --> 00:18:40,000
And now they're, but something coming new in the game, it's Microsoft fabric.

290
00:18:40,000 --> 00:18:44,800
How has your role changed since Microsoft fabric, enter the market?

291
00:18:44,800 --> 00:18:52,480
Well, Microsoft fabric is a, it's a big bit of Microsoft.

292
00:18:52,480 --> 00:18:58,480
They, the data prefer with my group is that with the Azure, you know, and in Azure,

293
00:18:58,480 --> 00:19:08,600
they start to deliver a lot of platforms on the service, but these platforms are service

294
00:19:08,600 --> 00:19:11,400
this past.

295
00:19:11,400 --> 00:19:21,840
There was with the started with big layhouse, the, sorry, big buckets of data with the, with

296
00:19:21,840 --> 00:19:31,560
this blobs storage accounts. So the idea is to make a, make a delivery of a lot of a bunch

297
00:19:31,560 --> 00:19:37,120
of data in the, in the cloud for managing for analytics.

298
00:19:37,120 --> 00:19:43,320
And they start with a lot of product, you know, for data purpose, thinking in big data.

299
00:19:43,320 --> 00:19:50,400
But the, the thing that of that all these separated tools is when you go there, you always

300
00:19:50,400 --> 00:19:55,440
start to hire the same, yeah, the same products, you know, you, you buy the same product.

301
00:19:55,440 --> 00:20:03,040
When, when you go to Azure, you go to blobs storage, because you need to save the data,

302
00:20:03,040 --> 00:20:12,560
you need a data flows for moving data, the, you need, yeah, as a set of tools that you

303
00:20:12,560 --> 00:20:17,960
always go into there. So Microsoft thinks, hey, all the people is buying all these tools.

304
00:20:17,960 --> 00:20:23,600
Why we don't have all these tools in one, one big software as a service. And that is

305
00:20:23,600 --> 00:20:30,960
fabric. Fabric is big data and, and mature learning for companies in one software as a

306
00:20:30,960 --> 00:20:37,160
service. That is the, yeah, you don't need to buy separate tools for do the same. So it's

307
00:20:37,160 --> 00:20:43,040
one big tool for big data into the companies. The idea of the, this big data, you can manage

308
00:20:43,040 --> 00:20:50,720
your, your data from different sources, they start with a concept like the one, the, the

309
00:20:50,720 --> 00:20:58,320
one lake concept is, yeah, it was the same concept of one right in Microsoft 365, you have

310
00:20:58,320 --> 00:21:04,120
one right because it's only one right for all the company. Yeah, and in the big data of

311
00:21:04,120 --> 00:21:11,560
fabric, you have one lake. So one lake, get all the data with George Cards with, you know,

312
00:21:11,560 --> 00:21:21,560
these, they are using a technology ability for technology created for Databricks. Databricks

313
00:21:21,560 --> 00:21:28,400
created a technology named Delta Lake Delta Lake is a way to manage data, packet data with

314
00:21:28,400 --> 00:21:34,320
a roll of made data data. They give you the ability to, to transform the data into acid

315
00:21:34,320 --> 00:21:42,600
patterns. So with the, with the acid, you can manage all your data like SQL database. So it's

316
00:21:42,600 --> 00:21:48,760
amazing because you get, you get that. That technology Delta Lake Microsoft take it because

317
00:21:48,760 --> 00:21:56,000
it's open source and delivering to one lake. So one lake is, it's Delta Lake. So it's a very

318
00:21:56,000 --> 00:22:00,880
faster, very easy, some very good technology, open source technology. So you don't have to

319
00:22:00,880 --> 00:22:06,240
pay for that in a new, that license. Microsoft is always asking you for the license about

320
00:22:06,240 --> 00:22:11,640
the service, but not for the license because it's open source. And then for managed data,

321
00:22:11,640 --> 00:22:21,840
you have Spark, Power BI and a lot of open sources streaming data managing. So yeah,

322
00:22:21,840 --> 00:22:29,840
fabric is all that is a bunch of technology of big data in easy for the companies. So,

323
00:22:29,840 --> 00:22:37,520
yeah, fabric has right now two years in the market and there is a lot of content in that. So

324
00:22:37,520 --> 00:22:47,840
I've been working with fabric in some companies here in Chile, in the States, in Spain,

325
00:22:47,840 --> 00:22:55,600
the little bit of a lot of data solutions. When now they are working with data agents, agents

326
00:22:55,600 --> 00:23:02,480
into fabric. So yeah, you can mix all the new things I think that is with their data of

327
00:23:02,480 --> 00:23:08,240
business, but the idea of that is to answer business questions. So that is a very good implementation.

328
00:23:08,240 --> 00:23:13,920
When you answer very good business question, yeah, the tool works perfectly.

329
00:23:13,920 --> 00:23:22,400
Yeah. When I found something really interesting, we talk about fabric and so on. But another topic,

330
00:23:22,400 --> 00:23:31,920
we are not soft talk, it's the, the, the, the, the, or, yeah, or I have tried to say that one of your

331
00:23:31,920 --> 00:23:38,320
core messages is everyone wants co-pilot on the data, but most organizations keep the government

332
00:23:38,320 --> 00:23:44,160
semantic layer that makes work. What exactly are they skipping?

