☕ Cafe · Moonee Ponds, Melbourne
A Taste of Georgia in Moonee Ponds
Research Phase
Before writing a single line of code, our research agent studied Mon Paris — their current website, social presence, reviews, team, and services. Here's what stood out.
App Router defines 4 route file(s): /, /about, /contact, /menu.
Components directory contains 3 TSX component file(s) (e.g., FloatingCallButton.tsx, Footer.tsx, Navigation.tsx).
data/business.json exposes 12 top-level field(s), including structured service/menu content.
Design Phase
Every design decision was intentional — informed by the research, not pulled from a template library.
Visual Direction
Multi-page Next.js App Router implementation driven by source-authored content modules and route-level sections. No Framer Motion dependency/import evidence was used for animation claims. Styling is utility-class based with project-specific globals from app/globals.css.
Design Rationale
Rationale is based on observable routing, component composition, and metadata/content files in source code; no external performance or client outcome claims were introduced.
Build Phase
Site Architecture
// Next.js App Router
Methodology
Spark (research agent) scraped Mon Paris's current website, Google reviews, social media, and business listings. Every piece of real data — team names, service pricing, business hours, unique details — was extracted into a structured profile.
Based on the research, a bespoke design direction was created specifically for Mon Paris. No templates — the typography, color palette, layout patterns, and visual effects were all chosen to match this business's personality and industry.
Pixel (design agent) built the entire 4-page Next.js application from scratch — 3 custom components, real content from the research phase, App Router with proper routing, and production-grade code.
Sentinel (QA agent) verified the build compiles cleanly, checked for placeholder content, validated all routes render correctly, and confirmed the design is unique (not recycled from another demo).
Additional Notes
Compiled strictly from source evidence in app/** page files, components/**, data/business.json (when present), and SOURCES.md (when present). Unknown or unverified fields are explicitly marked and no fabricated business facts were added.
More from the experiment
This case study is part of the AI Web Lab — a 30-day experiment where AI agents build bespoke websites for real Melbourne businesses. Every site is researched, designed, and built from scratch by a team of five specialist AI agents. The full methodology, code, and results are documented transparently.
This study is being prepared for publication as part of a research paper on AI-assisted web development at scale.
We built Mon Paris's site in null minutes. Same process, same quality — a custom website built for you, not a template.