I want to like this and dig into it as someone who has recently used Lovable and Base44 (and been using Bubble for a while), but the YouTube ‘demo’ video is really weak.
The pace is too fast and you spend barely any time showing off your visual workflow feature, which according to your description is your differentiator.
I would strongly recommend using some of your YC money to have a professional recreate that demo and show off what makes you unique. Even if it goes longer than two minutes - if I’m interested I’ll keep watching.
I’ll still try it out because I’m a sucker for trying out new vibecoding tools, but you’re not doing yourself any favors with that video…
Thanks a lot for the feedback. The video was meant as a very spontaneous ‘as it is’ showcase, but we’ll definitely make new demos that go deeper into the editor!
> recently used Lovable and Base44
Are you happy with either product? I tried them earlier in the year, and it was also really slow to make changes. I felt like they got stuck after a bit, too.
It's a neat concept, but I feel like they're expensive templates. I'd honestly prefer a template gallery with a smooth and fast editing UI.
I was enjoying Base44 but found out midway through a project that it doesn’t support websockets so it wouldn’t work for my needs.
Switched back to Lovable and have been happily hacking away at that same project so far (although its early, and I know vibecoded projects tend to get gnarly later in the build).
> I felt like they got stuck after a bit
Every AI product that’s not a chatbot
In general to me it makes a lot of sense to lean much more into "templates" (I'm sure lovable etc already do it, because it's also a nice way to save money). And it's much easier to at least guarantee some basic security when it comes to auth, payments, db setup etc. Of course you can shoot yourself in the foot right after that.
Totally agree, security is a big point. It’s hard to trust LLMs on security, which is why we aim to make ‘white box’ backends
Quite like the positioning of "this is the backend to your lovable ui", probably how chef (the vibe coding tool from the makers of convex) should have positioned it. (and kind of do).
This looks great! Can I export my end code / app and host it elsewhere easily? Where else would easily be able to host it?
They say they use Convex for the backend, which means you could in principle run it on your own account or go through the hoops of self hosting convex infra
exactly
I've been playing around with vibeflow for a while, it's impressive how fast you can go from a prompt to a working full stack app. The visual workflow editor is a game changer.
Appreciate it! What did you build? What other nodes would be game-changers for you?
I built a small url shortener and also experimented with a map‑based mood tracker. what stood out to me is how quickly I could go from a prompt to a working frontend + backend without boilerplate.
For me, the most useful next nodes would be: 1) auth 2) stripe 3) file upload 4) convex action nodes (for more complex workflows)
I think the evolution of vibe coding tool is definitely the editor. Having a black box with no way to maintain it is an absolute liability.
That's why I think app generators must be a good editor before being able to generate anything. It seems you went this way with the cool node interface.
I'm doing the same thing with https://luna-park.app, but for fullstack apps.
I'm seeing a huge union jack overlaying the page when I open it in Safari
That's pretty funny but not what I envision for my landing page, I'll have to take a look... (thanks for the heads up)
Bolt.new has a nice IDE and Roo.code is literally just a VS Code Plugin
I've just tried my first prompt on your "try" setting, and what was generated wasn't anything like what I was expecting, to be honest. I asked for a workout tracking app with a good list of requirements (maybe it was too complex?), and the platform thoughts for quite a while. What I got was a template for a front end to connect to an AI agent for chats.
I didn’t have to scroll very far to find this kind of comment, which I was honestly expecting right from the get go. I feel like I’m always seeing this kind of feedback for these kinds of services.
I like this. Any chance you'll be bringing similar tactility (is that a word) to the frontend? Granular changes to components via prompts leaves a lot to be desired.
like visual edits to ui?
Yes, more or less. I've been tinkering with what this might look like this summer, but haven't found a good solution. Seeing your "exploded view" of the backend resonated on that front.
But instead of the nodes representing steps in a workflow, you'd have screens/views as nodes. Now, how the user would handle layout and components at that level, I'm not sure, but that's directionally what I'm asking about.
I hope that makes (a little bit of) sense.
Check out WeWeb, it gives you an AI-assisted editor that lets you do exactly what you're looking for.
