1
00:00:11,890 --> 00:00:15,450
Hello and welcome to my podcast 
Azure Tech Talk. 

2
00:00:15,490 --> 00:00:18,970
Last month I attended Microsoft 
Build conference held in 

3
00:00:18,970 --> 00:00:21,050
Seattle. 
Obviously I didn't go there 

4
00:00:21,050 --> 00:00:24,930
physically but it was on online.
Their experience was amazing and

5
00:00:24,930 --> 00:00:28,210
this is one of the conference 
which I always looking forward 

6
00:00:28,210 --> 00:00:30,330
for it. 
You learn a lot of new things, 

7
00:00:30,640 --> 00:00:35,080
technology, Microsoft releasing 
everyday and you probably hear 

8
00:00:35,080 --> 00:00:38,480
about like what's new coming out
in, in this kind of conference. 

9
00:00:38,600 --> 00:00:42,520
So I'm, I'm not going to go 
through all the texts which they

10
00:00:42,520 --> 00:00:45,760
have released and announced 
where in, in that conference. 

11
00:00:46,040 --> 00:00:49,240
But what I'm going to do is like
looking at my some of the 

12
00:00:49,240 --> 00:00:52,480
favorite things which I wanted 
to share with you, which which I

13
00:00:52,480 --> 00:00:55,520
think is brilliant probably 
going forward because what's 

14
00:00:55,560 --> 00:00:59,600
happening currently right now is
everybody is going towards 

15
00:00:59,640 --> 00:01:02,680
artificial intelligence. 
So you look at Amazon, you look 

16
00:01:02,680 --> 00:01:05,920
at Google, and then you come 
back to Microsoft is building 

17
00:01:05,920 --> 00:01:09,120
huge things in using the 
artificial intelligence. 

18
00:01:09,120 --> 00:01:13,240
In my personal opinion, what 
what's happening is now is they 

19
00:01:13,240 --> 00:01:17,280
are making AI accessible to 
everybody rather than it's 

20
00:01:17,280 --> 00:01:20,920
becomes difficult to utilize it 
and incorporate into your 

21
00:01:20,920 --> 00:01:23,440
application. 
It's now becoming easier to 

22
00:01:23,440 --> 00:01:27,760
incorporate in your application,
making it more artificial 

23
00:01:27,760 --> 00:01:30,280
intelligence so it can make 
decisions for you. 

24
00:01:30,360 --> 00:01:34,360
I'll give you a very quickest 
example with Azure AI Foundry. 

25
00:01:34,360 --> 00:01:38,040
It's it's now very easy to build
those kind of models and train 

26
00:01:38,040 --> 00:01:41,920
them with your custom data. 
And on top of it, it's it's easy

27
00:01:41,920 --> 00:01:45,160
to build agents using your those
models now. 

28
00:01:45,320 --> 00:01:48,960
And it's now in your fingertips.
You don't need that much kind of

29
00:01:48,960 --> 00:01:52,240
knowledge. 
It's all in user interface and 

30
00:01:52,280 --> 00:01:56,600
with very basic level how to 
build the model like kind of 

31
00:01:56,600 --> 00:01:58,840
user guides are available for 
you now. 

32
00:01:59,120 --> 00:02:03,000
So once you build those models, 
they provide you REST APIs which

33
00:02:03,200 --> 00:02:07,600
with easy integration into your 
existing application, or maybe 

34
00:02:07,600 --> 00:02:10,680
you want to build something new,
you can incorporate that kind of

35
00:02:10,680 --> 00:02:14,480
model into your application. 
And that model is hosted in 

36
00:02:14,480 --> 00:02:16,760
Azure. 
You only pay for the compute 

37
00:02:16,760 --> 00:02:20,960
process, the model it takes to 
actually return you the results 

38
00:02:20,960 --> 00:02:24,160
or do the computation power. 
But what I'm telling you here is

39
00:02:24,160 --> 00:02:28,480
like back in the old days where 
you have to be a core Python 

40
00:02:28,480 --> 00:02:31,800
developer, need to have an 
understanding of like how the AI

41
00:02:31,800 --> 00:02:34,560
actually works. 
Then you build the model, you 

42
00:02:34,880 --> 00:02:38,080
tune it and then you train it 
with your data. 

