How AI & DevOps Are About to Change the Way We Create Products

Thank you so much. I'll start by saying I'm honored that you've decided to spend the next 30 to 50 minutes with me. I'm not going to be rushing, so I'm going to be walking through my presentation in a peaceful manner. I'll see if you start nodding, then I'll speed up. Half of my presentation is going to be basics, and the other half is going to be talking about actual AI, so be patient.

I'm going to be live coding some, but we'll get back to that afterwards. I'll start by saying that lots of the movement has been started naturally by GitHub. I'm not going to be bound into GitHub, but as they are the most advanced currently in this technology, it's the most natural place for me to present the technologies in AI-driven development.

As a starter, to give you some sort of a thinking base, one of these pictures is real. It's actually taken exactly 80 months ago here in Copenhagen, near Revan. Sorry for not pronouncing it correctly. Three of the others are descriptions of this one real picture, which is essentially very close to the same as what we're doing with AI-driven development.

Some of my slides also have a QR code, so if you're bored or interested, you can just scan it and read for some more information on the topic. The latest research that has actually been made on the topic is naturally by GitHub, and even if you have to take it with a pinch of salt, what they state is developers are going to be 55% faster by using AI co-piloting.

I'm just going to quickly present what this means. I have a small application made in JavaScript currently showing a line, and then I have a file called week number. This example came from working with my son, who is doing university studies and had to do all of the exercises. Next to him, I was working with co-pilot to do the same exercises, and it took me less than a minute to solve the exercises that had been put in place.

For this particular presentation, I'm going to use a similar programmer dilemma called date calculation. Let's do a function that gets the week number from a date as a parameter. You'll see that all of the algorithms that I have to come up with, the AI co-pilot already gives me. With a few tabs and then exporting that function, I should see the week number done. So that was easy.

Have a great day! No, just kidding. But you already see that doing the actual math and the algorithm in very basic situations, the AI co-piloting does make us a lot faster. With a friend of mine, we even took it a bit further and created an open AI-based pull request reviewer using only OpenAI, meaning that we asked all of the code from essentially ChatGPT for the code to create a pull request reviewer.

You can now find it in the marketplace with the name AI code review action. I'll quickly show you how it looks. There is an old pull request called 'changed color to blue,' and if we read down, we can see that GitHub actions have already made some comments in there. You can see, 'Oh, consider adding JS stock,' saying that's not necessary to create a copy.

Now, as we're there, we at OT have been working with lots of more traditional organizations. We worked with GE Healthcare in building their newest patient monitor. When we started the project, we already knew that it was going to take us three to five years to create that patient monitor, put it into the market, and get all of the certifications done for it.

When we talk about quick coding, the algorithms and how customers or users behave on the sites, DevOps practices naturally help there. All of the AI co-piloting will be helping there, and then a bit less on the agile culture and product and portfolio management, although it depends on how organizational or bureaucratic you are.

Because of course, ChatGPT will help you create very nice reports. In addition to all of these, we've already seen a movement called prompt engineering. What that means is during the last year, we've had ChatGPT learn to do the questions to have the prompts in the correct way for ChatGPT or other AI-driven engines. It's a skill that has emerged out of nowhere, and it's something that all of us have to learn.

For today, where we are standing, there are four areas that AI-driven development is especially good at. Auto-completion of code, tests, and comments. AI is pretty good at grasping the context you're working in and proposing you completions. You have your idea of something you want to accomplish, and then you use AI to just fill it in, so to speak. The second one, which is one of my favorites, is when you start working on a new library or open-source API. AI has all of the knowledge, and most of the libraries that we use today already have quite extensive documentation.