333
00:23:46,560 --> 00:23:54,240
What is at least the semantic layer or or co-pilot working with semantic layer? Yeah, yeah, I think

334
00:23:54,240 --> 00:24:02,080
when they put them, I think a lot of companies say, oh, we already have the nature in fabric or

335
00:24:02,080 --> 00:24:10,400
somewhere. So why we can't connect and I model direct to it. How did you, I'll, like, something like this?

336
00:24:11,120 --> 00:24:18,480
Yeah, you know, there is a mechanic for using AI in today is that's mechanic is independent of the

337
00:24:18,480 --> 00:24:26,720
tool. You need to prepare your database server with an MCB server, MCB is a protocol, you know,

338
00:24:26,720 --> 00:24:34,000
it's the real is a PICON script for, yeah, allowing to access your data for the R-A-G

339
00:24:36,160 --> 00:24:45,360
instance, an R-A-G instance is the ability to from an LLM to get data from your database and

340
00:24:45,360 --> 00:24:55,280
answer some prompts with your data. That is, so that is the mechanic. And that mechanic, you need to

341
00:24:55,280 --> 00:25:01,200
make it with whatever tool you are using. So you have a simple database, you know, well, open source

342
00:25:01,200 --> 00:25:09,040
database into your company, you need to start with an MCB and we need, you need to deliver the

343
00:25:09,040 --> 00:25:16,960
R-A-G. There is no way to do it, nothing but that. So in the fabric perspective, there is semantic

344
00:25:16,960 --> 00:25:26,640
model. Semantic model is a, you know, it's a Kimball's idea, because semantic model is a Kimball's

345
00:25:27,520 --> 00:25:34,720
order way for database, you know, you don't have entity relation in that, you have

346
00:25:34,720 --> 00:25:46,160
another modeling way that is, is for data art, you know, for Kimball's, the idea is to get a very good

347
00:25:46,160 --> 00:25:53,120
data mark and with the sum of the data marks, you're going to have a data work. And that is the semantic

348
00:25:53,120 --> 00:25:59,760
models into fabric. You have little data marks with all your data, you know, very modulated for,

349
00:25:59,760 --> 00:26:08,320
now for a R-A-G. And copy that or the LLM you want with Claude, with Jamie and I, with whatever you

350
00:26:08,320 --> 00:26:18,160
want. There is no limit with that. You need to go into that data, that data in the fabric leaves in

351
00:26:19,840 --> 00:26:26,400
semantic model. But when you have a lot of semantic models, and that is a reality in the companies,

352
00:26:26,400 --> 00:26:36,880
you have another tool over that semantic model. And that is the, I forgot the name in English,

353
00:26:36,880 --> 00:26:48,240
there is an over, over layer, that is a semantic model is the first one,

354
00:26:48,240 --> 00:26:58,080
in the second one, it's, you can add that to it. It's, oh, oh, yesterday was working is that.

355
00:26:58,080 --> 00:27:12,640
It's, the logical layer? Yeah, it's logical layer, but that logical layer has another name, it,

356
00:27:15,120 --> 00:27:22,080
then search. Yeah, it's solving the, in something that,

357
00:27:22,080 --> 00:27:31,120
ontology, yeah, over, you have the semantic layer and then you have the ontology layer.

358
00:27:31,120 --> 00:27:37,520
So, the ontology layer, what, what ontology layer says, make the relationship between semantic model

359
00:27:37,520 --> 00:27:45,440
without creating a big, big semantic model. So, that ontology layer allows you to, wherever,

360
00:27:45,440 --> 00:27:54,320
let them, to go into your data, in a modeling of data, not our relationship model. It's,

361
00:27:54,320 --> 00:28:05,040
it's a graph, relation model. So, the idea with the ontology model is, it's, it's,

362
00:28:05,040 --> 00:28:13,440
layer is to allow that ontology layer to the LLM, whatever LLM, you know, whatever,

363
00:28:13,440 --> 00:28:17,440
when I say whatever is whatever, the open source, you know, there is more than

364
00:28:17,440 --> 00:28:26,160
one cotton and fichal, models, allow it to go with the semantic layer. Go into there and stop the,

365
00:28:26,160 --> 00:28:33,280
the, the, the start to get your data for answer your questions. So, in a safe way, in a, so,

366
00:28:33,280 --> 00:28:38,720
that is, that is the thing, you know, the data is going to live into your semantic model.

367
00:28:38,720 --> 00:28:45,200
That semantic model can communicate with another semantic model using this ontology layer.

368
00:28:45,200 --> 00:28:51,920
And with the tonality layer, you can allow that for LLM and start to make questions for your,

369
00:28:51,920 --> 00:28:58,720
from your business to make business questions. And of course, you can go with all the security and

370
00:28:58,720 --> 00:29:05,440
the, you don't have access to the data, they're not to give you because you are not allowed to

371
00:29:05,440 --> 00:29:13,680
access that. They are going to anonymize the sensitive, sensitive data into your data.