I didn't know WeWeb had a full on AI rebrand. Will give it a shot -- thanks.
Will have to try this later, the YT video looks promising. Found tools similar to this promising to create early mockups or other pre-prototypes when developing products.
Thanks! Would love to hear what prototype ideas you have in mind
I do like convex but do you support any other data stores?
Seeing the backend nodes generate feels like magic
Glad to hear that. We want to make it as logical and white box as possible. Have you tried adding custom behavior after the first generation?
Congrats! Doesn't replit have an integrated database as well? Lovable has supabase, and I'm pretty sure Base44 as well, plus other agent integrations.
Thanks! Yes, Replit has KV store and managed Postgres, Lovable uses Supabase (requires manual setup). Base44 doesn't have a manual setup but has a black box backend. In VibeFlow: - no manual setup required - low code backend editor n8n style - no black box anymore - everything you do in the backend is code that you own
It's not just about databases, think about all the users currently using n8n with Lovable separately, without even owning the full stack
I tried this but kept getting errors. I asked it to build a TODO list that searches the internet to "augment" my todo list with advice
what errors did you encounter?
the UI that came out of the TODO app was saying error, although I gave it the firecrawl APIkey
Well I am/was building something that looks a lot like this, a shame I never applied to YC, wondering now if I should apply to other funds now so I can continue working on it, the prototype is ready so I have the main part figured out. A question, perhaps, could you give some tips to pitch this specifically, just for incubators, based on your experience?
Why not focus your energy on selling it to real people instead of figuring out how to pitch it to incubators?
that what everyone always says. But i think pitcing to a incubator is actually a good way to focus your idea. Anyways what is 2 hours in the grand scheme of things
Well all incubators ask the same thing (and search for the same profile). Just blast it to every incubator you find. Take some time write a nice YC application. There are tools like acceleratorfiller.xyz to send them to multiple accelerators. BTW (It's my company)
[CONVEX M(events:insertEvents_ion)] [Request ID: bbc76cc0a8e100df] Server Error Called by client
is any of the nodes in your editor marked as "incomplete"? there is probably a wrong call to the backend from your generated frontend. you can either ask the chat, or can help you debug in our discord https://discord.com/invite/Ctm2A2uEaq
Why did you use convex as backend?
Great question! We chose Convex for multiple reasons:
– We spin up isolated projects for each user. Convex handles this seamlessly with zero manual setup, while Supabase/Firebase have limitations and manual configuration needed – We abstract backend logic as visual nodes, so Convex's modularity makes it logical to find the right granularity for workflow representation. – Everything is reactive, so UIs and workflows stay in sync without bolting on listeners – Everything is end-to-end TypeScript with transactions by default, so generated code is predictable and maintainable
nicely done. are you sideswiping n8n as well here? i like it.
yes!
congrats on the launch, lots of competition in this space. (leap.new, replit etc). Even convex has their own app-builder.
thank you! There’s definitely a lot happening in this space, our focus is on making backends secure, robust, and understandable rather than just black-box codegen
did you think about using Effect.ts as the backend? i'm interested in pros/cons there
Awesome. Really, really awesome. One day no one will actually know how to write code, and no one will be able to fix all this shit.
Now make this build desktop apps. We don't need more web or mobile apps
Don't get me wrong, I wish your start-up all the best, but this particular application seems so stereotypical by current standards. It's at least four buzzwords combined into one "idea". As someone who has never tried to apply, I wonder how difficult it was to get through Y Combinator's selection process.
That's the most 2025 startup name and idea i've come across so far.
I worry that almost all the 2025 startups I've seen are AI app builders. Where are the novel new applications? I get that codegen is currently one area where AI does well, but it also feels like we're struggling with other use cases.
I’ve spent an enormous amount of time with practically every AI model out there, from coding to image-gen to video-gen
The tech is still simply too hard to use effectively for the vast majority of lay people, especially for anything beyond a cool product demo
Some of it is due to quality of the models, some of it due t quality of the tooling
Prompt engineering is still a skill and that’s beyond what a casual user can figure out
My optimism says the good new stuff is coming slowly because people who care about their craft and taking things slowly aren’t in any rush to get to market.
[flagged]