43
00:02:38,080 --> 00:02:42,400
Now this is become really easy 
for everybody to just go on a 

44
00:02:42,400 --> 00:02:46,480
journey of learning artificial 
intelligence and start building,

45
00:02:46,480 --> 00:02:49,160
utilizing ready to meet ready 
made models. 

46
00:02:49,360 --> 00:02:52,840
Just train them and use them in 
your application, which is, 

47
00:02:52,840 --> 00:02:55,800
which is incredible to be 
honest, like developers. 

48
00:02:55,800 --> 00:02:58,360
Now you talk about the 
developers who are front end, 

49
00:02:58,360 --> 00:03:01,120
back end developers or full 
stack developers wouldn't take 

50
00:03:01,120 --> 00:03:03,680
that much time to actually go 
and learn on a basic 

51
00:03:03,680 --> 00:03:07,840
foundational AI course, learn 
about AI Foundry and learn about

52
00:03:07,840 --> 00:03:11,160
the basic concept of how to 
build and how to actually 

53
00:03:11,160 --> 00:03:13,720
consume a bottle. 
So it's, it's more about like 

54
00:03:13,720 --> 00:03:16,960
consuming rather than building. 
So you train the model with your

55
00:03:16,960 --> 00:03:19,040
data and it's ready to be 
utilized. 

56
00:03:19,240 --> 00:03:22,840
So anyways, like few things to 
discuss with you because there 

57
00:03:22,840 --> 00:03:26,400
was plenty of things they 
discussed explored in their 

58
00:03:27,280 --> 00:03:30,160
conference because it lasted for
two to three days. 

59
00:03:30,360 --> 00:03:33,280
But the key things which 
actually I'm going to share with

60
00:03:33,280 --> 00:03:37,720
you is about how they have 
evolved the GitHub copilot, 

61
00:03:37,720 --> 00:03:40,440
according agent. 
Now why you can do that. 

62
00:03:40,640 --> 00:03:44,240
The GitHub copilot can do a 
range of development tasks for 

63
00:03:44,240 --> 00:03:47,160
you autonomously. 
It can refactor your code, 

64
00:03:47,160 --> 00:03:50,440
improve your test coverage, 
fixing defects and even 

65
00:03:50,440 --> 00:03:53,040
implementing a new. 
It's becoming insane. 

66
00:03:53,040 --> 00:03:57,680
For example, a copilot agent can
ultimately help you do the 

67
00:03:57,680 --> 00:03:59,840
stuff. 
So it means like from the 

68
00:03:59,840 --> 00:04:02,800
productivity point of view, you 
will be able to deliver your 

69
00:04:02,800 --> 00:04:07,280
work faster than ever before. 
And therefore for even complex 

70
00:04:07,280 --> 00:04:11,440
tasks get a copilot will be able
to collaborate with other agent 

71
00:04:11,440 --> 00:04:14,200
across all the stages of 
software life cycle. 

72
00:04:14,200 --> 00:04:17,399
So what they are trying to do 
that this software development 

73
00:04:17,399 --> 00:04:21,560
life cycle, it's being 
incorporated by this new 

74
00:04:21,680 --> 00:04:25,640
artificial agents which can help
you do the work quicker. 

75
00:04:25,800 --> 00:04:29,040
So I'll give you one example. 
Like when you develop a piece of

76
00:04:29,040 --> 00:04:32,040
software, obviously you need to 
write some kind of unit testing 

77
00:04:32,040 --> 00:04:35,280
and basic integration testing. 
Rather you spend that time 

78
00:04:35,280 --> 00:04:39,320
writing that integration or unit
testing, the copilot can help 

79
00:04:39,320 --> 00:04:41,040
you out. 
And in the future, like if 

80
00:04:41,040 --> 00:04:44,440
you're going forward, like some,
some bugs appeared in your 

81
00:04:44,440 --> 00:04:48,200
application in that specific 
area, what it can help you out 

82
00:04:48,360 --> 00:04:52,720
is to fix that bug automatically
and even create a PR for you. 