372
00:29:13,680 --> 00:29:22,800
Yeah, it's a very good tool. And that is the idea with fabric. Make semantic layers and make ontology

373
00:29:22,800 --> 00:29:32,080
layers. With the tonality layer, you're going to allow your data, get ready for AI because all the

374
00:29:32,080 --> 00:29:39,200
people, all of the companies wants AI right now. Yeah, they need to, we need to give them AI.

375
00:29:39,200 --> 00:29:50,480
Yeah, that's good, good, good, good, yeah, step forward for my next question. So,

376
00:29:51,520 --> 00:29:57,840
what is the difference between data being available, understandable, trust worthy, and yeah,

377
00:29:57,840 --> 00:29:59,040
generally AI ready?

378
00:29:59,040 --> 00:30:12,800
So, good question, you know, data, you need to work with data with different layers, with different

379
00:30:12,800 --> 00:30:21,680
perspectives. That is the reason because we have this medallion architecture into that.

380
00:30:21,680 --> 00:30:29,600
I don't like the medallion name, you know, because after the medallion name, we always say,

381
00:30:29,600 --> 00:30:35,040
yeah, we are going to get the three layers, but you can have two, you can have three, you can have

382
00:30:35,040 --> 00:30:40,400
five, you can have seven, you can have a lot of layers of data. There is no deal with that.

383
00:30:40,960 --> 00:30:47,680
Now, the marketing people start to speak about the medallion layer and all the people think that

384
00:30:47,680 --> 00:30:52,800
you need all these three layers. No, that is not true. You can have two, you can have three, you can

385
00:30:52,800 --> 00:31:00,080
have four, whatever you need, but always minimal two. The minimal two are the staking layer,

386
00:31:00,080 --> 00:31:06,640
you know, you get data from the, from the software perspective and get and save that into

387
00:31:10,480 --> 00:31:17,360
the first layer. Now, all the people start to say bronze. Yeah, well, yeah, there is a lot of

388
00:31:17,360 --> 00:31:23,840
company that they put another name like role in a lot of people say that is the staking, you know,

389
00:31:23,840 --> 00:31:30,640
well, different, different layers, different names from the same layer. So, the purpose of that

390
00:31:30,640 --> 00:31:36,240
layer is to get the data into a historical perspective. So, I wonder, I went that data from today,

391
00:31:36,240 --> 00:31:42,720
from tomorrow, from, yeah, whatever the date is coming and a save that in that layer. You don't worry

392
00:31:42,720 --> 00:31:50,080
for duplicate, you don't worry for consistency, you need only need the historical layer, the historical

393
00:31:50,080 --> 00:31:56,080
data into that. That is the first purpose of the, then you have the silver and the silver layer

394
00:31:56,080 --> 00:32:05,120
or ready for something layer, ready for BI, ready for, yeah, there is different names in that.

395
00:32:05,120 --> 00:32:14,080
Now, marketing says is a bronze, silver layer, okay, silver layer. And you get ready the data clean,

396
00:32:14,080 --> 00:32:24,000
you know, you save the duplicates, go into the primary keys, foreign keys, all the data is matching,

397
00:32:24,000 --> 00:32:29,680
all the data is consistency, you will see the sum is coming, is the same sum you have in the,

398
00:32:30,400 --> 00:32:36,560
in the operational software. So, yeah, that is a very good layer and you can start to do a lot of

399
00:32:36,560 --> 00:32:40,240
things with that layer. You can start to make business it's a little, you can start to make

400
00:32:40,240 --> 00:32:49,840
a little much learning, but then you need a specific layer or specific data,

401
00:32:49,840 --> 00:32:59,920
the sub-conscious. And that is the goal, is the purpose of the goal, the goal layer, data ready for

402
00:32:59,920 --> 00:33:07,920
something. So, when I go into the material learning model for, you know, make a predictive

403
00:33:07,920 --> 00:33:18,240
something, I'm going to take an specific data from the silver layer, put it into the gold,

404
00:33:18,240 --> 00:33:22,640
and with that data, you're going to start to make my material learning. And with that data,

405
00:33:22,640 --> 00:33:29,280
I'm going to start to make my deep learning. So, when you prepare your data for a specific tool,

406
00:33:29,280 --> 00:33:38,960
that is the data ready for something. When you need data ready for a UI, you need to prepare your data

407
00:33:38,960 --> 00:33:53,760
for a real cost benefit, a reason for a UI, you know, because you don't want to spend a lot of

408
00:33:53,760 --> 00:34:04,480
tokens into data that is expensive. So, you need to get the specific data for your tokens, make a real

409
00:34:04,480 --> 00:34:10,640
profit of that, you don't want to spend your tokens, you know, make you need to do that. So,

410
00:34:10,640 --> 00:34:18,320
you need to prepare that data for the real cost benefit of that token, a value. So,

411
00:34:20,800 --> 00:34:27,600
that is the big difference. That is data ready for a UI. It's data ready for

