🏢 Patisserie · Essendon, Melbourne
Essendon · Local Business
Research Phase
Before writing a single line of code, our research agent studied Parisian Patisserie Boulangerie — their current website, social presence, reviews, team, and services. Here's what stood out.
Rated 4.0 stars from 8 reviews on Yelp with a $$ price classification — one reviewer wrote 'Escape in this brilliant Patisserie, best coffee in Essendon and the pastries are to die for' suggesting a genuinely passionate following despite the small review count
Open Monday to Saturday 7am-5pm, closed Sundays (per Yelp) — classic French bakery hours that align with the authentic Parisian positioning, in a suburb where most cafes open 7 days
One of very few dedicated French patisserie-boulangeries in Melbourne's northwest — the dual French naming (patisserie for pastries, boulangerie for bread) signals authentic specialisation rather than a general bakery adding croissants to the display
Design Phase
Every design decision was intentional — informed by the research, not pulled from a template library.
Visual Direction
A 6-page site with separate Patisserie and Boulangerie pages reflecting the dual French disciplines, featuring a PairingGuide interactive component that suggests coffee-pastry combinations. The 9-component build includes an image gallery for showcasing handcrafted pastries and a dedicated catering page for event orders.
Design Rationale
The French patisserie tradition is inherently visual and aspirational — the design separates pastries (patisserie) from breads (boulangerie) to educate visitors on the distinction and position the business as authentically French rather than generically 'bakery'. The PairingGuide adds an interactive layer that mirrors the consultative experience of a real French patisserie counter.
Build Phase
Site Architecture
// Next.js App Router
Methodology
Spark (research agent) scraped Parisian Patisserie Boulangerie'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 Parisian Patisserie Boulangerie. 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 but was heavily limited by API quota exhaustion and CAPTCHA blocks across Google, Bing, and DuckDuckGo. Primary data sourced from the Yelp listing which provided hours, rating (4.0/8 reviews), amenities, and a standout review quote. Data completeness rated low — no website exists, no Google Maps data was extractable, and the exact street address could not be confirmed beyond Essendon VIC 3040.
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 Parisian Patisserie Boulangerie's site in 8 minutes. Same process, same quality — a custom website built for you, not a template.