Skip navigation
Jev can generate interfaces in under 2 seconds. Almost zero cost.
0:00 / 0:30

Jev can generate interfaces in under 2 seconds. Almost zero cost.

Rahul Chakraborty

@hckmstrrahul22K followers

Visit on X
543 likesDownloadOriginal post

40,860 views

Jev can generate interfaces in under 2 seconds. Almost zero cost. I took the shadcn component library... → hooked it to a custom style md file → made some basic UI rules of popular apps using the Mobbin MCP → Jev instantly decides based on the predefined library and gives you a fully responsive composition in 1-2 seconds. Adding an LLM layer at the end improves output efficiency much better but takes aorund 8-12 seconds to generate (Qwen, Haiku)

46 Comments

Comments from the original post on X (Twitter)

  • Juraj Ivan @ QikBuild's profile picture

    @juraj_at_qik

    Cool use case — Jev picking shadcn pieces is sharp. Grabbed it for

    8 likes

  • Rahul Chakraborty's profile picture

    @hckmstrrahul

    🙌

  • Aditya Das's profile picture

    @theadityadas

    is it technically "generation" tho? more like pick the right UI? 🤔

    4 likes

  • Rahul Chakraborty's profile picture

    @hckmstrrahul

    imagine a design system and a set of rules, it mixes both of them and picks the right thing and can fill in with some source/demo data. calling it jeverative (haha). check the architecture diagram in thread

    4 likes

  • Rahul Chakraborty's profile picture

    @hckmstrrahul

    Tighter and defined rules lead to more refined outputs.

    3 likes

  • Jonathan Moore's profile picture

    @Moore

    I got it down to 400ms

    2 likes

  • Rahul Chakraborty's profile picture

    @hckmstrrahul

    For small components, without much rules/styles to choose from- it is really fast

  • Ashish Singh's profile picture

    @ashzingh

    Was discussing with @karrrtiiikkk how generative ui flows would be a possibility because of Jev.

    2 likes

  • EDDY VU's profile picture

    @eddyvustg

    Using Mobbin MCP to establish the UI rules is super clever, how granular did you have to make that style file?

    2 likes

  • Rahul Chakraborty's profile picture

    @hckmstrrahul

    for now it just took some top fintech app references, for some complex queries Jev-only mode will throw an error. Jev+LLM might still be able to give something. Also, depending on your style filesize – Qwen has larger error rates but costs very less. Haiku does better outputs but costs more.

  • Kenneth Dsouza's profile picture

    @Kenneth

    @rohanchkrabrty Nice! Was thinking about this an hour back. I felt this would reduce hallucinations too and choose elements from the prescribed design system only.

    2 likes

  • Rahul Chakraborty's profile picture

    @hckmstrrahul

    @rohanchkrabrty yes. more rules and guidelines lead to better output. adding an llm to it is the most idea solution.

  • Kenneth Dsouza's profile picture

    @Kenneth

    @rohanchkrabrty So do you send the rules to jev in every request ?

  • Rahul Chakraborty's profile picture

    @hckmstrrahul

    @rohanchkrabrty not the entire rule set. based on prompt, a local code (or llm, in hybrid mode) does some filtering before passing on to Jev.

    1 like

  • Kenneth Dsouza's profile picture

    @Kenneth

    @rohanchkrabrty This makes sense. In my today’s exploration, I choose to filter top 60 but it would make sense to add some logic filters prior to sending to Jev. But its definitely not as fast on my local app.

  • Rahul Chakraborty's profile picture

    @hckmstrrahul

    @rohanchkrabrty what kind of logic filters are u passing? written md/schema

  • Kenneth Dsouza's profile picture

    @Kenneth

    @rohanchkrabrty I did like 5min work, not great. Just to explore how reliable Jev’s output is. Right now was just using top 60 tags from my bookmarking tag list. Ideally should send most relevant top tags for evaluation.

    1 like

  • Alejandro Carbajo's profile picture

    @Carbaj0

    Same shape here, filling widgets instead of components. Two things bit me: options dilute (leader 0.99 -> 0.81 as I added them), and one extra sentence in a question dropped accuracy from 92% to 68%. Shortlist before Jev sees the library.

    1 like

  • Arjun's profile picture

    @arjunsjv

    Really neat demo!

    1 like

  • Rahul Chakraborty's profile picture

    @hckmstrrahul

    🙌