412
00:34:27,600 --> 00:34:42,640
to make your best, uh, growing from, uh, from your tokens. Yeah. And sometimes some companies say,

413
00:34:42,640 --> 00:34:51,920
"Hey, you know, I need all my data ready for something." Yeah. So, when they want all your data,

414
00:34:51,920 --> 00:35:01,040
ready for a UI, already for an LLM, already for a specific tool, you need to prepare these

415
00:35:01,040 --> 00:35:08,320
semantic layers. You don't need to work with data, you need to work with metadata. So,

416
00:35:08,320 --> 00:35:16,800
for metadata, you prepare the semantic layer, all for this metadata because it's so expensive to

417
00:35:16,800 --> 00:35:25,680
get all the data ready for. You work in the semantic layer, you work in the, in the, I,

418
00:35:25,680 --> 00:35:31,200
ontology layer. Yeah, I need to learn a practice that word in English, ontology layer,

419
00:35:31,200 --> 00:35:37,760
ready for whatever the one. But with a big warning, if you get more data,

420
00:35:37,760 --> 00:35:42,160
you're going to spend a lot of tokens. Whatever the tool it is because tokens is the,

421
00:35:42,160 --> 00:35:48,960
is the way how the LLM works. You know, not only cloud, uh, uh, Gemini works for

422
00:35:48,960 --> 00:35:55,440
token, and in copilot works for token, all the LLM works for tokens. And token is

423
00:35:55,440 --> 00:36:02,320
getting expensive day by day. Yeah. Yeah.

424
00:36:03,520 --> 00:36:10,960
You say, same metadata, how, how can metadata help on, on, on, on, on this problem? So, I, I see a lot of,

425
00:36:10,960 --> 00:36:16,800
I say different departments use different definitions for revenue, customer, margin, or

426
00:36:16,800 --> 00:36:24,160
active employee. How should an AI system decide which definition is correct? No, they don't decide.

427
00:36:24,160 --> 00:36:30,160
You, you need to prompt that. You need to define what is your definition of the KPI. If you have

428
00:36:30,160 --> 00:36:35,920
sales in your perspective, you need to prompt that into the LLM. So, you don't need to,

429
00:36:35,920 --> 00:36:42,000
you don't have to allow to the LLM to decide something because you're doing wrong. You need to

430
00:36:42,000 --> 00:36:51,120
teach that LLM how that works for your company. Anything they have to do that your company needs. So,

431
00:36:51,120 --> 00:36:58,640
you don't have to decide. So that is the reason because you have to make very good prompt into your

432
00:36:58,640 --> 00:37:06,400
agent because if you make good prompt, you're going to have a minimal risk of hallucination of the

433
00:37:06,400 --> 00:37:14,160
LLM into your data. So, you don't need to allow the, the model to decide. This is not the way to,

434
00:37:14,160 --> 00:37:28,160
how to use the LLM. Yeah, interesting. Let's talk about your, your five dimension AI data readiness

435
00:37:28,160 --> 00:37:36,560
assessment. What are the those five dimensions? You know, when I go to, when I come to my company,

436
00:37:36,560 --> 00:37:46,320
with, with data, go to a customer, a client in this, say, yeah, we need to get AI into all data.

437
00:37:46,320 --> 00:37:55,280
Okay, let's do it, but I need to know how, how, how are you into the data perspective? So,

438
00:37:55,280 --> 00:38:04,160
this five dimension assessment is a tool that we create with data for to make a measure of,

439
00:38:04,160 --> 00:38:16,960
you know, the make a measure to, we want to know how far are the company ready for AI adoption,

440
00:38:16,960 --> 00:38:26,080
you know, and that's five dimension are governance, technology, political decision,

441
00:38:26,080 --> 00:38:37,600
internal political decision, not a political party decision, a human resource ready, training,

442
00:38:37,600 --> 00:38:46,240
yeah, with that five dimension, we take a view of how the company is and see what we have to

443
00:38:46,240 --> 00:38:53,680
work first. If they don't have governance, we need to work governance first. If they don't have

444
00:38:53,680 --> 00:39:04,240
the, the human resources properly trained, we need to train that first. And when we get that five

445
00:39:04,240 --> 00:39:11,920
dimensions fully covered, we can start to work into the whatever data solution they wanted with

446
00:39:11,920 --> 00:39:17,200
data, with AI, with machine learning, with deep learning, with business, with whatever thing. That is

447
00:39:17,200 --> 00:39:24,800
the, the, the AI adoption assessment. That is the purpose of that assessment. We have applied in a

448
00:39:24,800 --> 00:39:32,640
lot of companies here in Chile and into, outside of Chile. And it works, it works for the purpose

449
00:39:32,640 --> 00:39:38,400
because they have a measure. This is a picture of your company, how they are right now, what they

450
00:39:38,400 --> 00:39:47,680
have to work first, after to work into the AI adoption, you know, you're gonna take your money

451
00:39:47,680 --> 00:39:54,800
directly into the trash. If you go with a big LLM, you people don't have idea about the pros.

