This is my first time in this beautiful city. Honestly, I haven't spent too much time in Europe, but I've learned two quick things in my 24 hours since being here. People love beer. It's cheaper than water at the restaurant I was at last night. Two, people really like to bike everywhere, so we're going to combine these two things by building an app. It's the Amsterdam Breathalyser. We're going to do this all armed with Codium, an AI developer tool.
So we're going to start with our JS monorepo, so fairly standard. The thing that I want to call out is that we have packages, we have shared dependencies, think design system, think utils, and a completely empty Vita project. We want to start by creating a landing page. Traditionally, you might have spent some time learning how to centre a title and a button on a page. What would you do? You would go to StackOverflow, try to find the exact copy of what you want. You might go to W3 schools, or you might even be in, who has played Flexbox Froggy? The classic let's get into the Flexbox game. Now, with Codium and all these new dev tools, we're able to speed up that acceleration of learning. We're able to automatically learn from your active files, from your repository, to actually ingest your codebase and trade that compute for analysing your dependencies, indexing your code, and summarising your files ahead of time.
It's this whole idea where we are trading compute so that your work can go faster. In this case, I'm actually telling it, I want to use Tailwind for my styling, and I also want to use my design system, so I'm telling it explicitly, let's pin my design system as I'm performing my generations. As you can see, what used to be complex Googling is now simply an English sentence. We're able to type an English sentence, and it's able to use context from our codebase and use that additional compute to now give us exactly what we want. The whole idea is that we are trading compute for a personal and unique experience with an AI developer tool. This can make typing a lot faster. As you can see, there's a lot of boilerplate with setting up state. We have to make sure we're tracking the number of drinks that this person is having. It can kind of read your mind in that sense. It can even suggest product decisions. Here our AI thinks that five drinks is an appropriate amount to drink before you can bike home. Maybe it's a skill issue on my part. It seems a little high, but who knows? Similarly, you can use that context ingestion here instead of Googling on how modals can work, we can ask, how do I use a modal? It will look through components that I have existing in my design system and give me the exact spec on what that means. Finally, what this gives us in under a couple of minutes when I was doing this asynchronously, you get this kind of experience where we have now focused and built a full-fledged app by a lot of English sentences rather than a lot of typing.
Comments