Raphaël Goldsztejn

WeWeb 3.0 - Vibe-code apps with the safety net of a no-code editor

WeWeb is the only AI app builder that gives full editing control to non-coders. Prompt AI to generate your app, then refine every screen, workflow, and database in a powerful no-code editor where you always understand what’s happening under the hood. No more black box.

Add a comment

Replies

Best
Raphaël Goldsztejn

Hey Product Hunters 👋

Raphael, WeWeb CEO & co-founder here.

WeWeb is THE AI app builder for non-technical users: it lets you generate full applications with AI, then customize every part visually with a drag-and-drop editor.

Over the past year, we've all watched AI transform how fast you can build web apps.

But what happens after the prompt?

For most non-technical builders, AI generation hits the same wall: you create something impressive in minutes… then get stuck at 80%.

You can't really edit the output. You don't understand what's under the hood. One wrong click and everything breaks.

We are fixing that.

WeWeb is the AI app builder for people who want to understand what they're creating: where AI speed meets no-code control.

Generate full apps with UIs, workflows, and data structures in minutes.

Then use the drag & drop editor to inspect exactly what the AI produced, modify any part visually, and publish your app in one-click.

What can you build with WeWeb?

  • SaaS products that scale to millions of users

  • AI-native applications

  • Internal tools and operations platforms

  • Client portals, ERPs, and CRMs

Backed by YC, WeWeb is used by solo founders, startups, scaleups, and companies like PwC, L'Oréal or Décathlon to ship production-grade apps at scale.

I'd love to hear your feedback - ask me anything, I'll be here all day 🙂

🎁 Exclusive for the Product Hunt community: Use code PH2026 for 20% lifetime discount on any plan. You have one week to take advantage of this exclusive PH discount, don't waste time!

Artem Fedorovich

@raphael_goldsztejn Hey Raphaël, congrats on shipping 3.0 🎉

The "AI gets you to 80% then you are stuck, one wrong click and it breaks" framing is exactly right, and the visual editor as the safety net is a smart answer to it.

One question on the part of "under the hood" that non-coders cannot see even with a visual editor: backend security. When AI generates an app that connects to Stripe, Supabase, or an external API, who guards against the generated config exposing keys client-side or leaving an endpoint open? A non-coder visually understands the UI and the workflow, but they cannot eyeball whether the data layer is safe. Does WeWeb sanitize that automatically, flag risky configs, or is the assumption that the user brings their own backend discipline? Asking because that gap is where most no-code plus AI apps quietly ship vulnerabilities.

Raphaël Goldsztejn

Great question @artem_fedorovich , this is a key topic.

Here is how we address it in a few points:

  • when using the WeWeb backend, we create secured endpoints by default to CRUD the DB.

  • when using WeWeb auth, accesses to data and pages are secured very easily, in just a few clicks.

  • the Stripe integration is automatically secured → keys are deployed on the backend, on the server we spin up for each user (each project has its own dedicated server).

  • the Supabase connection is done through OAuth, no keys exposed on the front-end. Calls go from the front to the backend through standard REST APIs, with no dependencies on our servers.

  • WeWeb generates vue.js / node.js code, and we push over-the-air updates if vulnerabilities are detected on these frameworks. Users just have to republish their app to apply the fix. No code maintenance headaches.

One caveat: setups are secured by default, but WeWeb is very open-ended, so users could still create breaches manually. We plan to ship a security audit feature this year that will scan for breaches and warn users about critical security issues.

Alexis Cuellar

Hi @artem_fedorovich,

This is a very important question, and honestly one of the biggest challenges in AI app building.

A non-coder visually understands the UI and the workflow, but they cannot eyeball whether the data layer is safe.

That’s exactly why we’ve been working to make our security system as explicit and manageable as possible. One major step was building our own backend layer. Secrets, API calls, database access, permissions, and endpoints can be handled server-side with clear access controls.

On the AI side, our assistant is trained to follow best practices by default, so the goal is not just generating something that “works,” but generating something that respects safe architectural patterns.

