🏢 Local Business · Reservoir, Melbourne
Reservoir · Local Business
Research Phase
Before writing a single line of code, our research agent studied Window Corner Cafe — their current website, social presence, reviews, team, and services. Here's what stood out.
Rated 4.8 stars on Yelp from 5 reviews — a near-perfect score with reviewers specifically praising the owners as 'beautiful people,' suggesting genuine owner-operated hospitality rather than hired staff
Located on Broadway in Reservoir (VIC 3073), part of Melbourne's northern corridor — a suburb that's increasingly gentrifying with a growing cafe culture along its Broadway and Edwardes Street shopping strips
Offers reservations, takeaway, and delivery for a small neighbourhood cafe — an unusually broad service model confirmed via Yelp, yet has no discoverable website, making online ordering invisible to potential customers
Design Phase
Every design decision was intentional — informed by the research, not pulled from a template library.
Visual Direction
A 6-page site built around warmth and neighbourhood charm, featuring a testimonial carousel to amplify the cafe's standout Yelp praise, an image gallery to visually establish the space, and a dedicated order/book page to convert the cafe's confirmed reservation and delivery services into online action. A bespoke Rush Predictor component gives visitors a real-time sense of when the cafe is busiest — a practical tool for a small venue where timing matters.
Design Rationale
Window Corner Cafe's biggest gap is digital visibility — 4.8 stars on Yelp but no website, no confirmed social presence, and blocked from most directories. The design prioritises discoverability and conversion: surfacing the owner-operated story and reviewer praise that currently lives only on Yelp, while adding online booking functionality for a cafe that already accepts reservations but has no digital channel to do so.
Build Phase
Site Architecture
// Next.js App Router
Methodology
Spark (research agent) scraped Window Corner Cafe'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 Window Corner Cafe. 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 covered 12 sources including Yelp Australia (primary data source), Google Maps, Yellow Pages, Zomato, TripAdvisor, Beanhunter, UberEats, Menulog, Instagram, and Facebook. Data completeness was low — most directories were blocked by CAPTCHA or Cloudflare, and the cafe has no discoverable website. Yelp provided the only confirmed data: 4.8-star rating, 5 reviews, amenity details, and a direct customer quote.
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 Window Corner Cafe's site in 10 minutes. Same process, same quality — a custom website built for you, not a template.