🏢 Local Business · Heidelberg, Melbourne
Heidelberg · Local Business
Research Phase
Before writing a single line of code, our research agent studied Cafe Matto — their current website, social presence, reviews, team, and services. Here's what stood out.
Featured on a reality TV show — Yelp reviews reference it being 'part of a tv show' and competing against neighbouring Cafe Burgundy on Burgundy Street in what reviewers describe as a 'reality TV battle'
'Matto' means 'crazy' or 'mad' in Italian — fitting for their Italian cafe positioning at 136 Burgundy Street, Heidelberg, categorised as Coffee & Tea Shops and Italian on Yelp
Has a 2.8 star rating from 12 Yelp reviews — mixed reception with the reality TV connection driving some traffic but also critical reviews, and unusually fragmented operating hours that vary significantly day-to-day
Design Phase
Every design decision was intentional — informed by the research, not pulled from a template library.
Visual Direction
A 6-page site with a Rush Predictor interactive component showing estimated busy periods throughout the week. Built across 1,777 lines of TSX with a Menu page, Gallery, and Order/Book page. The design channels Italian cafe energy with bold typography and a testimonial carousel, while the accordion component handles FAQ-style content about the cafe's story and offerings.
Design Rationale
Cafe Matto has no website and no claimed online profiles — its most notable digital footprint is Yelp reviews mentioning a reality TV appearance. The design needed to give this character-rich business a proper home that celebrates its Italian identity and quirky backstory. The Rush Predictor is especially relevant given the cafe's unusual and fragmented operating hours (varying significantly by day), helping potential visitors plan around unpredictable availability.
Build Phase
Site Architecture
// Next.js App Router
Methodology
Spark (research agent) scraped Cafe Matto'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 Cafe Matto. 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 6-page Next.js application from scratch — 9 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
Research attempted 12 sources but hit significant barriers — Brave Search API quota was exhausted, cafematto.com.au domain doesn't exist, and Facebook, Instagram, TripAdvisor, Yellow Pages, Zomato, UberEats, Menulog, and Beanhunter all failed or returned no data. Primary data came from the Yelp listing (2.8 stars, 12 reviews). The reality TV connection was noted in reviews but could not be researched further. Operating hours from Yelp appear unusual and may be inaccurate. Data completeness rated low.
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 Cafe Matto's site in 10 minutes. Same process, same quality — a custom website built for you, not a template.