83
00:04:52,840 --> 00:04:56,760
So I think this is this is one 
of the biggest step from the get

84
00:04:56,760 --> 00:04:59,720
up copilot, which which 
ultimately is going to help the 

85
00:04:59,720 --> 00:05:02,640
developers to speed up their 
delivery. 

86
00:05:02,640 --> 00:05:06,240
And if you look from the bigger 
picture point of view, a 

87
00:05:06,240 --> 00:05:10,000
customer wants some feature to 
be delivered in X amount of 

88
00:05:10,000 --> 00:05:12,760
time. 
Now it's possible because it can

89
00:05:12,760 --> 00:05:15,880
help you write with code, but 
then where the human 

90
00:05:15,880 --> 00:05:19,960
intervention comes in is to 
validate like the code which has

91
00:05:19,960 --> 00:05:23,040
been written is actually 
conforming to the customer 

92
00:05:23,040 --> 00:05:26,640
requirements as well. 
So that was one of the one of my

93
00:05:26,640 --> 00:05:30,520
favorite kind of announcement 
from the Microsoft Build 

94
00:05:30,520 --> 00:05:32,840
conference. 
The second one which is about 

95
00:05:32,840 --> 00:05:37,720
like modernization capabilities 
in GitHub Copilot means like in 

96
00:05:37,720 --> 00:05:41,840
the past, if it used to take you
a couple of days, months or 

97
00:05:41,840 --> 00:05:46,320
weeks probably to migrate your 
existing application to the new 

98
00:05:46,400 --> 00:05:52,800
kind of framework forexample.net
Framework 3.0 to dot net core 8 

99
00:05:52,800 --> 00:05:54,960
or 9. 
Because you have to touch all 

100
00:05:54,960 --> 00:05:58,400
the code base, look at the 
libraries, the packages which 

101
00:05:58,400 --> 00:06:02,200
you are using, how are you going
to transform them into the new 

102
00:06:02,200 --> 00:06:04,480
kind of framework? 
It was the kind of time 

103
00:06:04,480 --> 00:06:07,640
consuming like with the new 
announcement of GitHub Copilot 

104
00:06:07,640 --> 00:06:11,640
mode app modernization can it 
can do all things for you, even 

105
00:06:11,720 --> 00:06:16,360
your Java apps, your.net apps 
able to organize using the 

106
00:06:16,360 --> 00:06:21,160
faster UI agent and it can do 
the coolest assessment and even 

107
00:06:21,200 --> 00:06:24,840
remediate any kind of problems 
happened during the migration 

108
00:06:24,840 --> 00:06:29,480
from old framework to the new 
framework, even configuring your

109
00:06:29,480 --> 00:06:33,280
dependencies across hundreds of 
thousands of files. 

110
00:06:33,440 --> 00:06:37,600
So means like the work which 
used to take you about like a 

111
00:06:37,600 --> 00:06:40,920
month can be done in a week or 
maybe less than a week. 

112
00:06:41,080 --> 00:06:45,040
I've not tried it personally, 
but it's in public beta so you 

113
00:06:45,160 --> 00:06:47,480
probably going to go and give it
a try. 

114
00:06:47,480 --> 00:06:50,720
And I've got few applications 
with me but which has been 

115
00:06:50,720 --> 00:06:53,600
written quite a while ago. 
I'm going to give it a go but 

116
00:06:53,640 --> 00:06:55,480
but this is amazing. 
I think. 

117
00:06:55,480 --> 00:06:58,560
I think when when people think 
about modernization or 

118
00:06:58,560 --> 00:07:03,040
transformation of their existing
application, my personal kind of

119
00:07:03,040 --> 00:07:06,760
advice would be forced. 
You need to make sure like your 

120
00:07:06,840 --> 00:07:11,200
application has covered a 
substantial amount of unit 

121
00:07:11,200 --> 00:07:14,160
testing and integration test 
because it will help you 

122
00:07:14,160 --> 00:07:16,760
validate your customers 
requirements. 

123
00:07:16,920 --> 00:07:19,640
And then once it's done that 
then the next step is like how 

124
00:07:19,640 --> 00:07:22,520
you can upgrade that application
to the latest framework. 

