文字稿 🔗
WEBVTT
NOTE
Transcription provided by Podhome.fm
Created: 07/03/2026 15:27:40
Duration: 2476.330
Channels: 1
1
00:00:05.120 --> 00:00:06.160
So,
2
00:00:06.799 --> 00:00:14.344
hey, man. It's good to see you again. Been too long. It's been a while. Indeed. Yeah. Thank you for having me. Yeah. Well,
3
00:00:14.985 --> 00:00:18.105
we're now in such interesting times and you are
4
00:00:18.585 --> 00:00:19.945
an advocate for
5
00:00:20.425 --> 00:00:21.704
GitHub Copilot,
6
00:00:22.025 --> 00:00:23.145
I think online,
7
00:00:23.384 --> 00:00:24.825
and for your customers as well.
8
00:00:25.800 --> 00:00:28.680
And I'm using tools that you created as well,
9
00:00:29.080 --> 00:00:36.760
and lots of my customers do that as well. And I always tell them to install things that you created. So I would love to talk about that as well.
10
00:00:37.080 --> 00:00:42.155
But maybe to start with, could you introduce yourself to the listeners?
11
00:00:42.394 --> 00:00:43.114
Yes.
12
00:00:43.195 --> 00:00:50.795
I'm Rob based in The Netherlands. I still call myself a DevOps consultant because that really frames the way that I think and the way that I approach things.
13
00:00:51.675 --> 00:00:52.475
So that helps.
14
00:00:53.480 --> 00:00:54.760
And I tend to help
15
00:00:55.000 --> 00:01:03.719
do that with my customers as well. I tend to help them with whatever do we need to get code into production because that's basically the focus of everything that is there.
16
00:01:04.759 --> 00:01:07.080
And from that, that really comes with a devil's mindset.
17
00:01:07.955 --> 00:01:12.835
I switched over to the GitHub platform, I wanna say six years ago. It's probably it's even already seven
18
00:01:13.235 --> 00:01:18.835
when GitHub Actions became a thing. I mean, it's also been interested
19
00:01:18.835 --> 00:01:22.899
in CICD as well because that helps with a lot of the automation parts.
20
00:01:23.700 --> 00:01:32.100
But also with the security around those platforms. And I was doing that on the Azure side or Azure Devo side, I should say. And then all of a sudden, we had good of actions, and that was new.
21
00:01:32.805 --> 00:01:39.205
And it has its own supply chain issues, so I dove straight into that. And it's been full time GitHub for me ever since.
22
00:01:40.245 --> 00:01:49.365
And still also on the focus of how can we get more out of the platform. So I tend to help customers with everything that that's
23
00:01:48.540 --> 00:01:49.740
purchased, basically.
24
00:01:50.300 --> 00:01:55.100
So that can be enterprise governance on how to set things up, for example. That can be
25
00:01:55.340 --> 00:02:05.405
how do we train engineers to actually understand how things work, either on how do you write your first pull request, for example, up to the point of how do we do supply chain management properly.
26
00:02:06.205 --> 00:02:11.405
And and, of course, you know, the breadth of the ecosystem that GitHub is. So that is quite a lot.
27
00:02:12.205 --> 00:02:21.320
For the last year and a half or so, that's really been a a full time dedication almost on GitHub Copilot, of course. It is a tool for a developer in my opinion.
28
00:02:22.200 --> 00:02:26.440
But, yeah, everybody saw that we need to do something with AI, and then they call us.
29
00:02:27.080 --> 00:02:28.040
Yeah. So,
30
00:02:29.080 --> 00:02:30.280
yeah, GitHub is huge.
31
00:02:30.995 --> 00:02:36.355
There's so much in there. Maybe we can stay there for a while before we dive into AI land. Like,
32
00:02:37.155 --> 00:02:37.955
GitHub
33
00:02:37.955 --> 00:02:43.075
has this thing which called advanced security and there's lots of stuff under there as well.
34
00:02:44.099 --> 00:02:51.380
What do you see customers using there? Like, dependent bot and stuff that's also under there. Right? Basically, everything that is there,
35
00:02:51.540 --> 00:03:00.405
and it stems from making your setup more secure. So that can be either your repository itself, making sure that you don't get all sorts of, weird things in there.
36
00:03:00.885 --> 00:03:03.845
That can be dependable for dependency scanning, for example.
37
00:03:04.724 --> 00:03:13.450
But there's also code scanning involved as well where you scan your own code instead of third party code for, hey, figuring out what is happening, how do certain things work,
38
00:03:15.050 --> 00:03:18.410
do I have SQL injection attacks in my own source code, things like that.
39
00:03:18.970 --> 00:03:22.730
And two weeks ago, I wanna say, maybe three already, they launched Code Quality.
40
00:03:23.225 --> 00:03:24.665
That's another
41
00:03:25.225 --> 00:03:28.825
product owner, the same sort of name. It's not necessarily the phone security.
42
00:03:29.225 --> 00:03:34.185
So that becomes a whole suite of enabling things in and around your repository as well.
43
00:03:34.584 --> 00:03:43.540
And, again, one of my little things that I really like to to work on as well because there's so much interesting things happening in supply chain and supply chain attacks these days.
44
00:03:44.180 --> 00:03:51.780
Yeah. Yeah. That's yeah. That's very important that you don't have, let's say, infected packages or packages with vulnerabilities,
45
00:03:51.780 --> 00:03:53.220
things like that in your code base.
46
00:03:53.765 --> 00:03:55.045
There's a lot
47
00:03:55.685 --> 00:04:01.685
and then if we zoom out a little bit because you already mentioned you first focus on Azure DevOps.
48
00:04:02.325 --> 00:04:09.800
Know it does also similar things to GitHub. You know, you host your code, that type of stuff. I remember back in the day we had a server
49
00:04:09.880 --> 00:04:14.280
under our desk and we did SVN and then Team Foundation Server,
50
00:04:14.520 --> 00:04:16.840
and then eventually that became Azure DevOps.
51
00:04:17.400 --> 00:04:17.960
So
52
00:04:18.840 --> 00:04:22.520
the Azure DevOps thing by itself, is that going away?
53
00:04:23.435 -->
Load full transcript
00:04:25.035
Yeah. That's always interesting.
54
00:04:26.075 --> 00:04:37.195
And it's always interesting because that is one of the questions we get asked as Microsoft consultants as well. Yeah. And the official answer is, of course, Microsoft has still stated that whatever they release right now, they will continue to support it for ten years,
55
00:04:38.180 --> 00:04:44.020
which is true. But also then looking at the other side is if you see where new features are being launched first,
56
00:04:44.500 --> 00:04:49.620
that is GitHub all the way. It's just ridiculous how fast GitHub is moving and operating in that that
57
00:04:49.940 --> 00:04:50.340
direction.
