Is it only me or is it not a short-coming of regular weather apps that they only provide the weather for a period of time for a single place at a time. What if you’re constantly moving, then you’d like the forecast to be for the location where you will be at a given point in time, right?

We make a few longer drives per year, it’s either going from Stockholm to the north for skiing or it’s for visiting the summer house in the south of Sweden. When driving north in the winter you typically will want to know if it’s going to snow since you may want to adjust your route depending on the weather. If it’s going to snow by the coast when you pass through, then you’ll want to check if it’s smarter to drive in-land and vice versa.

Similarly in the summer, we bring the dog and the dog needs a walk some time during the drive. So I want to know, when during the drive will it not rain (remember it’s Sweden, it rains a lot)?

I’ve had these scenarios in my head for a long time and the only solution has been to check the forecast for a few different places one by one to see what the weather will be where I will be at a given time. So sort of like the love-child of a route-planning-app and a weather-app and I bet you wanted one too (even if you didn’t realize it until now).

To be honest, I’ve tried to build this on a number of occasions but it’s always failed/ran out of steam due to my lack of front-end abilities. With some rainy days during the vacation and an underlying urge to try out some of the new agent frameworks to build something more substantial I gave it another go.

The tech stack is straight forward, the backend is a simple dotnet application (because dotnet is what I work with) and a React front-end. Using Matt Pocock’s collection of skills and a couple of grill-me sessions pretty much set the stage and from there on it was just letting Claude have a go at it. What can I say, it nailed it pretty much immediately. A few iterations to add multiple waypoints and a deployment pipeline and that was it.

I have mixed feelings, not about the result - I think it’s great - but about the whole building experience. Normally, once you have something (I don’t want to say completed something) you feel a certain level of accomplishment. You did something by putting effort into it, it cost you some effort and you can view the result.

I don’t get that feeling here, I’ve thought about it a lot and the best way I can describe it is that of “empty calories”. I built something but I don’t feel it will have a lasting effect on me as I’m not sure I learnt something by doing it.

Then on the other hand, the app is there and (to me) it actually provides some value without having to put in the matching level of effort for it (or what used to be the expected matching level of effort) which of course is spectacular and certainly something that is great.

I think it’s going to be a while before this panic-anxiety inducing euphoria of what you can build with AI is going to fade and I will get used to it.

Enough said, here is the nice working prototype, an app that shows the weather for the route that you’ve planned. A forecast that is not static to a place but shows the weather along the route you intend to follow. Check out Wayther and feel free to fork the code.