Have something to say?

Tell us how we could make the product more useful to you.

Promising ! - Improve SQL commands

1) I like it ! The work on the UX is very interesting. Even my cat likes the animations and it loves to watch me using Creatr ;) . AI API, Resend, Analytics integrations are a very good way to offer something different from Lovable. 2) I encountered problems though, regarding SQL commands : I feel like the Creatr doesn’t have full context of what is happening at the Supabase level. So when it creates a non correct SQL commands producing errors, it will try to correct itself but as it encounters bugs in Supabase, it will try to fix it at the frontend level, so it doesn’t work. A workaround I found is to copy the last produced SQL commands into the SQL editor in Supabase and debug the SQL commands with the Supabase AI. 3) My two cents recommandations : - Does the AI have access to the Supabase SQL console output ? - Does the AI have access to the Supabase Logs ? (Postgres, API Gateway, Auth, Pooler…) - As OpenAI is quite expensive per token, I would appreciate having access to Open Router API. - As Sonnet is not yet supported as API providers within our created app/website, would it be correct to assume that Sonnet 3.7 is not at work as the Creatr AI ? From my Websim.ai experience, Sonnet 3.7 is much better than the 3.5. Thank you for bringing this great product to life !

Luigi Le J. 9 days ago

Early Access User: Feedback after 2 hours using the platform

Overall, my experience with the platform has been positive so far. The generation and preview features are working well, and I’m looking forward to testing the interface further in the coming weeks by integrating it with a backend project I’m currently working on. However, I do have a few observations and suggestions for improvement: Token Context Limitations I noticed that after processing around 350,000 tokens, the code generation started returning errors. Specifically, these errors were related to authentication with Google services. While I understand that token limits depend on the underlying LLM model, it would be helpful to know if there’s any summarization or optimization strategy being applied to manage large contexts. If not, perhaps this could be an area for improvement to handle larger projects more effectively. Version History and Chat Integration One feature that would significantly enhance usability is the ability to navigate directly to the chat session that generated a specific version in the version history. For example, when reviewing past versions, having an option to “jump to the chat” associated with that version would provide better context and make it easier to revisit or refine earlier work. This would streamline the workflow and improve the overall user experience. Thank you for the opportunity to provide feedback as an early access user. I’m excited to see how the platform evolves and am happy to assist with further testing or insights if needed.

Lenyn Alcántara About 1 month ago

I have created skinlens ai with superbase integration

Hi to all! I am one of the early access users, and I just completed developing a full SaaS application with Superbase integration. It took a total of 2 million tokens to finish the project, and the best part was that I only needed to connect to Superbase once. After that initial connection, I didn’t even have to open Superbase again to review anything, as all the data was added automatically in the background. I decided to explore the application further, and this is what I can share: the whole process was super easy—like, incredibly easy! All I had to do was click the Superbase integration button, sign in, create a new project, and then wait for a little while. It was as simple as that—there was no need to add columns or tables, or even create sign-in pages manually, which saved me a ton of effort. Overall, the total project cost me 1.8 million tokens. Let’s break it down: I spent 500k tokens on design, 600k on fixing errors and integrating Superbase, and the last 700k tokens went into polishing and finishing the product. I can also mention that I have the option to further enhance it as needed, as there seems to be plenty of potential for additional features. Throughout the project, I made a total of 27 edits, and the best part was that the system automatically provided me with suggestions at every step, and I just had to press "OK" to implement them. You can check out the project at this link: https://moral-sapphire-guppy-prod.getcreatr.xyz/

Usman Yousaf About 1 month ago

1

Prompt Editing Experience in Creator

First off, I really appreciate the early access and the work you all are doing with Creator. It’s been great exploring the tool, and I can see how powerful it can be for UI generation. That said, there’s one usability issue I’ve come across that I wanted to share. Right now, I’ve noticed there’s no way to edit prompts after I’ve started working on them. Given that Creator functions as a chat UI where I can iteratively build and refine my UI, not being able to adjust previous prompts forces me to start from scratch whenever I need to make modifications. This breaks the workflow a bit and makes iteration less fluid than I’d like. Would love to hear your thoughts on whether this is something that could be improved in future updates.