58
00:04:51.075 --> 00:05:02.355
All of the new shiny things are on the GitHub side. GitHub's phone security for Azure DevOps is a thing, but I think we waited, like, two and a half years before they actually launched that after GitHub's phone security became a thing.
59
00:05:03.080 --> 00:05:04.040
Copilots,
60
00:05:04.040 --> 00:05:12.040
we've been doing that for four or five years now on the GitHub side. Azure DevOps has just launched their private preview of two or three of the features
61
00:05:12.360 --> 00:05:14.920
after years of their so, yes,
62
00:05:15.855 --> 00:05:21.055
it is not going away in my opinion. I think there's way too many users still using that on a day to day basis.
63
00:05:22.175 --> 00:05:26.175
But, yeah, if you wanted to have the new shiny features, then you go to GitHub.
64
00:05:26.335 --> 00:05:36.840
And, also, there's a perfectly fine setup where you can use both. Even licenses, for example, is relatively trivial to also get a GitHub Enterprise license these days if you already have an Azure DevOps license.
65
00:05:37.320 --> 00:05:38.919
So there's plenty
66
00:05:38.919 --> 00:05:43.800
of benefits of saying, hey. We're going to stick with Azure DevOps for the things that we really need it for.
67
00:05:44.384 --> 00:05:46.145
And that's often, for example,
68
00:05:46.625 --> 00:05:52.945
we've have tons of experience in pipelines, and we've created a lot. So why not leave them there, for example?
69
00:05:53.585 --> 00:06:00.270
Azure boards is a big thing. Azure test plans, those things don't have an equivalent on the GitHub side.
70
00:06:00.510 --> 00:06:03.950
So it's perfectly fine to stay with those on the platform where it works,
71
00:06:04.270 --> 00:06:09.070
and then migrate your source control over to GitHub and start doing Copilot on your source code, for example.
72
00:06:10.294 --> 00:06:15.735
Right. So to get benefits from GitHub, it's already enough to just move your repositories.
73
00:06:15.975 --> 00:06:21.015
That's the the biggest driver we see for migrations these days. Get your source code over because then
74
00:06:21.255 --> 00:06:26.135
you get access to additional tooling, both at phone security, for example, that does a little bit more
75
00:06:26.670 --> 00:06:30.030
because that has autopilot already enabled
on the GitHub side.
76
00:06:31.310 --> 00:06:35.870
But also, you get Cloud Agent. We can spin it up autonomously.
77
00:06:36.990 --> 00:06:49.205
You get access to the review agent that is there. You get access to the chat from GitHub for Copilot. So there's a lot of functionality that you get additionally available if your source code is hosted on github.com.
78
00:06:49.685 --> 00:06:51.845
And just to to give an indication there,
79
00:06:52.805 --> 00:07:06.700
we recently created a training around that. And that training by itself, what are all the features on github.com if you have Copilot, is two hours of just going through all of the features that is there. It's ridiculous. So there's a lot of catch up that Azure DevOps still has to do in that regard.
80
00:07:07.100 --> 00:07:10.380
So, yeah, starting with source control migration is usually
81
00:07:10.780 --> 00:07:11.820
the easiest partner.
82
00:07:12.595 --> 00:07:13.315
Okay.
83
00:07:13.715 --> 00:07:14.354
Cool.
84
00:07:14.595 --> 00:07:16.514
So, yeah, Azure DevOps,
85
00:07:16.595 --> 00:07:31.180
GitHub, GitHub, the repositories in GitHub then as an enabler for all sorts of features like the cloud agent, GitHub Copilot, Cloud Agent, all sorts of other stuff. And then GitHub Copilot is then just a feature of GitHub,
86
00:07:31.340 --> 00:07:37.020
which you can also use without having your repos in there, right? No. Just just on anything really.
87
00:07:38.139 --> 00:07:42.139
And that is really cool. So I've been using that now for years,
88
00:07:43.075 --> 00:07:45.155
as long as it's been out kinda
89
00:07:45.395 --> 00:07:52.035
and seen the evolution. So it's still very new, right? But the capabilities that this thing has is just
90
00:07:52.355 --> 00:07:52.995
it's
91
00:07:53.235 --> 00:07:54.115
mind
92
00:07:54.115 --> 00:07:59.370
blowing still to me to this day. It's running right now here in GitHub
93
00:07:59.449 --> 00:08:03.930
Copilot desktop app. I'm having it do something with Opus 4.8,
94
00:08:03.930 --> 00:08:05.610
which is so expensive.
95
00:08:05.930 --> 00:08:07.770
But, you know, just let it cook.
96
00:08:08.090 --> 00:08:10.090
I'm trying to see if I can
97
00:08:10.525 --> 00:08:21.565
get an email from somebody that to say, hey. Stop using all these tokens. It's getting too expensive or something. Yep. That's usually the financial department that will find you. Yeah. We'll see. I haven't I'm trying.
98
00:08:22.669 --> 00:08:29.070
Nothing yet. But let's see. I'm doing my best. Yep. So so what's your experience with GitHub Copilot?
99
00:08:29.710 --> 00:08:49.985
Yeah. I I'm at the point where if I join a new project and I'm not allowed to use it, I won't join the project. Okay. This this is now a a minimum requirement that you need to have access to these things. Mhmm. Because my value as an engineer is in the way that I think and in the way that I produce stuff and not necessarily in the way that I hand by
100
00:08:51.300 --> 00:08:54.260
create code by hand, I would say. Yeah.
101
00:08:54.980 --> 00:09:01.940
And I can think pretty fast, but I can definitely not type that fast. So that's where I really can help me along with those things.
102
00:09:02.660 --> 00:09:07.735
So, yeah, I'm an advocate of at least using it where it makes sense. There's definitely use cases where it doesn't make sense.
103
00:09:08.695 --> 00:09:13.015
But, yeah, for the most of the things that I tend to do, I I work a lot of
104
00:09:13.415 --> 00:09:15.815
big picture type of projects as well.
105
00:09:16.580 --> 00:09:18.500
It's a lot of architecture overview,
106
00:09:18.500 --> 00:09:23.540
sometimes a lower level scripting and things like that, and it is just amazing for that. So if you really
107
00:09:24.180 --> 00:09:26.580
know how to use it, and that's an interesting thing,
108
00:09:27.380 --> 00:09:32.100
then you can get so far with these tools. As long as you have the right guidelines in place
109
00:09:32.274 --> 00:09:36.115
and you have realistic expectations of these tools, that's where it really shines.
110
00:09:36.675 --> 00:09:47.795
Yeah. And and that know how to use it. That's kind of a a loaded term. Isn't it just as simple as just typing into the text box and that's it? Yep. That's usually the the the whole bare minimum that is there.
111
00:09:48.650 --> 00:09:55.770
And that's what I see with customers all the time as well. We regularly do customer events. The last time we had an event, we had 30
112
00:09:55.930 --> 00:09:57.690
potential customers there.