452
00:39:54,800 --> 00:40:02,000
That is a real fact. So, to avoid the people, the companies spend their money like

453
00:40:02,880 --> 00:40:11,680
like disappeared like magic, we are, we apply that data assessment. And there's a very good tool.

454
00:40:11,680 --> 00:40:21,200
Probably we're gonna publish that. We're gonna keep, keep applying that into some companies. And

455
00:40:21,200 --> 00:40:27,200
when we have a lot of experience, we're gonna publish that like a method. That is the, that is the,

456
00:40:27,200 --> 00:40:33,760
the idea. This is a, a tested method of how to take measures with this five dimension into

457
00:40:33,760 --> 00:40:41,520
companies before, adoption AI, before adoption, the AI or whatever they want to adopt.

458
00:40:41,520 --> 00:40:55,440
Yeah, awesome. I think, yeah, there it's also, you call it the seven-layer architecture model,

459
00:40:56,000 --> 00:41:03,680
that's from your, from your book, how do you define the seven-layer architecture model?

460
00:41:03,680 --> 00:41:14,560
So seven, they are seven, seven layers. Yeah. Yeah. Four layers, yeah, you know, it's a living

461
00:41:14,560 --> 00:41:19,760
inspired about the three-gill and quadraming, you know, they all live in the dogs. Yeah, yeah,

462
00:41:19,760 --> 00:41:26,240
the circumstances, it's nothing fried much. I was remembered that they said, yeah, because we have three

463
00:41:26,240 --> 00:41:35,840
layers for all the company. The first one is governance. You need to govern all the data in all

464
00:41:35,840 --> 00:41:42,720
the steps. You have the monitoring layer, you need to monitor, you know, to see what's going on in all your

465
00:41:44,240 --> 00:41:54,560
data solution. You need to make the security of all your company or all your data. So there are the

466
00:41:54,560 --> 00:42:02,000
first three layers into the bottom of this model. Then you have four layers. That four layers are

467
00:42:02,000 --> 00:42:08,480
functional is the path of the data. So you get the, you get the first one, you know, the sources.

468
00:42:08,480 --> 00:42:14,160
What is the sources? Because the data source is very important because I, it's not the same

469
00:42:14,160 --> 00:42:20,880
thing to get data from a database from a SQL database, from a non-SQL, a non-SQL database,

470
00:42:20,880 --> 00:42:29,520
or coming from an API, sometimes you need to scrap that data from source. So yeah, there is a

471
00:42:29,520 --> 00:42:35,680
different technique to get data from the source. So that is the first thing. Then you need to say that

472
00:42:35,680 --> 00:42:43,760
layer into the warehouse or, oh, no, that is the third one. The second one is to get the data. What is

473
00:42:43,760 --> 00:42:49,040
the best way to get that data? This data is coming in streaming. So I need an streaming solution to

474
00:42:49,040 --> 00:42:59,760
move that data that I can get that data from a, from different space of time. So I need to move that

475
00:42:59,760 --> 00:43:10,640
data into little packets from the source to the, to the same. And we use pipelines for, from that

476
00:43:10,640 --> 00:43:18,800
perspective, that is the data engineering layer, the way how to move that data from the source

477
00:43:18,800 --> 00:43:24,880
to the destiny. And the destiny is the third layer that is where are going to save that layer.

478
00:43:24,880 --> 00:43:28,560
Probably I'm going to use a database, add the warehouse, add that amount,

479
00:43:28,560 --> 00:43:38,400
layhouse, or whatever. I want to save that data for the four layer that is the analytic layer.

480
00:43:38,400 --> 00:43:44,720
Because I need to go for the layer every time for a different perspective. The, the four layer is

481
00:43:44,720 --> 00:43:52,960
for analytics. And you can go into that with a business intelligence solution with a data science

482
00:43:52,960 --> 00:43:59,840
solution with mature learning, the learning or AI solution. It is, so companies with these seven

483
00:43:59,840 --> 00:44:10,560
layers of architecture can make a, can, can design a very good experience using your data for

484
00:44:10,560 --> 00:44:18,480
make better decisions. And you can get that into a few seconds. They're going to take a lot of time

485
00:44:18,480 --> 00:44:24,560
moving the data from one time to another to transform that data into a decision if they go for

486
00:44:24,560 --> 00:44:30,000
these seven layers. So that is, that is the, the message of these seven layers in my book.

487
00:44:30,000 --> 00:44:39,200
Okay. Cool. I think what, what, what, what is the, the main step to, to make

488
00:44:39,200 --> 00:44:48,480
data AI ready? What's the misconceptions companies have here? What's, what's, what's the difference

489
00:44:48,480 --> 00:44:55,120
between, I don't know, use data and power BI and use it in, in, in, in, yeah, in AI systems like

490
00:44:55,120 --> 00:45:07,760
co-pilot? Woof! You know, David, question. First one, you don't need to go to the role data always.

491
00:45:07,760 --> 00:45:18,400
When you have a big data, go to all the different, minimal step of data. Yeah. That is

492
00:45:18,400 --> 00:45:27,280
not cost-efficient. So the first one, you need to get a very good metadata in your, in your data.