We also added a powerful Ask mode: users can interrogate how their app works, understand the data flow, and clarify what is public vs private instead of treating the generated app as a black box.

That said, we don’t think this problem is “solved” yet. We’re actively exploring more proactive auditing capabilities to help users detect risky configurations before they ship.

Artem Fedorovich

@alexisjc Thanks both, this is a more thoughtful answer than I expected on a launch day 🙏

Raphaël, the "secured by default, but open-ended so users can still breach manually" honesty is the right framing. Secured defaults plus a planned breach scanner is a solid trajectory.

Alexis, your point lands hardest for me: "generating something that respects safe architectural patterns" rather than just something that works. That is the actual hard problem. An AI that writes functional code is table stakes now. An AI that writes code a non-coder can trust without auditing is a different bar entirely.

The Ask mode is a smart bridge, letting users interrogate data flow instead of treating the app as a black box. The piece I would watch next is the gap between "user can ask if something is safe" and "system proactively blocks the unsafe config before it ships." The first depends on the user knowing what to ask, which non-coders by definition often do not. The second is where this gets genuinely safe. Sounds like that is exactly the proactive auditing direction you mentioned. Rooting for it.

Raphaël Goldsztejn

@artem_fedorovich yes exactly, and this is going to be possible to do in WeWeb programmatically. Our AI doesn't generate raw code, it generates a JSON that WeWeb parses to build the app. If the JSON has flaws, the app simply doesn't build. So we can put programmatic guardrails directly at that JSON layer.

We call this architecture "AJA": AI to JSON to App. It adds deterministic guardrails on top of the non-deterministic nature of AI. As we progress, we'll layer in more programmatic security guardrails, and this is exactly the "system proactively blocks the unsafe config before it ships" direction you mentioned. Rooting for the same thing!

Bengeekly

@raphael_goldsztejn Congrats on the launch

Raphaël Goldsztejn

@bengeekly thank you for your support!

Marc Fabre
Bengeekly

I see in your website that the app can be in Github. Does that mean I have the full app in Github and I can host it somewhere else ?
If that the case, is it your own framework or an existing one ?

Raphaël Goldsztejn

Great question @bengeekly! Yes, you can push the full app to your own GitHub and host it wherever you want. Under the hood, WeWeb generates standard Vue.js SPAs (no proprietary framework) with a Node.js backend, so you can run them through any CI/CD pipeline and deploy on any infra.

Bengeekly

@raphael_goldsztejn  Can I edit the code directly on Github? Will it apply to your platform?
It would be amazing if you build an open source framework around it.

Raphaël Goldsztejn

@bengeekly Yes, the code can be edited directly on GitHub. However, once edited, it can't be "imported back" into WeWeb. Most users use the export feature to deploy on their own infra, but keep editing inside WeWeb so things don't fall out of sync with the editor.

Joyce Kettering

@raphael_goldsztej @bengeekly "Can I edit the code directly on Github? Will it apply to your platform?" It's technically possible to edit the exported code from WeWeb, but it's not easy or recommended because the code is structured by a machine for a machine so it's not organized like a human developer would organize it.


Editing these files safely would require super in-depth knowledge of WeWeb's internal logic. So it's not really a viable approach if you're planning to build a project in WeWeb and then maintain it independently outside the platform.

That said, we're working on a CLI that I think might change a lot how technical people build in WeWeb and could partly solve that limitation...

Bengeekly
@joycekettering thank you 🙏🏼 interesting logic.
Alenzeli Ramji

Huge congrats on the launch 🎉

We built gamercoin.co / gamerperks.co on WeWeb to test an idea fast, with little coding experience between us. The pitch in this launch is exactly what made it work for us. We could get something real off the ground, then actually go in and edit the UI, logic, and data without staring at code we didn't understand. WeWeb is the reason we got past it.