113
00:09:58.250 --> 00:10:00.890
Some of them that we've helped get on to Ash Devils, for example.
114
00:10:01.895 --> 00:10:04.055
And I'm an online consultant,
115
00:10:04.055 --> 00:10:10.295
of course. Right? So I start asking questions like, hey. How many of you actually do Copilot already? It's like 8080% or something.
116
00:10:11.495 --> 00:10:19.150
How long? Some of them already more than half a year, for example, so you get a feel of where they are. And then you say, how many people actually enabled
117
00:10:19.150 --> 00:10:20.110
engineers
118
00:10:20.110 --> 00:10:22.190
more than here's a license, have fun.
119
00:10:22.910 --> 00:10:26.910
And then, like, five hands were still up in the air of 30 different organizations.
120
00:10:27.230 --> 00:10:29.630
And then you say, okay. And I'll be honest.
121
00:10:30.495 --> 00:10:36.655
Is that more than here's a license and here's a YouTube video of half an hour and that's it? And then all of it has one.
122
00:10:37.135 --> 00:10:40.335
And then I say, I've helped set up the training curriculum
123
00:10:41.055 --> 00:10:44.175
for this, and we are currently at fourteen hours of training.
124
00:10:45.070 --> 00:10:56.750
Just to give an indication of there's so much that you learn you need to learn to be able to get the actual not necessarily get the actual results, but get great results out of that at a speed where it makes sense
125
00:10:57.505 --> 00:11:04.705
without necessarily using Opus 4.8 for everything and just burning all of the cash that you have there. Oh, come on. That
126
00:11:05.345 --> 00:11:06.225
was too easy.
127
00:11:07.505 --> 00:11:15.440
No. That's what we really often see. That people get a license. They get a basic minimum understanding of what it could do, and they start typing in a chat editor.
128
00:11:16.080 --> 00:11:32.225
And then often after half an hour, they have a lot of frustration off. I set it to fix the bug, it didn't fix the bug. And then I look at the prompt and go, yeah, you really said it to fix the bug, but you didn't tell where the bug was. What is it? And how does it actually represent itself? Do you have a log file somewhere? No context whatsoever.
129
00:11:33.185 --> 00:11:36.865
And that is usually the biggest eye opener of. You really need to spend some time there.
130
00:11:37.580 --> 00:11:41.260
Even how I approach training, for example, we tend to give people a training,
131
00:11:41.580 --> 00:11:49.180
and then we wait a week before we do a follow-up training because they need to get hands on time to absorb the the things that we've just shown.
132
00:11:50.055 --> 00:11:53.255
And just to give an indication of that, when we started doing Copilot,
133
00:11:53.655 --> 00:11:55.895
we were doing a lot of enablement of customers.
134
00:11:56.775 --> 00:12:04.135
And I've been giving training at that point for, I wanna say, eleven, twelve months together with a colleague who's been doing the same for other customers as well.
135
00:12:05.550 --> 00:12:25.385
I gave a demo, and then we went for coffee. And during coffee, they came to me and said, I didn't know you could do that with Copilot. I've learned something new. And that was a coworker that has been doing this for almost a year back then. Then we switched roles after the break, and his first demo was to me completely new. I've never thought of it doing it that way. And then you go, wow.
136
00:12:26.345 --> 00:12:38.790
And eventually, I looked back and I started to list out all of those moments that I had, for example. And I created some YouTube videos around that, and that became an hour and twenty minutes of nine moments of enlightenment as I called it,
137
00:12:39.110 --> 00:12:42.470
where I, as a trainer working on this on a day to day basis,
138
00:12:43.270 --> 00:12:53.025
went, oh, but I didn't know you could also do this. And, oh, if I change the way that I approach these tools and I get more value out of that. And looking back, I realized that that nine
139
00:12:53.025 --> 00:12:57.585
moments of enlightenment that I had took me six months to internalize that.
140
00:12:58.145 --> 00:13:01.500
Yeah. And then you're talking about an engineer with more than ten years experience,
141
00:13:01.660 --> 00:13:07.580
and then still you need half a year to absorb some of these things there before it really clicks and then you can actually go fast.
142
00:13:08.300 --> 00:13:10.780
And that's the the common mistake that we see being made here.
143
00:13:11.405 --> 00:13:14.125
We approach this like this as a hammer, and we give an
144
00:13:15.645 --> 00:13:26.720
a carpenter a new hammer and say, have fun. But we don't tell them it's a pneumatic hammer, and there might be rockets involved, and it really, really goes faster and can also go fast in the wrong direction if you use it the wrong way.
145
00:13:27.920 --> 00:13:30.720
Yeah, and there's a million ways to use it as well.
146
00:13:31.200 --> 00:13:32.000
You
147
00:13:32.080 --> 00:13:36.800
know, I always explain it as there's the core. That's the text box you type stuff into.
148
00:13:37.274 --> 00:13:38.954
You give it some
149
00:13:39.915 --> 00:13:43.035
context as in the things you're actually talking about.
150
00:13:43.995 --> 00:13:49.450
And then there's all this markdown and tools to control the thing and guide the thing a little bit,
151
00:13:49.930 --> 00:13:54.730
which is very confusing as well. Like, markdown, why is it markdown? Yeah. It's
152
00:13:55.290 --> 00:14:02.890
yeah. You gotta love markdown nowadays. But even just with saying, hey. I add files, for example, to the conversation because I think they're interesting.
153
00:14:03.555 --> 00:14:10.435
There's so much mishaps that are happening there as well, and especially now with, we're we're getting billed for the actual usage.
154
00:14:10.755 --> 00:14:23.680
I still see people just drag entire folders of log files into the context and then say, hey, fix this bug. That will be so helpful if you do one single search for the error and then paste in the five lines of log files that are really interesting.
155
00:14:24.000 --> 00:14:31.120
So having that basic understanding of what an LLM actually does with the code that you send in after you hit enter in a prompt,
156
00:14:31.745 --> 00:14:35.665
That is so important. I've seen people that got enablement sessions
157
00:14:35.904 --> 00:14:37.345
even from vendors,
158
00:14:37.584 --> 00:14:42.464
where they had, like, ninety minutes of demos and everything was shown, and then somebody raised their hand up and said,
159
00:14:42.785 --> 00:14:47.584
can you do a prompt against this code base and ask it about, the code complexity in this code base?
160
00:14:48.360 --> 00:15:08.154
And then the the person demonstrating it actually typed in that prompt, and we got an answer back. And everybody thought that was the actual code complexity number that was there. So after ninety minutes of explanation, they completely missed the basic things there that LLMs don't do computation. There's nothing really intelligent involved there. It's just trying
161
00:15:08.635 --> 00:15:11.515
to predict the next word or the next token that is there.
162
00:15:12.475 --> 00:15:25.450
And that is often skipped over these kinds of things. Whenever we try to do enablements, for example, we got four or five slides that actually
explain what an LLM is and what it does, and especially give all the examples where it can show that it doesn't work.
