Loviux
From 1 store to 25+ countries run by 2 people: Magento 2 + Hyvä, plus an AI layer that writes the catalog in 16 languages, keeps stock in sync with suppliers, and handles customer support for cents per conversation.
The Challenge
Loviux is an intimate wellness ecommerce business that has worked with Kiwop since 2009. It wanted to operate like a major international ecommerce player (over 70,000 products, 25+ countries, each with its own language, currency, taxes, and carriers) while staying exactly what it is: a two-person team. The bottleneck wasn't the platform, it was the hands doing the work: writing and maintaining product pages in 16 languages took weeks per batch, stock from multiple suppliers changed daily in different formats, and every customer query had to wait until someone was free to read it.
The Solution
We solved it in four layers. Platform: Magento 2 with a Hyvä frontend, a custom checkout, Varnish, and zero-downtime deploys with automatic rollback, shipping orders the same day they come in. Internationalization: 27 store views from a single backend, each with its own domain, currency, taxes, and shipping rates, full hreflang, 4,500 programmatic SEO landing pages, and sitemaps covering 265,000 URLs. Operational AI: a content pipeline that writes and maintains product pages in 16 languages (from weeks to a single night per batch), stock synced with suppliers several times a day, tracking and emails in the customer's language, and per-order margin reports built by cross-referencing supplier invoices. Customer-facing AI: a model-agnostic chatbot (Anthropic and OpenAI, interchangeable) that recommends products with linked cards, looks up orders after verifying identity, and replies in 16 languages from a 3 KB widget that doesn't touch Core Web Vitals.
Technologies.
The tools that made this project possible
How a request flows.
- 01 A new product enters the catalog from the supplier feed and is flagged as pending content
- 02 That night, the AI pipeline writes the full product page and publishes it in the 16 languages across the stores; what used to take weeks per batch is now done in a single night
- 03 Stock is synced with supplier feeds several times a day (mixed XML, CSV, and JSON formats, normalized into a single format)
- 04 Every order triggers tracking and transactional emails in the customer's language, and the package ships the same day (weekday orders placed by 5 p.m. CET)
- 05 Supplier invoices are cross-referenced with each order to calculate the real margin, order by order
- 06 If a customer asks, the chatbot replies in 3-8 seconds in their language: it recommends products with cards linked to the catalog, or looks up their order after verifying their identity
What is AI and what is deterministic.
AI components
Language models (Anthropic and OpenAI, interchangeable) write and maintain product pages in 16 languages, generate the content for programmatic SEO landing pages, handle customer support conversations, and classify incoming queries. Catalog copy that used to take weeks per batch is now written in a single night, cutting editing time by 90%.
Deterministic components
Everything transactional runs on conventional code: stock synchronization with suppliers, prices, taxes and shipping rates per country, the checkout, identity verification before showing order details, and matching supplier invoices to orders for the margin reports. AI never touches prices or stock: it only reads them.
What the system does not do.
- The chatbot never shows order details without first verifying the customer's identity; that check runs on the server, not in the model
- It only recommends real products from the catalog, with cards linked to their page: it cannot invent products, prices, or availability
- Every conversation is logged in a review dashboard with its cost per chat; the team audits the bot's responses
- The AI layer is model-agnostic: Anthropic and OpenAI models can be swapped through configuration, with no dependency on a single provider
- The chatbot widget weighs 3 KB and loads lazily: AI never degrades the store's Core Web Vitals
- Every generated product page goes through automatic validation before publishing: banned phrases, character limits on titles and metas, heading and FAQ structure, and mandatory mention of every product variant
- Regression detectors watch the published catalog (language leaks, for example) and trigger surgical regeneration of only the affected products; the pipeline only touches active products with stock
Results.
Metrics in detail.
| Metric | Result |
|---|---|
| Completed orders vs same period last year | 8× |
| Revenue vs previous year | ~6× |
| Stores with sales after the relaunch | 5 → 15 |
| Countries with a live store | 25+ |
| Languages for catalog and support | 16 |
| Store views from a single Magento backend | 27 |
| Products in catalog | 70 000+ |
| Live URLs | 1 300 000 |
| Programmatic SEO landing pages | 4 500 |
| Lighthouse desktop / mobile / CLS | 100 / 91 / 0 |
| Cost per AI support conversation | < 0,01 € |
| Tokens per chatbot message (input / output) | ~4 300 / ~350 |
| Customer response time (previously, hours) | 3-8 s |
| Returns since the relaunch | 0 |
Methodology: Figures verified on July 11, 2026 against the live platform: orders and revenue come from the Magento database, comparing January-July 2026 with January-July 2025 (completed orders, amounts in euros); catalog, stores, countries, and URLs are counted in the backend and in the generated sitemaps; performance was measured with Lighthouse on the production templates; and cost and tokens per conversation are calculated by the chatbot's review dashboard from each chat's real consumption at API pricing. The chatbot passed end-to-end functional tests before launch: recommendations with filters, order lookup with identity verification (including the negative case), and rate limiting.
Process.
Platform
Magento 2 with a Hyvä frontend, a custom checkout, Varnish, and zero-downtime deploys with automatic rollback
Internationalization
27 store views from a single backend: domain, currency, taxes, and shipping rates per country, full hreflang, and 4,500 programmatic SEO landing pages
Operational AI
A pipeline that writes and maintains the catalog in 16 languages, syncs stock with suppliers, and calculates the real margin on every order
Customer-facing AI
A model-agnostic chatbot with recommendations linked to the catalog, order lookups with identity verification, and 16 languages, in a 3 KB widget
Ongoing expansion
New countries launch in days, not months (the latest were Hungary and Norway), with a conversation dashboard and cost-per-chat tracking to audit the AI
The Platform.
"On deadlines, they do not just deliver on time, they regularly deliver early. Things we expected to take weeks have landed in days; the AI chatbot went from idea to live on all our stores in a couple of days. Honestly, sometimes we joke that we do not know what these guys are running behind the scenes to move this fast."
Let's Talk Results.
Tell us your challenge. We'll respond within 24h.
Start Conversation