493
00:45:27,280 --> 00:45:34,880
So the first thing, go to the good metadata. When you have a good metadata, you can implement

494
00:45:34,880 --> 00:45:42,960
a lot of AI solutions into your data because AI goes to metadata, find what they need and then go

495
00:45:42,960 --> 00:45:50,240
to the data. So you need to create that, that, that root layer. You know, it's like a map. When you

496
00:45:50,240 --> 00:45:56,720
drive from one city to another, you go to the street, you go for the, for the main street, you go

497
00:45:56,720 --> 00:46:05,440
for the, no, the highway. You don't go to the little streets, because in, in, in every, in every town,

498
00:46:05,440 --> 00:46:11,840
you, you find a node, you're never going to find your destiny. So you go to the freeway, you go,

499
00:46:11,840 --> 00:46:17,520
then you move to the streets and then you go to your exactly points. That is the same thing in the data.

500
00:46:17,520 --> 00:46:24,880
You don't, you don't need to allow your LLM to get all your data scanning and then get the node.

501
00:46:24,880 --> 00:46:32,720
That is not cost-efficient. You need to create that roads, create that streets and the specific

502
00:46:32,720 --> 00:46:39,760
little street when your data leaves. So that is metadata. And that is the, the, the first year,

503
00:46:39,760 --> 00:46:48,240
to create a good metadata to create this map for your LLM to get exactly what they need, the, the data and

504
00:46:48,240 --> 00:46:55,840
they can, the LLM can take the freeway, they go to that, get the data and I showed you. So that is

505
00:46:55,840 --> 00:47:01,280
the first, that, that is the importance of the, of the media data. That's the first step.

506
00:47:01,280 --> 00:47:07,920
Create, to create, to get good metadata is your the half good metadata. You are not going to have a

507
00:47:07,920 --> 00:47:15,840
good LLM or, or IAI solution in your data. That is, that is the first one. And yeah, very

508
00:47:15,840 --> 00:47:20,640
salary job is that. You have, yeah, there is a lot of technique for my step.

509
00:47:20,640 --> 00:47:29,520
Awesome. Yeah. I think a lot of companies have have their, their problems to get a, I, I

510
00:47:29,520 --> 00:47:41,440
ready, a lot of products that stands, okay. It's AI ready. It's AI ready. What, what, what did you say,

511
00:47:41,440 --> 00:47:50,880
what impact has governance on, on, on AI readiness? Oh, total impact. If you have a governance company,

512
00:47:50,880 --> 00:47:57,520
you're not ready for the day. Yeah. You can hear that the, the base might have been the base plan. But

513
00:47:58,080 --> 00:48:05,520
if you allow whatever people to get data from your data, you're not convinced. The question is,

514
00:48:05,520 --> 00:48:14,480
if there is no responsible for one thing, you are not convinced you're the, you are, you have a very

515
00:48:14,480 --> 00:48:22,240
good tool implemented, but it's not, it's not a side business into that. Some companies, you don't

516
00:48:22,240 --> 00:48:31,040
need to allow people to know the salary of the other people. You don't allow, you know, get the

517
00:48:31,040 --> 00:48:40,160
social number for another people. Why do I have to know the phone number and the address for

518
00:48:40,160 --> 00:48:46,560
miracle in your, yeah, we, yeah, we're colleagues. We work in the same company. Yeah, but you and

519
00:48:46,560 --> 00:48:52,720
me and 1000 more people working here. And I don't need to know what is your address, what do you

520
00:48:52,720 --> 00:48:59,440
phone number because it's your private life. So if I get that, my data is not fully governance. So

521
00:48:59,440 --> 00:49:04,800
it's a, whatever thing, but it's not a company. It's not a serious company. So the governance is

522
00:49:04,800 --> 00:49:12,560
very important for us from that perspective, you need to allow to access the data for the people

523
00:49:12,560 --> 00:49:19,120
who need to really need to access that data for make better decisions. And all the people working

524
00:49:19,120 --> 00:49:25,200
in the company don't get the same decision. They don't need access to all the full data. They need

525
00:49:25,200 --> 00:49:31,600
some portion of the data for major business. So that is the reason because you need to govern your,

526
00:49:31,600 --> 00:49:39,520
your data into the company because it's, to me is the main, the main thing, to make a

527
00:49:39,520 --> 00:49:47,280
probably governance with your data and don't allow people has no access to your data. No,

528
00:49:47,280 --> 00:49:59,440
yeah, I think that's, yeah, it's, it's a, it's a real, really interesting topic. Have you tried

529
00:49:59,440 --> 00:50:03,520
these, I think, yeah, new tool. It's called, I think fabric apps.