163
00:15:26.250 --> 00:15:32.025
And those are still the the benevolent silly things like give me a random number between one and a 100.
164
00:15:32.425 --> 00:15:39.625
And then you look at a group full of engineers, you say, do you actually know the the answer to this? And one out of 10 times, nobody has an answer.
165
00:15:39.945 --> 00:15:43.465
And then I I sort of heckled them that they're not really nerds
166
00:15:43.960 --> 00:15:45.640
because the answer is 42.
167
00:15:46.120 --> 00:15:54.680
That is what an LLM has been trained upon. That's nine out of 10 times that is the answer, especially for all the models. The newer models have some some ways to mitigate that.
168
00:15:55.240 --> 00:15:57.720
But even there, you can then show, for example,
169
00:15:58.345 --> 00:16:02.025
these days, most of the time, the next answer is 73.
170
00:16:02.665 --> 00:16:04.985
So one of the prime numbers that we use
171
00:16:05.305 --> 00:16:06.185
as well.
172
00:16:06.745 --> 00:16:13.545
So yeah. Those kinds of little things, they're they're key to having a realistic expectation of what you can do with an LLM,
173
00:16:14.310 --> 00:16:23.350
And that's often missed. So people think they type into a text box and magic will happen, but, yeah, it's not necessarily magic. You definitely need to check out the results.
174
00:16:24.630 --> 00:16:36.515
Yeah. Definitely. And is that something that you still do as well? Like when you ask a thing to do something, it spits out a bunch of code. Do you still look at the code? Less and less. It depends on what I'm trying to do.
175
00:16:38.940 --> 00:16:46.140
What I've I've grown into and probably something we should have done in the early days anyway, like we're we're like we're approaching coding.
176
00:16:46.700 --> 00:16:57.964
We always said, you should have a good harness, for example, around testing. CICD should be in place. Your test should actually be sensible tests. You can look at code coverage and things like that.
177
00:16:59.005 --> 00:17:08.860
And that's also still my devils background of I'm looking into those kinds of techniques to have them in place to have more trust in that the code actually does what it needs to do.
178
00:17:10.060 --> 00:17:14.380
And that can go to point to the point of, okay, I wanna summarize this data,
179
00:17:14.460 --> 00:17:29.155
write me the code and actually summarize the data, and I need to be able to trust that the sum of the results is actually the actual sum of what is happening there. That's the benefit with code is that you can actually look at it and see, yes, it's actually looping over everything and summarizing it the right way.
180
00:17:29.715 --> 00:17:36.435
That is helpful. And then with that, you can start zooming out of, okay, build me the unit test and actually validate this.
181
00:17:37.159 --> 00:17:44.119
Often, you can then get get the question of, yes, what you're now generating the unit test with AI. Can you still trust the unit test there?
182
00:17:44.600 --> 00:17:46.999
And I usually counter that with,
183
00:17:47.320 --> 00:17:56.964
we've been having the same discussions for the last thirty years. If you don't trust your unit test, throw away mutation testing to the mixing to see if your unit tests actually fail.
184
00:17:57.445 --> 00:18:01.364
If you don't wanna write all of the nitty gritty unit tests, maybe write progression tests.
185
00:18:01.924 --> 00:18:11.389
And I've been doing that in my career for most of the time anyway, so that's a natural go to of I wanna validate that the outcomes are at least in my realm of expectation,
186
00:18:12.350 --> 00:18:25.344
and then level up with some more spelunking usually. I I phrase that off. Let's try and figure things out because it's really interesting to see that if you have your test harness and then ask to a capable model,
187
00:18:25.985 --> 00:18:29.904
look at this code, look at the test harness, and tell me where my blind spots are.
188
00:18:30.304 --> 00:18:33.904
That's a whole different way of phrasing the the research that you're trying to do,
189
00:18:34.700 --> 00:18:41.659
and often it finds blind spots where you go, oh my god. I couldn't even realize my code could do this.
190
00:18:42.300 --> 00:18:47.260
So that's where I tend to do that. So it depends a little bit on am I writing scripts?
191
00:18:48.035 --> 00:18:52.994
Because I write a lot of scripts against systems like GitHub, for example, to validate certain things.
192
00:18:54.035 --> 00:18:57.955
And there, I tend to go into more of a sort of an investigation
193
00:18:58.755 --> 00:19:02.195
validation mode to check, hey. If I have something where
194
00:19:02.800 --> 00:19:04.640
I calculate the amount of
195
00:19:04.960 --> 00:19:08.800
pull request velocity for a repository, that's something you can still validate.
196
00:19:08.800 --> 00:19:13.040
So at least have sort of a sniff test of does this make sense here so no.
197
00:19:13.600 --> 00:19:15.120
That's what I tend to do for scripting.
198
00:19:16.405 --> 00:19:18.165
And then another option
199
00:19:18.165 --> 00:19:20.885
is I work a lot with web applications, for example.
200
00:19:21.365 --> 00:19:26.405
I am really fan of handing over tasks to, for example, Copilot Cloud Agent.
201
00:19:26.805 --> 00:19:29.205
And then in the instructions, it's always part of
202
00:19:29.810 --> 00:19:34.289
build the code, validate that it works, and show me a screenshot of the before and after.
203
00:19:34.930 --> 00:19:41.090
Makes it really easy to visualize. You check if the code is in the sort of realm that you wanted to have set up for.
204
00:19:41.410 --> 00:19:44.530
You can do some more testing on the outside if you need to.
205
00:19:45.315 --> 00:19:53.154
So I build in the tools and up to a level that gives me a sense of trust to be
able to push this to production for those kinds of things.
206
00:19:54.674 --> 00:20:04.359
Another use case that I specifically have, you mentioned it in the beginning, I write a couple of official studio code extensions these days, and those are really, really hard to automatically test.
207
00:20:04.679 --> 00:20:07.719
So there's only one thing that you can really do with big changes,
208
00:20:08.279 --> 00:20:10.200
run the damn thing and validate it yourself.
209
00:20:10.965 --> 00:20:24.404
And that's also for some of the things that are changing in the UI. I just run it and validate that it works. If it's something where I have a configuration file and a new model is discovered, for example, I need to display that. Yeah. I trust that I have my automation in place that it works.
210
00:20:25.290 --> 00:20:31.530
So those are some of the the techniques that you then use for working. Do you actually still need to write every single line of code?
211
00:20:32.170 --> 00:20:48.794
For most of the time, I build in so much test harness, for example, that I can trust that it actually does what it needs to do. And, of course, we still do the normal things. Right? You deploy to production sorta in a way that nobody sees it so that you can flip a switch internally, test it out, and validate if it works.
212
00:20:49.274 --> 00:21:06.370
Then put a layer of logging on top of that and then put a layer of incident sort of management on top of, hey. If we have a bug, we actually log the information and feed that back into an LLM system to improve it for next time. And all of a sudden, you get sort of a self healing situation, and then it becomes really interest.