125
00:07:22,520 --> 00:07:25,880
Not like I'm talking about from 
the architecture point of view, 

126
00:07:25,880 --> 00:07:29,480
but as it is how it can move 
from the older framework to the 

127
00:07:29,480 --> 00:07:33,560
newer framework. 
I think this is the kind of work

128
00:07:33,560 --> 00:07:37,400
where the developers feel not 
very happy because it's a very 

129
00:07:37,400 --> 00:07:40,640
kind of Labor work. 
You have to go through each file

130
00:07:40,800 --> 00:07:43,760
dependency libraries and make 
sure that you can you can 

131
00:07:43,800 --> 00:07:47,640
actually manage them easily. 
But with the modernization tool,

132
00:07:47,640 --> 00:07:50,320
you don't need to worry about 
the copilot will do all the 

133
00:07:50,320 --> 00:07:52,600
things for you. 
The thing where you have to come

134
00:07:52,640 --> 00:07:57,440
and help it is the manual 
intervention to make sure that 

135
00:07:57,440 --> 00:08:00,640
things are working exactly like 
the way. 

136
00:08:00,960 --> 00:08:04,840
The last thing about this one is
the copilot tuning in the 

137
00:08:04,840 --> 00:08:08,280
Microsoft 365. 
I think this is a very good and 

138
00:08:08,320 --> 00:08:11,080
it's it's a game changer 
probably. 

139
00:08:11,280 --> 00:08:14,760
So I can do that. 
You can you can use your 

140
00:08:14,760 --> 00:08:18,320
knowledge here to train the 
models on in on your company's 

141
00:08:18,320 --> 00:08:21,920
data on a specific domain. 
For example, either it's 

142
00:08:22,000 --> 00:08:26,120
accounting, financial or HR or 
maybe onboarding a new 

143
00:08:26,120 --> 00:08:29,760
technology, or maybe you're 
buying the stuff from the market

144
00:08:29,920 --> 00:08:34,440
and you have like a legal and 
they can feed in all the 

145
00:08:34,440 --> 00:08:36,480
recommends to them. 
And then what happened? 

146
00:08:36,480 --> 00:08:40,320
That agent will help you make 
the decisions right? 

147
00:08:40,520 --> 00:08:42,960
It can help you speed up the 
work for you. 

148
00:08:42,960 --> 00:08:46,360
So for example, you're 
purchasing a software from a 

149
00:08:46,360 --> 00:08:50,320
third party company and you have
a set of procedures rather than 

150
00:08:50,320 --> 00:08:54,440
you fine tune those procedures 
or write those documents to 

151
00:08:54,640 --> 00:08:58,240
actually on board those that 
third party kind of software 

152
00:08:58,480 --> 00:09:00,920
where you could do that. 
You can feed it into this 

153
00:09:00,920 --> 00:09:05,360
Copilot agent with an the 360 
app 5 app, which can help you 

154
00:09:05,560 --> 00:09:09,040
actually generate those kind of 
documents and even help you 

155
00:09:09,040 --> 00:09:13,560
write those kind of business 
cases to actually purchase that 

156
00:09:13,560 --> 00:09:16,440
third party software. 
I think this is huge in terms of

157
00:09:16,440 --> 00:09:21,520
like helping the colleagues, 
helping the staff today, 

158
00:09:21,520 --> 00:09:25,520
day-to-day staff, helping with 
their day-to-day kind of work. 

159
00:09:25,640 --> 00:09:29,480
I think it's, it's, it's, it's a
big thing, big step forward and 

160
00:09:29,480 --> 00:09:35,160
it can definitely, definitely 
going to help and the staff and 

161
00:09:35,160 --> 00:09:39,720
the colleagues within, within an
office environment to help and 

162
00:09:39,720 --> 00:09:43,080
speed up the process rather than
writing everything from the 

163
00:09:43,080 --> 00:09:44,800
scratch and following the 
process. 

