🏢 Service · Eltham, Melbourne
Great coffee, delicious food + good vibes!
Research Phase
Before writing a single line of code, our research agent studied Zen Den Cafe — their current website, social presence, reviews, team, and services. Here's what stood out.
Uses Proud Mary coffee beans — a respected Melbourne specialty roaster — and offers house-baked cakes and slices alongside all-day breakfast and lunch, with the kitchen closing at 3pm
Dog-friendly with accessible entry and facilities plus rear parking at 736 Main Road, Eltham — positioned as an inclusive neighbourhood gathering spot rather than just a coffee shop
Already has a modern website (zenden.au) with online ordering via me&u app and eGift cards via Square — one of the more digitally mature small cafes in this batch, offering a meaningful benchmark for the demo redesign
Design Phase
Every design decision was intentional — informed by the research, not pulled from a template library.
Visual Direction
A 6-page site featuring a Rush Predictor interactive component helping visitors plan their visit around peak times. Built across 1,917 lines of TSX with Menu, Gallery, Order/Book, and About pages. The design mirrors the cafe's relaxed, community-focused brand — using warm tones, casual typography, and the informal '+' sign style found in the business's own tagline ('Great coffee, delicious food + good vibes!').
Design Rationale
Zen Den already has a website, so the demo needed to demonstrably improve on it rather than just exist. The Rush Predictor adds genuine utility for a cafe that's clearly a neighbourhood favourite (hence the need to manage peak times). The Order/Book page integrates functionality they currently handle through third-party app links (me&u, Square), bringing the experience in-house. The design expresses the accessibility and inclusivity central to their brand — dog-friendly, vegan/GF options, wheelchair accessible.
Build Phase
Site Architecture
// Next.js App Router
Methodology
Spark (research agent) scraped Zen Den 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 Zen Den 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 8 sources with the official zenden.au website providing the strongest data — business identity, contact details, hours, menu categories, and brand positioning were all sourced directly. The menu PDF was binary/unreadable, and Instagram and Facebook were blocked by JS walls. No review quotes could be extracted from any platform. Brave Search API quota was exceeded. Data completeness rated medium.
For Reference
Zen Den Cafe's current website: www.zenden.au
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 Zen Den Cafe's site in 10 minutes. Same process, same quality — a custom website built for you, not a template.