213
00:21:07.695 --> 00:21:09.215
Yeah. That's cool, isn't it? Yeah.
214
00:21:10.735 --> 00:21:15.134
So this is all the stuff that we should have been doing already, including
215
00:21:15.135 --> 00:21:17.054
creating good specifications. Right?
216
00:21:17.615 --> 00:21:20.575
So now we're finding out that our specifications
217
00:21:20.575 --> 00:21:21.535
might not be
218
00:21:22.320 --> 00:21:23.119
specific.
219
00:21:23.200 --> 00:21:23.839
And
220
00:21:24.000 --> 00:21:25.919
so we need to go back to those
221
00:21:26.240 --> 00:21:28.880
yeah, the basics, right? Specifications,
222
00:21:28.880 --> 00:21:30.399
deterministic controls,
223
00:21:30.480 --> 00:21:33.279
tests, quality gates, that type of stuff.
224
00:21:34.000 --> 00:21:38.864
I like to I'm starting to think about this as, you know we used to.
225
00:21:39.904 --> 00:21:45.024
Outsource a lot of software development, so you hire somebody or a team that is in a different country somewhere
226
00:21:45.184 --> 00:21:48.384
and to do that you need to write very good specifications
227
00:21:48.384 --> 00:21:53.220
and you need to have extremely good tests because the output is nondeterministic.
228
00:21:53.300 --> 00:21:54.980
Sometimes it works,
229
00:21:54.980 --> 00:21:57.860
sometimes it doesn't. This is kind of similar to that.
230
00:21:58.420 --> 00:22:00.900
Although sometimes the results are better depending
231
00:22:00.900 --> 00:22:19.915
on the models and things that you choose, but you need those controls around it and also then humans to test it, for instance. Exactly. And that's what you see happen now more and more depending on sort of which part of the industry you're in. I've had conversations with customers where they said, we wanna give the engineering team AI, in this case, Copilot,
232
00:22:21.510 --> 00:22:26.309
And we have a specific team in mind because they're starting a greenfield project in three months, and
233
00:22:26.710 --> 00:22:38.325
they're almost ready to go. I said, cool. Let's start there. And they said, yeah. But now that we're thinking about it, we're not going to give the engineers Copilot yet because our business analysts are not done yet writing all the specs.
234
00:22:38.965 --> 00:22:39.925
And I went,
235
00:22:40.325 --> 00:22:44.485
this is your chance to actually bring the business analyst into the team,
236
00:22:44.725 --> 00:22:48.725
make them write the the instructions or the the user stories together
237
00:22:49.279 --> 00:22:52.399
so that we get better results. I've always been a fan of
238
00:22:53.519 --> 00:23:07.935
end to end testing by writing things like Cucumber specs and things like that because that enables you to write natural language of this is my rule. If you have that covered, you can test the dentin from the outside and all of a sudden, a lot of your unit tests go away
239
00:23:08.095 --> 00:23:14.415
and you bring in those business folks on board. They write the specs. Often, they write conflicting specs. That's the interesting part.
240
00:23:15.840 --> 00:23:23.999
And how you can find that easier, you can write better specs, and we're almost in the direction of some people are already talking about
241
00:23:24.320 --> 00:23:25.440
dark factories
242
00:23:25.520 --> 00:23:30.080
where you just push in a spec and code changes come out the other end, and you have no clue what happened in between.
243
00:23:31.045 --> 00:23:32.965
Yep. So, yeah, if you if you make
244
00:23:33.605 --> 00:23:35.285
all of the the stakeholders,
245
00:23:35.285 --> 00:23:40.725
the business analysts, bring them into the team, now you have a very powerful setup of what are we actually implementing.
246
00:23:41.445 --> 00:23:46.485
And we've been having that conversation for the last thirty years as well of when do we actually add value to production.
247
00:23:47.260 --> 00:23:50.139
Yeah. We haven't figured out the answer. That's the interesting part.
248
00:23:51.260 --> 00:24:03.645
No. And now instead of an guesstimated man hours, now you actually get a number of it costs this much because we can see it. Yep. So it's this many tokens, this amount of
249
00:24:04.045 --> 00:24:08.044
euros, and so that's what it cost costed for this feature.
250
00:24:08.205 --> 00:24:14.765
Was it
worth it? I don't know. But it becomes more visible now. And it becomes all of a sudden a a conversation point
251
00:24:15.600 --> 00:24:21.919
because it can be very flexible in that sense as well. It used to be we had people hours
252
00:24:21.920 --> 00:24:24.639
and that took us to actually make the changes there,
253
00:24:24.880 --> 00:24:29.679
and we had license calls and maybe some hardware calls and that was it. And all of a sudden, we have
254
00:24:30.945 --> 00:24:40.224
cost in the mix that are very incidental. Your prompt might actually take you twenty minutes, and it cost you 2,000,000 tokens. And if I do the same one, it might cost me 5,000,000 tokens.
255
00:24:41.025 --> 00:24:47.669
And figure then out which one of us who had a meaningful session actually contributed value. Super hard to to define.
256
00:24:48.310 --> 00:24:51.190
But now that it actually comes with a monetary cost,
257
00:24:51.350 --> 00:24:55.509
all of a sudden, everybody's kicking and screaming of, we need to keep this under control again.
258
00:24:55.990 --> 00:24:56.870
It's really interesting.
259
00:24:58.375 --> 00:25:02.215
It is interesting, and that is where are we? June? July?
260
00:25:03.095 --> 00:25:05.335
So we've had a month of
261
00:25:05.575 --> 00:25:08.455
usage based billing now with GitHub Copilot,
262
00:25:09.015 --> 00:25:12.054
where previously it was a premium request units basically for free.
263
00:25:12.870 --> 00:25:17.429
So now people are kinda tasting what this thing actually costs to use,
264
00:25:17.830 --> 00:25:20.230
and some of them are surprised, of course.
265
00:25:20.630 --> 00:25:25.750
I get that. And you you already said it. You built some extensions.
266
00:25:26.345 --> 00:25:28.745
You have a very nice one that I use
267
00:25:29.465 --> 00:25:30.184
daily
268
00:25:30.265 --> 00:25:32.985
and I get all my customers to use as well,
269
00:25:33.305 --> 00:25:36.505
and that is called AI Engineering Fluency.
270
00:25:36.505 --> 00:25:37.705
I'm looking at it right now.
271
00:25:39.490 --> 00:25:48.369
This is in Versus Code and other places as well. Right? Can you maybe talk about that and why you even created? Yeah. It actually started out as the Copilot token tracker
272
00:25:48.450 --> 00:25:50.690
because I hated PRUs,
273
00:25:50.690 --> 00:25:52.929
premium regress units. Because
274
00:25:53.010 --> 00:25:58.025
it it was always hiding that there's actual cost involved when you talk to an L. Yeah.
