Transcription
GitHub just launched Spark and I cannot wait to tell you more about it. My mind is blown. I'm not even exaggerating here. I literally built a working full stack application in just a few minutes with this thing. And you are going to see an entire demo in just a few seconds.
But first, let me quickly explain what Spark actually is. So, we've been seeing all kinds of AI coding tools lately on the market, right? Cursor, Replet, etc. Well, GitHub said, "No, let's skip coding altogether." Spark is basically an AI powered app builder that runs entirely in your browser. But here's the crazy part. It is not just generating front-end mockups. We are talking about full stack applications with database, authentication, AI features, and the whole nine yards.
It's powered by Claude Sonnet 4 and it has its natural language editor where you literally just describe what you want to be built. Then it has its own runtime environment that hosts everything, persistent storage, and you can even add other large language model features without touching any APIs. Plus, it's got this progressive web app dashboard, so you can build, test, and deploy from literally anywhere. No local setup, no configuration hell, just pure browser-based development.
Look, I had to test this thing myself because, hey, it really sounds amazing. So, let me show you exactly what happened when I gave GitHub Spark a try. Let's see it.
Now, this is what Spark looks like. You can literally type in natural language exactly what you want to build and it will build you a full stack application. Now, if you're like me, you would want to create a really good prompt. And so, I went into Claude. I gave it my idea, asked it to create a PRD, a product requirements document for a personal nutrition and fitness app. And it gave gave it a few little descriptions of what I want. I also asked it to connect to Gemini flashlight API for taking images of the food so that you can extract macros. It is doing an absolutely amazing job trying to take all of my requirements from natural language into uh converting it into a PRD document. I'm looking for Gemini. Did it actually put my description for Gemini and for data management into the prompt? And after I'm satisfied with this prompt for PRD, I go into Spark and then paste that prompt as is. And now that I'm happy with it, I am able to click on submit prompt. And as soon as I do that, Spark is going in its think mode. Right. And here on the right, I absolutely love how it uh changes these little things calling itself "I'm building tiny things," "consulting," "researching," "blockchain," buzzwords. Um, I'm just enjoying reading the the different nuggets that they have on the on the right-hand side while on the left it is actually trying to create my code. Um, and in just a few minutes, I kind of um did a little bit of a speed up here. Um, it has my login information for profile and logging in and it's taking all the details that I gave it in the description. And then on on the quick actions thing, it is not doing a good job with scanning the food and manual entry. I don't think it actually connected itself to Gemini API. Um, so we'll have to go fix that and figure out how to. But on the left in the themes section, um, you'll see that I can actually uh change the appearance pretty easily, which I really, really love. And I don't have to worry about writing code. So this is really for people who want to do this in natural language, right? And then I've got the prompts and the assets and the data. And on the right, I'm able to see that I can go into the mobile mode, how it's going to look on mobile, convert it back into.
Now, let's go actually fix the problem with our log food, right? So, I created another prompt and I'm really asking it to figure out what's going on here and make sure that you connect to Gemini Flashlight and really what I was trying to test here is um Spark's ability to connect to other large language models. And I kind of speed things up here a little bit as well um to try and see it's creating settings dashboard and there we have it. It has it, according to it, it has connected to the Gemini API. Now I don't know if it has done that. I'm actually asking it gives you the prompts on the left to um as a follow-on. So it kind of knows what you're trying to do. Um, and I asked it to actually go set it up for me, the Gemini API key, and I see it in the settings that it did that, but uh it's also requiring the API key from me. So something somewhere did not go right. I go in to the settings myself and then I try to see if um where is the Gemini API key, right? And then I manually pasted it myself and then I asked it to run the app again and see um what happened and it goes ahead and does that. And now at this point, I'm actually able to upload an image or take a photo. I love Chola Bura. I uploaded that and wanted it to analyze chaura into the different macros that this food has. And then I went in and tried to do the same in the text description. It analyzes that text and creates um the macro u profile for me and it adds all of that and tracks my today's progress. Um, and then on the top, I can go in and create a repository of this code. So just two button clicks and I have a repository built, which is amazing. Um, I'm seeing the exact same thing in my mobile app as well. And then when I want to go to the repository, I'm able to see the the GitHub repo. Now I can use repurpose this repo in any way shape or form. I can also open the code in Codespaces. So um Codespaces, if you don't know, is uh basically a hosted version of VS Code and it allows you it's so easy to use that it is browser-based and you can very easily go ahead and and create those um and or edit anything that you want to in this code. Um, so that's a really good thing to have. And then in the settings section here um there is just a little bit of a description of what's going on. And with the publish button here, I am actually able to publish this application entirely just in one click. There I have my app live. It's only visible to me right now. So I can go in and see this application live and how it's performing. This is great. I love it. Oh, I can see my API key as well. I can test if it's working. Really good experience here. Now I can actually make it visible to all the GitHub users. Again, I don't really care right now, so I was just giving it a try and it worked really well.
Now on the left in the suggestions section, let's say now we've published the app. I wanted to see what the experience is like after adding an additional feature. So I asked it to add some social feed feature into this. And um after um thinking for maybe like a minute or two, I've speeded this process up here for us to get to it faster. Um once it is able to create all of the requirements for the social page that I asked it to do. All right. Once it has done that, I see that at the very top of the page, it has added a social section and that is what I wanted. Okay. So um now let's see what happens when we okay when I go to create repository, it's asking me to create a repository that is not right, right? Because we actually just edited it um but anyway, it actually takes the right repo when I click on it and updates that repo, which is perfect um and then I have this update button which actually allows me to update the application um that is already live. This is amazing. I'm again not really writing any code. It's doing all of this for me and it is updating this application with the new social feature that we added after deploying it once. And when I click on the website, I'm actually able to see my social feature. Great. This is absolutely mind-blowing. Okay.
So, after seeing Spark in action, what is my honest take? Well, it is a paradigm shift. We are living in an era where we are democratizing software development in real time. Is it perfect? Absolutely not. Complex enterprise applications still need that traditional development approach. The AI can make mistakes and you still need to understand the software development principles to truly build applications for production. But for prototyping, internal tools, personal projects, and even early-stage SaaS products like startups, Spark is an absolute game-changer. The speed from idea to working prototype is mind-blowing. Right?
Right now, Spark is available in public preview for GitHub Copilot Pro Plus subscribers at $39 per month. I will be diving deep into Spark in the coming weeks, building some real projects and testing its limits further. And I would love to hear what you think and if you have given it a try yourself. Please share what you've built in the comments below. I'd love to know. And if you liked this video, I'm sure you're going to like my other video on Vibe Coding. And I will see you next time. Thank you.