Hearth — a marketplace where every handmade piece comes with the maker's own voice.

Category: Marketplace

What it does: Hearth is a marketplace for handmade goods where every product listing includes a short audio story — the maker's own voice telling you where the piece came from, how it was made, and what it means. Buyers browse by craft (ceramics, textiles, jewelry, woodwork, and more), open a listing, hear the maker, and connect directly to purchase. Makers get their own dashboard to manage their profile and listings. It turns shopping from reading a product description into meeting the person behind the object.

How I built on the Bubble AI base: Hearth started from a single Bubble AI prompt, which generated the foundation — the data model, the core pages, and the marketplace structure. From there I built the layer that makes it Hearth: a voice data architecture where every product carries an audio story, a custom-built audio player wired with dynamic data so each maker's voice plays inside their listing, a fully rebuilt and photographed browse experience, working maker profiles and dashboard, and a warm editorial design that ties the whole concept together. The AI gave me a marketplace; I gave it a voice.

https://lotfiharbaoui84-12043.bubbleapps.io/

Great idea Lotfi 🌟 keep going

Figma Make isn't just a prototyping tool. I used it to ship a Claude-powered design system generator.

Most designers treat Figma Make as a quick vibe-coding sketchpad. I wanted to show it's something deeper — a full vibe-coding platform that integrates with external APIs.

The connection nobody writes about

There are three ways Claude connects to Figma today. Figma MCP — Claude reads and writes Figma files via MCP server. Figma's built-in AI — Figma calls its own models internally. And mine — a React app inside Figma Make that calls Claude API directly from the browser. Claude responds to the code, not to Figma. Figma Make is the hosting.

The new pipeline

Old approach: get brandbook and references from client → generate moodboard → align → write prompts for UI Kit. Separate steps, human in the center every time.

My approach: collapse all of that into one step. Run an AI analysis and output structured data — input for machines, not a result for humans.

We don't ask AI how the brand looks. We run an MRI on it and get structured data that machines use to build code.

What gets generated

11 files, all consistent with each other because they share one analysis. For Figma specifically:

tokens.json — W3C DTCG 3-tier format (primitive → semantic → component), imports directly into Figma Variables via Tokens Studio or Figma Make prompt

design-system.css — all tokens as CSS custom properties, ready to import

starter.tsx — paste into Figma Make, full design system renders instantly

figma-make.md — session context, paste once and the AI knows the entire design system

Add a content plan on top — generate a full design in one run with minimal token spend.

The entire tool was built and shipped inside Figma Make. No external hosting. No separate codebase.

→ vibecodingdsgen.figma.site

#ConfigMakeathon #FigmaMake #DesignSystem #VibeCoding #ClaudeAPI #BuildInPublic

tNot gonna lie, I opened this out of curiosity and left with more questions than answers 😅 But that's usually a good sign. Really interesting exploration of what design workflows might look like in the AI era. And by the way, this link doesn't work figma-make.md