275
00:25:58.505 --> 00:26:06.505
And I I have been pushing back to the teams on the GitOps side from day one of. I wanna see that. It comes with
276
00:26:06.825 --> 00:26:12.419
computation cost. It comes with monetary cost. It has an environmental impact. I wanna show that information.
277
00:26:13.380 --> 00:26:22.654
And somewhere in December last year, they did an update to Versus Code, and all of a sudden, they could show the information from your session. So which
278
00:26:23.054 --> 00:26:29.615
tools did it call, for example, what happened, how many tokens were used, and finally I had some information that I could run with.
279
00:26:30.095 --> 00:26:38.140
We were still paying in premium request units, so users only saw, hey, I I went down 10 premium request units this session, and that was it.
280
00:26:38.700 --> 00:26:42.700
So I start to work with, okay. We have the files on disk. I have Copilot,
281
00:26:42.700 --> 00:26:49.420
and I had some some time available to work on things. And because I was triggered off, I wanna see how far I can bring this forward.
282
00:26:50.145 --> 00:26:55.424
So literally started as figuring out all of your sessions on disk and just read the log files on your machine.
283
00:26:56.945 --> 00:27:03.185
Look into them and then look at things like chat turns, how long was your session, how many tokens did you actually go through.
284
00:27:03.930 --> 00:27:07.050
So that I could summarize that and then projects
285
00:27:07.130 --> 00:27:11.610
of, hey. If I look back at the last thirty days, I can actually see how many tokens you've used.
286
00:27:12.010 --> 00:27:17.530
There is some fuzzy calculation available on, hey. A token amounts to this amount of computation.
287
00:27:18.365 --> 00:27:25.885
This amount of computation, can actually express that in c o two cost, for example. So how much environmental impact that you actually have there.
288
00:27:26.845 --> 00:27:32.605
You can do the same thing for water usage for cooling a data center on average just to give an indication of what happens there.
289
00:27:33.250 --> 00:27:37.489
And if you have c o two, then you can also calculate how many trees you actually need to plant
290
00:27:37.650 --> 00:27:41.090
to be able to do something about that c o two impact.
291
00:27:41.330 --> 00:27:45.090
That's where it actually started off. I wanna have that kind of information available
292
00:27:45.455 --> 00:27:49.934
because there are people that say, hello, good morning every day to Opus four point eight.
293
00:27:50.495 --> 00:27:52.015
And that has a
294
00:27:52.495 --> 00:27:54.975
big impact on the back end of what is happening.
295
00:27:55.375 --> 00:28:03.090
And that's still a thing. I would go so far is that as a user, I would like to schedule certain things and keep environmental impact in mind.
296
00:28:03.410 --> 00:28:05.970
So if I have something that runs every single day,
297
00:28:06.290 --> 00:28:12.770
I would like to have the option to choose a data center in Sweden where that runs that runs on hydropower
298
00:28:12.770 --> 00:28:13.570
and things like that.
299
00:28:14.865 --> 00:28:26.545
But we're not still not there yet. So that's where it started in December of, I wanna have some information to show people that this is more than just asking something, a question, and you get an answer back. Notice actual impact hap
300
00:28:27.919 --> 00:28:31.840
And, yeah, of course, in good fashion, from there,
everything escalated. We
301
00:28:32.159 --> 00:28:40.799
dove deeper. We went broader. I've had some colleagues that spend an innovation day on this. So I think by now, six or seven people have contributed.
302
00:28:41.200 --> 00:28:43.440
It's open source, so people can contribute anyway.
303
00:28:45.125 --> 00:28:48.004
And we really started to go broader and
304
00:28:48.245 --> 00:28:52.325
a lot deeper in certain things as well. So by now, we support
305
00:28:52.725 --> 00:28:57.044
a lot of different AI tools that are available. So not just Copilot,
306
00:28:57.125 --> 00:28:59.205
ClotCode, for example, is being picked up as well.
307
00:28:59.980 --> 00:29:01.340
The new Mistralvibe,
308
00:29:01.340 --> 00:29:02.620
for example, that is currently
309
00:29:03.580 --> 00:29:05.419
might still be in beta. I'm not sure.
310
00:29:07.019 --> 00:29:16.755
It's being found. So all of those different harnesses that you can use and you name it. Even if it's OpenCode, if it's the pyre harness, we pick up the files from there as well.
311
00:29:17.555 --> 00:29:20.595
From that, we can actually start mapping your sessions.
312
00:29:20.995 --> 00:29:25.315
So how long was the session? How many chat turns did you actually have there?
313
00:29:27.235 --> 00:29:31.470
How much tools did you call in that session? Session? Are you very specific
314
00:29:31.470 --> 00:29:32.030
when
315
00:29:32.430 --> 00:29:37.550
you do prompting? Do you actually bring in context files and refs, for example, into your session?
316
00:29:38.190 --> 00:29:47.195
If you know all that kind of information, you can start to plot that in a chart to give you a little bit of insights, and then we can also give you very fine grained improvement
317
00:29:47.275 --> 00:29:52.234
tips there as well. If we see, for example, that Claude's code continuously
318
00:29:52.635 --> 00:29:53.515
automatically
319
00:29:53.515 --> 00:30:01.330
summarizes your session, that's an indicator that apparently you don't know what that does and what's the risk of compacting, for example, might be.
320
00:30:01.570 --> 00:30:07.410
So we can at least surface that information and say, hey. We see that this happens all the time. Maybe you wanna be a little bit more specific.
321
00:30:07.810 --> 00:30:19.094
We already know that compacting also causes a a cash miss in the next turn, for example. So, hey. We're paying for these things. Caching is the thing, and it's super helpful because that brings the the cost down.
322
00:30:19.414 --> 00:30:25.894
So we can actually surface that tip-off. Hey. This is what we see happening. Maybe you wanna look at some information around this and
323
00:30:26.215 --> 00:30:28.534
get better in the way that you're using these tools.
324
00:30:29.570 --> 00:30:43.010
So, again, this escalated completely and now has a fluency score in there where we look at different aspects of your usage. And we can see, for example, hey, in the the prompt engineering, you're scoring level three, and in the context engineering, you're scoring at level four, for example.
325
00:30:43.795 --> 00:30:46.355
And there we can at least give you some guidance.
326
00:30:48.835 --> 00:30:51.635
Super useful. So I'm I'm looking at it. I am
327
00:30:51.875 --> 00:30:56.755
in the fluency score. I am stage four AI strategist.
328
00:30:56.929 --> 00:30:57.649
Awesome.
329
00:30:58.770 --> 00:31:00.769
And I don't know if that's good.
330
00:31:01.330 --> 00:31:05.249
That is the highest level. We take people through different aspects.
331
00:31:06.370 --> 00:31:12.770
I'm pulling it up on this side as well to make sure that I have them in the right. And per aspect, we try to find if you're
332
00:31:13.165 --> 00:31:19.164
between stage one and four. So it starts with an AI skeptic. You use it, but not necessarily that often.