530
00:50:04,800 --> 00:50:12,880
fabric apps. Wow. Yeah, I, I, I implement fabric apps in two companies in this year. And

531
00:50:12,880 --> 00:50:21,920
yeah, and it works perfectly. When you get, yeah, companies will implement that. They have a

532
00:50:21,920 --> 00:50:31,760
lot of good media, and these fabric apps allow them to make faster some data

533
00:50:34,080 --> 00:50:42,000
for the world. You have some process in your company. When you have some process in your company,

534
00:50:42,000 --> 00:50:49,840
you need data for, obviously, for data and steps for make something. So in some cases, you need a

535
00:50:49,840 --> 00:50:56,000
lot of steps of the decisions or whatever you need to do for time, from that data into the decision,

536
00:50:56,000 --> 00:51:01,920
whatever decision it is. Sometimes you need to release some data for, you know, for inspections.

537
00:51:01,920 --> 00:51:11,360
You need to release some data for no tax purpose or for governance, or maybe a stakeholder needs

538
00:51:11,360 --> 00:51:18,240
data for something. So that is a process that is our responsible, that is data. So make a combination

539
00:51:18,240 --> 00:51:24,240
of that process with the data and the purpose is a fabric apps. And that fabric app is a kind of

540
00:51:24,240 --> 00:51:31,520
application for that purpose into data. So when you apply that and you have a lot of process,

541
00:51:31,520 --> 00:51:38,080
you know, repeating process is better to make an app for that. So it's a, it's easy. Probably you're

542
00:51:38,080 --> 00:51:44,800
going to have 1000 stockholders into your company. And all they want, a personalized report of

543
00:51:44,800 --> 00:51:50,320
something, yeah, you know, to get one people writing all these personalistic reports for 1000,

544
00:51:50,320 --> 00:51:56,640
and stock, oh, forget it. It's a bunch of work. So a fabric app make you a solution for that because

545
00:51:56,640 --> 00:52:01,840
you program that, you're going to deliver, you get the access to the property data and they make

546
00:52:01,840 --> 00:52:07,120
it for you. So it's a very good solution. It's trying to make magic into your company with data,

547
00:52:07,120 --> 00:52:14,080
and we're not little bit on that. Yeah, yeah, very good to. I like it. We'll kill Power BI or

548
00:52:14,080 --> 00:52:22,560
no, no, you know, the tools, no, we're going to not go to kill Power BI. I think Power BI, no,

549
00:52:24,000 --> 00:52:32,640
into the, into real world, all the solutions when there is a evolve in that, they're not disappeared,

550
00:52:32,640 --> 00:52:38,800
they get into the new one, you know, for example, for data meaning, data meaning, all the people

551
00:52:38,800 --> 00:52:46,240
start to speak in a data meaning, oh, no, in 2000, now nobody speaking of data meaning, but data meaning,

552
00:52:46,240 --> 00:52:52,640
data mining is still working, is still working into Power BI. The first step you do in Power BI is

553
00:52:52,640 --> 00:53:01,920
data mining. And then you can make these facilities. Yeah, people don't ask, yeah, stop a low of,

554
00:53:01,920 --> 00:53:11,200
appeared in a stop of appears in the news, the data meaning, but that means data meaning,

555
00:53:11,200 --> 00:53:17,520
disappeared. Data meaning is still living into Power BI is still living to be query is still living

556
00:53:17,520 --> 00:53:27,280
in another, in all their data tools still living there. So to me is not going to happen that Power BI

557
00:53:27,280 --> 00:53:32,880
will disappear. Probably Power BI is going to live in a bigger tool, but still living, you know, it's

558
00:53:32,880 --> 00:53:44,560
the same thing with SQL SQL SQL starts in 1960s. It's about 80 years without SQL and SQL is still living,

559
00:53:44,560 --> 00:53:50,080
still living into the lake house, still living into the warehouse, still living into the data base,

560
00:53:50,080 --> 00:53:56,960
is still living in the not SQL database. So SQL is still living. So it's not going to disappear.

561
00:53:56,960 --> 00:54:02,640
Probably it's going to be part of another solution, more NIGGard, more harder, more something. So I

562
00:54:02,640 --> 00:54:09,200
don't think it's going to disappear. Okay, yeah, oh, we're having a little bit all of time, I see,

563
00:54:09,200 --> 00:54:16,000
but yeah, I have in every session I have a reference firewall, so I give you a short,

564
00:54:16,000 --> 00:54:23,120
yeah, short short short questions and you give a short answer, okay? Okay. Lakehouse or warehouse?

565
00:54:23,120 --> 00:54:26,320
Lakehouse. Import mode or direct lake?

566
00:54:26,320 --> 00:54:36,800
Wow. Wow, wow, wow, depends depends for AI, direct lake for report import mode.

567
00:54:38,480 --> 00:54:43,840
Power BI. That's to go our browser based development. Power BI desktop.

568
00:54:43,840 --> 00:54:50,880
SQL Python. Oh, they're different. They're different. Like a

569
00:54:50,880 --> 00:55:01,280
jacolic cake or cookies cake. Yes, it's different. Yeah, SQL for database and Python for

570
00:55:01,280 --> 00:55:12,400
machine learning. Yeah, what I prefer, I prefer both. Yeah, I don't. Sorry. Which one?

571
00:55:12,400 --> 00:55:19,920
That's our SQL. SQL. Okay, notebooks or pipelines? No books.

