Viktor.comAn AI coworker that actually does the work
Launching today
x1
Lovable for iPhone apps. From idea to App Store
92 followers
Lovable for iPhone apps. From idea to App Store
92 followers
X1 is an AI app builder that takes you from an idea to an iPhone app you can publish on the App Store. Instead of trying to generate the entire app from one prompt, X1 guides you step by step. It asks focused questions, designs each screen for you to review and edit, then builds the app in stages. Preview and test it on your iPhone as you go. When it’s ready, X1 prepares your App Store listing, screenshots, and submission. No coding required.
x1
Hey Product Hunt 👋
X1 is an AI app builder that takes you from an idea to an iPhone app ready for the App Store.
Most AI app builders try to generate the entire app from one prompt. X1 guides you through it step by step. It asks focused questions, creates a plan for the whole app, designs each screen for you to review and edit, then builds the app in stages so you can test it on your iPhone as you go.
X1 also remembers the decisions behind your app. If you change something later, it updates the screens, flows, and features that depend on it instead of treating every request like a brand-new prompt.
When you’re ready to ship, X1 prepares your App Store listing, screenshots, and submission through your Apple Developer account.
I built X1 because AI could generate an impressive first demo, but I still had no clear path to something I trusted enough to ship. The first version was easy. Keeping the whole app coherent as it evolved was the hard part.
You can build a working prototype free at x1.new. No coding or credit card required.
If you try it, tell me what you’re building and where X1 gets confused, makes a bad assumption, or slows you down. Brutal feedback is more useful than polite feedback. I’ll be here all day.
Nice congrats on launch. Curious how you guys are better than other app builders like replit?
x1
@essam_sleiman Yeah, Replit is probably the closest comparison.
The main difference is that X1 is built around how a strong engineer would actually use AI: on well-defined, scoped problems with the right context.
So instead of asking the model to build your whole app and then iterating through chat, X1 breaks the app down, works through the important decisions for each part, designs it, then builds and tests that piece before moving on.
Replit gives you a very capable AI builder. X1 is more opinionated about the process around that builder.
Congrats guys! What would you estimate the median time to be to go from first prompt to a playable game? I've always wanted to re-create Restaurant City (from the 2010 facebook era) and play it on my phone when I'm on the bus or something.
x1
@boris_skurikhin This would actually be a sick test case lol.
For something like Restaurant City, I’d estimate around a week to go from the first prompt to a genuinely playable version on your phone. You’d probably have something basic much sooner, but a week feels realistic once you include the actual game logic + iteration.
If you build it, please send it to me lol. I want to see this.
Congrats @manil_lakabi1 How's it different from Rork in practice? Both promise real iOS apps without code.
x1
@boyuan_deng1 Yeah, surface level the promise is similar. The biggest difference is how X1 thinks about building the app.
We try to emulate how a strong product team actually works: figure out what should happen, make the product decisions, design the screens, build that piece, test it, then move on.
AI accelerates each of those steps instead of pretending they can disappear.
So rather than “describe your whole app and hope the model gets it right,” X1 works through it with you piece by piece and keeps those decisions connected as the product evolves.
That’s really the bet: AI should compress the product development process, not remove it.
HyNote AI
Been burned before by builders that forget context after a few edits. If X1 actually solves that, it's a real differentiator.
x1
@ristan_nakko Yeah, I had the exact same experience and it was infuriating because you could taste how close you were.
The app would be 80% there, then a few edits later the model would forget why something was built a certain way and start breaking other parts.
We’re definitely not perfect yet, but that’s really the mission with X1: keep enough context and structure around the product that every new change builds on what came before instead of slowly undoing it.
Triforce Todos
Curious how X1 decides what to ask you vs. what to just assume. Does it feel like a real back-and-forth or more like a form?
x1
@abod_rehman Definitely more back-and-forth. We try to only ask when the answer would meaningfully change the app or create downstream decisions. If something is obvious or easy to change later, X1 just makes a reasonable call and keeps moving.
The questions are also based on your app and previous answers, so it shouldn’t feel like filling out the same form every time. The goal is basically to catch ambiguity before X1 turns it into a bunch of assumptions you discover 20 changes later.
Mom Clock
What happens if you want to pivot halfway through, does it rebuild cleanly or does the "memory" start working against you?
x1
@justin2025 That’s exactly the failure mode we’re trying to avoid.
If you pivot, X1 treats the old decisions as things to re-evaluate, not sacred memory. It updates the plan/underlying decisions, figures out what actually needs to change, and keeps the parts that are still valid instead of rebuilding everything from scratch.
The goal is for memory to preserve context, not trap you in it.