333
00:31:19.405 --> 00:31:23.164
And then you can graduate into an AI explorer, an AI collaborator,
334
00:31:23.165 --> 00:31:25.485
stage three, and then AI strategy is a stage four.
335
00:31:26.299 --> 00:31:31.499
And at that point, we don't really know which extra tips to give you, so that's a a good thing to be at.
336
00:31:32.140 --> 00:31:35.340
But we do that for, as I said, prompt engineering, context engineering.
337
00:31:35.740 --> 00:31:41.659
We look at your tool usage, for example. Have you enabled tools? Do you have enabled tools in your editor?
338
00:31:42.705 --> 00:31:53.585
The basic ones are always read file or write file, for example. But there's, of course, so much more that you can install in these editors, it's good to see either, a, you haven't been installed, but also, b, if you're actually using them.
339
00:31:55.110 --> 00:31:57.430
And then the last two aspects are customization
340
00:31:57.430 --> 00:32:03.750
and workflow integration. So across all of those topics, we look at, okay, this is some of the the metrics that we track.
341
00:32:04.150 --> 00:32:07.030
Where are you in your, basically, maturity
342
00:32:07.030 --> 00:32:08.230
of using these tools?
343
00:32:09.815 --> 00:32:10.375
Yeah.
344
00:32:11.415 --> 00:32:13.335
And so it also shows
345
00:32:13.335 --> 00:32:15.095
usage by editor.
346
00:32:15.655 --> 00:32:23.735
So cloud code for instance, also sometimes use. I see that show up cloud desktop, co work, and there's all sorts of places. SQL Server Management Studio of course.
347
00:32:24.630 --> 00:32:30.470
And you name it. So do you then need to install and test That's all of the fun part. And
348
00:32:30.790 --> 00:32:31.590
it is.
349
00:32:31.910 --> 00:32:43.954
I work for a company that is a Microsoft and GitHub partner, but I'm a consultant, so I'm not necessarily married to a specific product. I wanna have the best tool available that we can use both for me and the people that I train.
350
00:32:44.835 --> 00:32:48.354
And the only way to find out about those things is install them all.
351
00:32:48.995 --> 00:32:57.330
And that's
where the fun stuff first starts to happen. So I have accounts on most of these things available on working certain things. Some of them are free, luckily.
352
00:32:57.730 --> 00:32:59.810
But, yeah, I've got them all installed.
353
00:33:01.170 --> 00:33:02.930
That is fun. Yeah.
354
00:33:03.250 --> 00:33:09.965
So if you let's be honest. If you compare, let's say, Claude code to GitHub Copilot,
355
00:33:10.205 --> 00:33:12.524
different harnesses can have the same models.
356
00:33:13.804 --> 00:33:23.299
What do you think? Which one wins right now? Right? Can change It all depends on where your muscle memory comes from. That is the biggest one. So if you've been using cloth for two years,
357
00:33:23.620 --> 00:33:27.940
then probably the answer for that person will be cloth. The interesting part is that
358
00:33:28.420 --> 00:33:32.820
and I've had those folks in trainings as well. They looked at it at a certain point in in time,
359
00:33:33.485 --> 00:33:35.725
and then they ignored it for one or two years,
360
00:33:36.045 --> 00:33:41.804
and then they come back. I've had people in the training where they say, hey. This is the first getting started training on Get a Copilot.
361
00:33:42.125 --> 00:33:45.325
I've looked at it, it was crap. And you have two hours to convince me.
362
00:33:46.690 --> 00:34:07.575
What do do as a trainer? But still, after two hours, they came back and said, holy moly. I haven't looked at these tools for two years, and apparently, I missed this, that, and this, and I can also do that. It changes so quickly. And that's often how you see these these things being portrayed where somebody says, yeah, but I can schedule something in Claude and it runs every Monday and it does the magic for me. Mhmm. And I say, Copilot can do that as well.
363
00:34:07.975 --> 00:34:11.815
So the harness itself is becoming more and more
364
00:34:12.455 --> 00:34:19.140
fluid as well, and it's no longer a unique selling point. It's more of the experience that you have there and that you want to do.
365
00:34:19.860 --> 00:34:25.780
And I recently created an overview of these are all the the sort of the surfaces where you can use Copilot these days.
366
00:34:26.020 --> 00:34:31.380
It it's a massive slide off. You you can use this from your editor. You can use this from your CLI.
367
00:34:31.885 --> 00:34:37.565
You can run this from your editor and hand it over to the Cloud Agent, and then then it can do something autonomously
368
00:34:37.565 --> 00:34:47.900
there. You can trigger this from GitHub mobile and then run the session in Cloud Agent. You can actually go to the web and run a session in Cloud Agent. Cloud Agent actually has automations these days, and you can schedule them in for you.
369
00:34:48.619 --> 00:34:53.820
And it all then leads for me to the Copilot app because that thing is just freaking amazing.
370
00:34:53.980 --> 00:35:00.285
Let's see how far they got that thing to work. It was released and built
a month ago, I would say.
371
00:35:01.485 --> 00:35:04.925
But I've have had access to this since March,
372
00:35:05.565 --> 00:35:13.420
it is my go to. It is really energetic setup where everything is really focused on I wanna implement something.
373
00:35:13.820 --> 00:35:24.380
So the Copilot app has really been configured to say, whatever you're going to do, you're going to create a pull request because that is where the value of an engineer lives, and it's really geared towards all of those things.
374
00:35:25.835 --> 00:35:27.595
That's my go to these days,
375
00:35:28.474 --> 00:35:33.355
because the the the way that they think about it is differently. So Versus Code for me, for example,
376
00:35:34.075 --> 00:35:35.595
is really interactive.
377
00:35:35.595 --> 00:35:37.595
I wanna see the files that are being changed.
378
00:35:38.010 --> 00:35:43.770
I want to see the the harness go through the loop that it has, run the test, then maybe validate it from there.
379
00:35:44.730 --> 00:35:49.530
And then if I need a pull request from Versus Code, I need to prompt it, create a pull request, or do it myself.
380
00:35:50.250 --> 00:35:51.370
In the CLI,
381
00:35:52.164 --> 00:35:55.205
I tend to use it mostly for stuff I have on my machine.
382
00:35:55.605 --> 00:35:58.405
Find me this file or hey, if I have
383
00:35:58.724 --> 00:36:04.164
an issue on my machine, look at the logs, look at the stack trace, go for it, and then just plung through whatever is in there.
384
00:36:04.910 --> 00:36:17.150
And the Copilot app is really I trust that I have a good setup in my repository. I have my testing in place, for example, and then I can really go faster and just have multiple concurrent sessions and say, just go for it.