164
00:09:44,800 --> 00:09:48,640
This is where the tuning can 
help you out and incorporate 

165
00:09:48,640 --> 00:09:53,400
into your existing processes and
it can help you even with your 

166
00:09:53,400 --> 00:09:57,000
Q&A, all these kind of thing. 
And you don't need to worry 

167
00:09:57,000 --> 00:10:01,080
about like looking into 
something which is probably in 

168
00:10:01,080 --> 00:10:03,480
in your old documents to find 
answers. 

169
00:10:03,480 --> 00:10:06,920
Once you feed in all the 
information to that copilot 

170
00:10:06,920 --> 00:10:10,320
tuning, it can help you and 
retreat those information 

171
00:10:10,320 --> 00:10:12,200
easily, even do the work for 
you. 

172
00:10:12,560 --> 00:10:15,200
So I think these announcements 
are really great. 

173
00:10:15,200 --> 00:10:18,320
I'm really looking forward to 
working, but then then exploring

174
00:10:18,320 --> 00:10:22,640
further And I thought like, 
maybe it's it's, it's good to 

175
00:10:22,640 --> 00:10:25,720
share with you if you haven't 
watched it or if you have 

176
00:10:25,720 --> 00:10:28,440
already watched it and you're 
trying to explore something. 

177
00:10:28,440 --> 00:10:31,920
But these are my favorite ones, 
which I think is great. 

178
00:10:32,120 --> 00:10:34,280
AI is changing, is changing the 
world. 

179
00:10:34,280 --> 00:10:36,800
We have to embrace it. 
We don't need to be scared of 

180
00:10:36,800 --> 00:10:39,600
it, to be honest. 
The world is changing. 

181
00:10:39,600 --> 00:10:41,440
It's a kind of evolution 
happening. 

182
00:10:41,600 --> 00:10:44,480
But rather than being scared, we
embrace it. 

183
00:10:44,480 --> 00:10:48,120
We learn about these things. 
And I don't personally think 

184
00:10:48,120 --> 00:10:52,000
like AI is going to replace 
your, your, your kind of job. 

185
00:10:52,280 --> 00:10:55,400
But what I think it's like, it's
definitely going to speed up 

186
00:10:55,640 --> 00:10:59,840
because when you are delivering 
A requirement to your end user 

187
00:10:59,840 --> 00:11:03,880
or your customer, the most 
important thing for them is like

188
00:11:03,880 --> 00:11:07,040
how quickly that can be 
delivered to us, right? 

189
00:11:07,280 --> 00:11:10,560
And you always think, think 
about giving the quality and the

190
00:11:10,560 --> 00:11:13,200
value back to your customers, 
right? 

191
00:11:13,440 --> 00:11:18,080
And if you don't give that value
in a very specific time, which 

192
00:11:18,080 --> 00:11:22,400
your customer has asked for, so 
you are upsetting them and it 

193
00:11:22,400 --> 00:11:25,400
means like they might lose a 
trust on you. 

194
00:11:25,600 --> 00:11:30,960
So probably with these AI tools 
coming up every day, enhancing 

195
00:11:30,960 --> 00:11:34,600
your work, I think it's it's 
helping you to speed up that 

196
00:11:34,600 --> 00:11:40,000
process, speed up the delivery 
of your end user kind of 

197
00:11:40,000 --> 00:11:45,640
requirement, but it also gives 
you the flexibility to actually 

198
00:11:45,640 --> 00:11:49,920
help and improve that process 
manually verifying from the 

199
00:11:50,200 --> 00:11:53,440
human point of view. 
Overall, I believe like these 

200
00:11:53,440 --> 00:11:59,120
are going in a very positive 
direction and I'm continue to 

201
00:11:59,120 --> 00:12:02,320
learn more about like how it's 
going to shape this world. 

202
00:12:02,440 --> 00:12:04,520
I think that's it from me on 
this one. 

203
00:12:04,520 --> 00:12:06,560
Do shame here with your 
feedback. 

204
00:12:06,560 --> 00:12:09,560
How did you find out and do do 
let me know like if you are 

205
00:12:09,680 --> 00:12:14,720
exploring about AI or anything, 
anything exciting, I'll catch 

206
00:12:14,720 --> 00:12:17,880
you up in my next podcast. 
Till then, thank you. 

207
00:12:17,880 --> 00:12:18,400
See ya.