Jaleel Bennett About 1 month ago

Please Implement a Higher Level of Control

No-Code development depends heavily on pre-structured guidance in the form of documentation. Most people do not know how to build out this documentation effectively, which can result in slow development, the no-code development engine overwriting critical code or missing concepts entirely, and an awkward game of trying to sketch out ideas in real-time, hoping that the platform doesn’t completely change everything in exchange for adding new features. The main issue with the guidance parameters is structure and filling in monotonous details. However, AI is VERY skilled at rapidly building out guiding docs by asking questions, and filling in the gaps with structural knowledge. CJ_Z on x is doing an incredible job at this, and his community has grown well beyond 1,000 monthly users. https://x.com/cj_zZZz/status/1871227397925929294 The first no-code environment to build in a planning and documentation support feature will have an unfair advantage, as it will allow for such a high level of control and specificity, saving time and stress and ensuring consistent and powerfully aligned outcomes, that it won’t make sense to use any other programs. You guys could very easily add this to the files system, where the user has the choice of either uploading files manually, or going through the collaborative planning and coordination process with whatever AI support you choose (or they could use their own API key). I would LOVE to help build this out or answer any questions if you guys need. SUPER inspired by the work you are doing, and please lmk if there is anything I can do to help.

Wa-Ya Aeon About 2 months ago

1

Old code is still there even i have remove or replace it

I have been experiencing issues with my project where, for instance, after adding a background animation and implementing it properly, I now want to switch to a new animation or perhaps change its color. However, whenever I attempt to type something in the code to make these adjustments, I encounter persistent errors indicating that the specified elements cannot be found or accessed. x: file not found error /home/ubuntu/projects/probable-aqua-bandicoot/src/components/ui/Spotlight.tsx: file not found error /home/ubuntu/projects/probable-aqua-bandicoot/src/components/ui/BackgroundCircle s.tsx: file not found error /home/ubuntu/projects/probable-aqua-bandicoot/src/hooks/use-screen-size.tsx: file not found error Dropping src/hooks/use-screen-size.tsx from the chat. /home/ubuntu/projects/probable-aqua-bandicoot/src/components/ui/gooey-filter.tsx : file not found error Dropping src/components/ui/gooey-filter.tsx from the chat. /home/ubuntu/projects/probable-aqua-bandicoot/src/components/DeepAgentsBanner.ts x: file not found error Dropping src/components/DeepAgentsBanner.tsx from the chat. /home/ubuntu/projects/probable-aqua-bandicoot/src/components/ui/Spotlight.tsx: file not found error Dropping src/components/ui/Spotlight.tsx from the chat. /home/ubuntu/projects/probable-aqua-bandicoot/src/components/ui/BackgroundCircle s.tsx: file not found error Dropping src/components/ui/BackgroundCircles.tsx from the chat. I'll help enhance the design and user experience to make it more premium. Let's add some sophisticated features: But the new features are added just every time i see this errors now

Usman Yousaf About 2 months ago

1

Ability to add screenshots in chat itself

The image upload feature is a great addition, allowing us to customize elements with our own visuals. However, its utility is limited when we need to communicate specific design adjustments, like fixing a layout issue. Currently, I can't effectively use the image upload to show Creatr what needs to be changed. For example, I recently encountered a CTA button that was too long. In other tools, I could simply take a screenshot, highlight the issue, and ask the AI to correct it. This visual communication is much more efficient than trying to describe the problem in words. The lack of this screenshot/annotation functionality makes it difficult to clearly convey these types of targeted edits within Creatr. Implementing this would significantly improve the workflow.

Krishna Goutham N About 2 months ago

1