572
00:55:19,920 --> 00:55:29,920
I calculate columns or measures. Measures. One enterprise, the Mantic model or multiple domain

573
00:55:29,920 --> 00:55:42,400
models. Onto the models. Yeah, it's not there's another one. I prefer semantic models because

574
00:55:42,400 --> 00:55:49,280
the scheme was 100%, but now when you try to connect to get a very, very, very good semantic model,

575
00:55:49,280 --> 00:55:57,120
that is not working. So the onto the models work for that. So yeah.

576
00:55:59,280 --> 00:56:03,120
self-sales freedom or centralized control. Centralized control.

577
00:56:03,120 --> 00:56:06,000
The most underrated fabric feature.

578
00:56:06,000 --> 00:56:17,360
Yeah, I cannot say because I'm working in what private something of public that is soup. But now,

579
00:56:17,360 --> 00:56:26,160
fabric agents, fabric agents use that is a very, very, very, just do nice and public preview.

580
00:56:26,160 --> 00:56:34,240
It's working and we implemented a couple of companies right now and they are fabric agent.

581
00:56:34,240 --> 00:56:39,440
How to that? MCT or MVP? MVP.

582
00:56:39,440 --> 00:56:46,480
Yeah, yeah. MVP is a very good community. We speak a lot. Yeah.

583
00:56:46,480 --> 00:56:51,440
I every time get this on somewhere.

584
00:56:54,400 --> 00:57:01,600
MCT is on your purpose. It's a good tool, but it's a certification to allow you to teach.

585
00:57:01,600 --> 00:57:09,120
That is MCT. The community is a little bit close, but they are very, they're not

586
00:57:09,120 --> 00:57:14,960
shiny like the MVP. And we become these. You got the community, you have events. Yeah, it's a very

587
00:57:14,960 --> 00:57:21,040
good community. Yeah, when such a dollar call you and say, Walter, you get all the money and

588
00:57:21,040 --> 00:57:28,400
resources for Microsoft. You want to develop the one feature on the data platform. What will it be?

589
00:57:28,400 --> 00:57:35,680
The topic of...

590
00:57:35,680 --> 00:57:45,120
Yeah, it's a good question. The answer is Excel.

591
00:57:48,080 --> 00:57:53,840
Why? Because Excel is a must-useful tool for a lot of people. It's very easy to use.

592
00:57:53,840 --> 00:58:02,160
Every time people are using Excel, Excel is the tool that all the world economy is supported.

593
00:58:02,160 --> 00:58:10,000
So, yeah, we need to put more money into that because every time Excel is getting more using,

594
00:58:10,000 --> 00:58:20,400
more multi-porchos, people need that. Excel needs a very good refresh. What guests should I invite next

595
00:58:20,400 --> 00:58:25,360
and what is the secret question I can ask? Oh.

596
00:58:30,800 --> 00:58:40,000
Gaston Cruz from his, from the White Paths is living in the States since 10 years.

597
00:58:40,000 --> 00:58:47,520
It's one of the director of this Lallem company and Microsoft and really their platform.

598
00:58:47,520 --> 00:58:56,240
So, you can invite him and make this question signups of fabricants.

599
00:58:58,480 --> 00:59:06,000
Yeah. Yeah, thank you for staying with me. So, my closing question is, what is the one thing people

600
00:59:06,000 --> 00:59:14,560
should take away from this session? Oh, good question. Say that again, please.

601
00:59:14,560 --> 00:59:20,960
What's the one thing people should take away from this session today?

602
00:59:24,720 --> 00:59:36,160
Get into the semantic model and on top of the models. That is a good thing. I would think they need to

603
00:59:36,160 --> 00:59:41,440
learn and make a deep dive into that. It's the future. It's the part of the future.

604
00:59:41,440 --> 00:59:49,200
Yeah. Then I say, you're welcome. Thank you for joining me on the podcast. I think you help us

605
00:59:49,200 --> 00:59:57,120
understand why a success lie does not begin with a chat prompt or even a language model.

606
00:59:57,120 --> 01:00:01,200
It begins with Artichag Chaud Trust, and shared business division.

607
01:00:01,200 --> 01:00:06,800
They finish it. Yeah, responsible governance and yeah, so the mantic lay-acquip ability.

608
01:00:06,800 --> 01:00:14,080
And also, thank you for let us look in your books, in your framework. And yeah, in your frameworks,

609
01:00:14,080 --> 01:00:22,240
that was also amazing. Thank you so much. And yeah, for the guests on the mcc65 podcast,

610
01:00:22,240 --> 01:00:28,720
we will connect or learn more about water. You will find all the data in the show notes on the button

611
01:00:28,720 --> 01:00:34,480
on the mcc65 of them podcast. And yeah, thank you for being here. This was amazing.

612
01:00:34,480 --> 01:00:39,600
Oh, thanks to you for being with me, Dechenen. And be happy to be here. So, thank you, thank you.

613
01:00:39,600 --> 01:00:44,560
Okay, goodbye. Goodbye.