Rooting for the team today 🚀

Raphaël Goldsztejn

This already made my day @alenzeli_ramji 🙏

So glad WeWeb helped you get past that first wall. Rooting for Gamerperks! 🚀

Joyce Kettering

Very cool@alenzeli_ramji, gamerperks looks amazing! 😀 "without staring at code we didn't understand" -> as a fairly technical non-coder, I feel you! Short code snippets I can usually understand and edit confidently but complex logic in a full-blown app? No way!

Ishika Jain

Love what you built @alenzeli_ramji The UI is awesome 🔥
We’d be thrilled to feature gamerperks.co on our showcase page if you’re open to it 🙌

Marc Fabre

@alenzeli_ramji Thank you ! I'm really happy to see non coders building and understanding their apps with WeWeb !

Louis Lecat

love the idea of being able to actually go in and tweak yourself! When the AI generates the app, can you also go back and re-prompt it later to make changes, or is it more of a 1-shot generation and then everything else happens in the visual editor?

Alexis Cuellar

@louislecat You can use our AI both for the initial generation and for further iterations :)

Kévin BARFLEUR

@louislecat You can also do things yourself in the visual editor at any point, then ask the AI for feedback, improvements, or additional changes !

Clément Le Cuillier

Congratulations to the whole WeWeb team for the launch ! Go WeWeb🔥🔥🔥

Raphaël Goldsztejn
Thanks for you support @clem_le_c! Much appreciated 🤗
Candice Aime

A lot of AI tools can generate apps now, but the frustrating part comes after: editing things, understanding what was built, making changes without breaking everything 😅

Definitely going to try it!


Congrats on your launch WeWeb's team!

Raphaël Goldsztejn

So glad it resonates with you @cancan_aime ! Thanks for your support and let us know what you think about it!

Joyce Kettering

@cancan_aime yeah, I love vibe coding dashboards with Claude because it's so fast and I don't really care about the design or security when it's on my machine but I wouldn't trust myself to push it to production with all the appropriate security measures 😅 I definitely value our visual workflows then because at least I can clearly see what logic I built.

Quentin “𝑸” Durantay

Hey team,

Amazing work on the v3! The backend part is truly impressive.

Is there any plans in the future for an MCP? Importing our skills or own models?

Congrats on the launch!

PS: so cool to see the product evolution since I left the company. You guys rock 🙌

Joyce Kettering

Thanks for the support @quentindty! "Is there any plans in the future for an MCP? Importing our skills or own models?" hehe, of course 😉 You know @wwflo ... He wouldn't be Flo if he wasn't already working on it 😄

Slavo Pastor

@quentindty Flo doesn't want us to share this but...CLI coming very soon...

Quentin “𝑸” Durantay

@slavo_pastor CLI's amazing new 👌

Raphaël Goldsztejn

@quentindty you know what questions to ask :D

Marc Fabre

Thank you @quentindty !

The MCP is on its way :)

No ETA for now but quite soon !

I miss you and the ZipZap!

Marc Fabre

We have been working hard on this and we will continue to work hard to provide the best AI experience possible for our users :)

Tomasz Wieczorek

When you dev on weweb you don't really need AI to speed it up. Weweb is quick enough :D
+1 Good luck team!

Joyce Kettering

@tomasz_wieczorek haha love it! 😀 I love having AI do the first generation, especially for the UI, but still prefer building the logic myself because it's quicker (and more reassuring) for me to build it from scratch than retro-engineer what the AI did.

Alexy Carlier

@tomasz_wieczorek Hey! You can still rely on AI for advice or to help understand implementation details when you're building with a team. AI can scan your project and understand it really well! 🙂

Marc Fabre

@tomasz_wieczorek You are right! But even I now use the AI to build in WeWeb, it's way faster than doing manually and you actually just become lazy :P

Florian Briou

Hi everyone! I'm Florian Briou Rolle, Co-founder & CPO at WeWeb.

I am incredibly proud of our team for the hard work they put into bringing this new version to life, and I absolutely can't wait to see what you all build with it!

Please drop your thoughts, questions, and feedback in the comments below. I’ll be hanging out here answering them today, and we are ready to iterate fast based on what you tell us. Let us know what you think! 🚀

123
Next
Last