385
00:36:17.865 --> 00:36:26.825
And that gives me so much more power because I have all of the sessions in the same overview, and I can just look at it from there. Whereas with other editors,
386
00:36:26.825 --> 00:36:27.865
depending on what they do,
387
00:36:28.185 --> 00:36:32.105
before the CLI, for example, you tend to have a single session and a single shell session.
388
00:36:32.425 --> 00:36:34.510
So if you wanna do something concurrently,
389
00:36:34.510 --> 00:36:38.830
then you need to create two sessions and hope that the harness actually allows you to create a work stream.
390
00:36:39.150 --> 00:36:44.109
So it's different touch points for different editors, for different types of work that I even have.
391
00:36:45.005 --> 00:36:51.325
And it is. I use cloth and cloth code and cloth co work. I use Mistral, Mistral code, and Mistral vibe
392
00:36:51.725 --> 00:36:58.365
all intermediately because I try to keep up to date of what the heck they're doing. And the interesting part is that everything starts to
393
00:36:59.740 --> 00:37:11.900
group together. They they start to build the same UIs for these things. So you see that Yeah. The harness and the way that they they create those things, yeah,
everybody's looking at everybody else, and they pick up the the things that work from them.
394
00:37:12.905 --> 00:37:20.105
So going back to your question, I don't necessarily have a preference. I like the way that GitHub approaches things from a developer perspective.
395
00:37:20.825 --> 00:37:25.065
Mhmm. And the tools that are building right now are very good, so that tends to be my go to.
396
00:37:26.105 --> 00:37:27.145
Okay. Yeah.
397
00:37:28.080 --> 00:37:30.800
Yeah. I I like it too. Right. It's nice.
398
00:37:31.280 --> 00:37:31.840
So
399
00:37:32.160 --> 00:37:34.880
the extension AI engineering fluency,
400
00:37:34.960 --> 00:37:36.480
do I per se need
401
00:37:36.880 --> 00:37:38.160
Versus Code to
402
00:37:38.480 --> 00:37:42.560
do it? Is it also in Visual Studio? Versus Code, Visual Studio, JetBrains.
403
00:37:42.995 --> 00:37:49.875
There is a NPM package, so you can run it in a shell or a status line, for example. You can build bring it into Omar Posh if you want to.
404
00:37:50.195 --> 00:37:52.275
Can bring it into the Copilot CLI.
405
00:37:52.515 --> 00:37:56.275
I think I have a script somewhere to do that for Cloth code, for example, as well.
406
00:37:57.090 --> 00:37:59.730
So, yeah, you can bring it in lots of different places.
407
00:38:00.930 --> 00:38:04.450
Nice. And has a GitHub Copilot team not yet
408
00:38:05.010 --> 00:38:16.595
knocked at your door to integrate this into their product somehow? Not specifically. Everybody's very enthusiastic, and they're looking at certain things. And you can see that this kind of information is relevant for a lot of folks. So
409
00:38:16.915 --> 00:38:17.395
Mhmm.
410
00:38:17.715 --> 00:38:22.195
Versus Code has been building the session debugger, for example, into their setup.
411
00:38:22.755 --> 00:38:31.060
They've done the same now with Cache Explorer and things like that. So everybody's learning from each other and then building little things into the product as well.
412
00:38:31.380 --> 00:38:31.700
So
413
00:38:33.700 --> 00:38:38.260
Okay. Well, let's see what happens. Maybe maybe they'll buy you out or something.
414
00:38:40.194 --> 00:38:41.555
That would be cool.
415
00:38:42.595 --> 00:38:46.435
Okay. So we have discussed a lot of stuff already here,
416
00:38:47.315 --> 00:38:49.155
and also the
417
00:38:50.275 --> 00:38:52.595
extension and how you built that type stuff.
418
00:38:53.714 --> 00:38:59.260
Maybe we can finish on this. Where can people find your trainings,
419
00:38:59.340 --> 00:39:07.180
like online trainings and things like that to learn more and to get up to speed with GitHub Copilot and other stuff? And, of course, your extension and wherever else.
420
00:39:07.740 --> 00:39:09.420
Oh, do you now have another hour? Yeah.
421
00:39:11.825 --> 00:39:13.265
Oh, absolutely. Yeah.
422
00:39:14.625 --> 00:39:22.865
You can start, and I'm always available on LinkedIn. I contribute a lot to the kids, go to community, for example. So I tend to share a lot of things over there.
423
00:39:23.265 --> 00:39:27.960
So that's your go to. I have a blog called devopsjournal.io.
424
00:39:28.040 --> 00:39:34.200
So you can find a lot of things there as well, and then definitely check the about page because that is where all of the links are grouped.
425
00:39:35.400 --> 00:39:41.795
And, again, from there, it just escalates in so many different directions. So I'm very active on GitHub. You can follow me there as well.
426
00:39:43.395 --> 00:39:47.635
I have several LinkedIn learning courses on GitHub.
427
00:39:47.875 --> 00:39:50.835
GitHub with phone security and GitHub with phone security for Azure DevOps,
428
00:39:51.430 --> 00:39:55.110
a responsible use of AI with GitHub Copilot and things like that.
429
00:39:56.470 --> 00:40:05.430
I've written two books by now. So GitHub actions and action, if you want to dive deeper into the actions ecosystem and how to work with that, and the GitHub Copilot handbook
430
00:40:05.985 --> 00:40:07.985
that came out last year.
431
00:40:08.225 --> 00:40:10.465
So those are the the big things there.
432
00:40:11.345 --> 00:40:12.625
What we've been doing
433
00:40:12.945 --> 00:40:16.385
at my employer, Zebia, we've built the tech.zebia.ns
434
00:40:16.385 --> 00:40:17.025
site.
435
00:40:17.185 --> 00:40:20.559
And that is a site that groups information
436
00:40:20.559 --> 00:40:23.440
around anything Microsoft, but also for Copilot
437
00:40:24.160 --> 00:40:26.000
on all of the updates,
438
00:40:26.000 --> 00:40:27.280
product updates,
439
00:40:27.280 --> 00:40:31.200
editor updates that are available, and we group a lot of information there.
440
00:40:31.520 --> 00:40:36.855
And we actually have a newsletter for that. Newsletter of yesterday was, like, 10 different updates from a single day.
441
00:40:37.335 --> 00:40:44.695
So if we wanna stay up to date, that would be a very good starting point because I tend to publish my stuff over to that site as well. So tech.zb
442
00:40:44.695 --> 00:40:45.335
and other things.
443
00:40:47.220 --> 00:40:53.620
Okay. Excellent. And all of those things will be in the show notes so that you can just go and click on those and go
444
00:40:53.860 --> 00:40:56.580
follow Rob and say hi to him. Awesome.
445
00:40:57.540 --> 00:41:05.185
Alright. This was very cool. Maybe we can do it again in a year to see how crazy things are by then. Probably. Yes. Let's do that. Alright.
446
00:41:06.705 --> 00:41:07.105
Thank you.