LOVE&SAKE AI Assistant
Existing products and editorial knowledge turned into grounded sake conversations and recommendations.
Project brief
05 / 20- Client
- LOVE&SAKE
- Type
- AI applications
- Period
- 2026
- Status
- In operation
- Collaboration
- Commissioned directly by the client
- Scope
- RAG architecture, chat widget, admin, WordPress plugin and full-stack development
Project overview
LOVE&SAKE already had rich editorial and product knowledge.
We made that content retrievable by AI and integrated conversation, recommendations, settings and feedback into WordPress and WooCommerce.
Key outcomes
Working flow
Every question returns to real content and product data.
- 01 Understand
Interpret taste, budget, occasion and knowledge intent from the question.
- 02 Retrieve
Use article and available product records as the evidence for a reply.
- 03 Recommend
Explain the recommendation and return the visitor to a real product page.
Starting with knowledge the brand already owns
The system indexes articles and products, retrieves relevant passages for each question, then produces sourced answers and in-store recommendations. New site content enters the same indexing flow.
A system the team can inspect and improve
The customer widget shows answers, sources and products, while the admin side exposes settings, queries and feedback. Data sources and human controls remain inspectable.
Answers use the site’s editorial knowledge and live product data together.
The assistant retrieves articles and the latest eligible products, then uses semantic analysis and a higher-capability model to formulate a recommendation with a route back to the shop.
The assistant lives inside the established WordPress experience.
A small widget opens from the existing site instead of replacing its content structure. An admin workflow supports the manually managed product index and the next iteration of the service.
Next case
Envy Apple Campaign →