Google's Gemini 2.5 Pro can now watch a 30-second video of a web app and rebuild it from scratch. LARRUZ shows the model generating code and files in about 26 seconds using Google AI Studio.
You might have heard that AI can build apps for you, but you kind of needed to know what to ask for. Now there's a new model which can actually take video as an input. So all you need to do is screen record an application that you want to clone, and then you can give this to the new Gemini 2.5 Pro model, and it will do its best. So what I did is I headed over to the site that I actually use regularly, and what I did is I ran a quick little screen recording, about 30 seconds. I just go through the different functionalities that I use, and what I'll do now is I'll open up Google Google AI Studio, where this new model is available. As you can see here, Gemini 2.5 Pro Preview, you got to select the one that says 0506. But if I go here into the studio, and I'll upload the screen recording of this application that I'm using every day, and all I'll say is, recreate this web app for me. And in 26 seconds, this already started to work. And initially it created an outline, but I had to follow up with telling it to do it. Very sophisticated prompting right here. And then it wrote the files, and I downloaded them and tried this out. But this is what the application that it built like looks like.
