AI Wine Sommelier
Shipped in 2024 | Proof of Concept
Taiwan wine sales hit 60-year low 📉
Carrefour tapped AI chatbot for turnaround
The AI chatbot provides tailored wine suggestions
The chatbot guides customers through Taiwan's largest wine collection with conversational AI and everyday language.
It breaks down knowledge barriers for wine beginners to unlock growth
Through conversational AI and everyday language, the sommelier demystifies wine selection, turning confusion into confidence for customers navigating Taiwan's most extensive wine collection
I led design of this AI product, Taiwan's first Google Gemini AI in retail
My Role
UX Designer
UX Researcher
Team Members
UI Designer
UX Researcher
PM
Duration
2023.09 - 2023.12
4 Months (Design)
Project Type
Consultancy
Client
Carrefour
Platform
Web App
Team Members
UI Designer
UX Researcher
PM
Direct Stakeholder
CTO
Data Team Lead
Dev Team Lead
My design delivered measurable business impact
Wine sales Increase within 2 months of launch
Users added wine to cart in ≤3 searches
Google Gemini AI application in Taiwan retail
"AI sommelier can give you the right wine in just a few seconds."
Henry Ting
Digital Technology Officer, Carrefour Taiwan
Research
To ship fast, I explored mature AI applications and market demands.
AI application assessment
I analyzed 14 deployed AI applications to extract workable design and interaction patterns.
Sommelier and seller interviews
We interviewed 2 liquor store owners and 1 Carrefour sommelier to understand wine selection challenges.
Online forum threads analysis
I analyzed wine community forums to uncover beginner barriers and purchasing behaviors efficiently.
Key Findings
Two critical findings: sommeliers' guidance and knowledge barriers
Sommelier's 3-step guidance framework
Knowledge barriers blocked wine beginners
Key Feature 1
Expert-informed AI conversation flow
Before
Customers stood in front of shelves, overwhelmed by selection, and left empty-handed
Carrefour's extensive wine selection intimidated beginners who lacked the knowledge to navigate options. Without accessible expertise, customers left stores without making purchases.
Challenge
How to provide personalized recommendations, manage AI costs, and meet tight deadlines?
Generating full AI responses and translating them consumed too many tokens, driving up costs and slowing response times. The MVP timeline didn't allow time to extensively test and guarantee AI predictability.
Key Decision 1
I translated sommelier expertise into step-by-step conversation flows
I transformed sommelier expertise into guided conversation flows with choice-based interactions. This approach made professional wine guidance accessible to beginners while ensuring accurate recommendations, controlled costs, and on-time delivery—all without requiring model fine-tuning
Key Decision 2
I designed choice-based interactions to ensure accuracy and delivery timeline
To guarantee accuracy and meet the 4-month deadline, I designed structured choice flows instead of free-form input. Guided selections ensured reliable recommendations without model training, while reducing decision anxiety for wine beginners.
The Design
Expert-guided conversation flow paired with choice-based interactions for reliable MVP delivery and accuracy
I transformed sommelier expertise into guided conversation flows with choice-based interactions. This approach made professional wine guidance accessible to beginners while ensuring accurate recommendations, controlled costs, and on-time delivery—all without requiring model fine-tuning
Key Feature 2
AI-simplified wine profiles in everyday language
Before
Expert wine language confused and excluded beginners
Technical terms like 'pencil lead,' 'sundried rocks,' and 'medium-bodied palate' excluded wine beginners rather than guiding them. This expert language reinforced intimidation, turning potential customers away without purchases.
Challenge
How to simplify wine language without sacrificing accuracy or credibility
Expert wine language ensures accuracy but excludes beginners. I needed to make descriptions accessible without oversimplifying—maintaining enough detail for trustworthy description while removing intimidating jargon that prevented purchases.
ACCESSIBLE LANGUAGE
Translate expert terminology into everyday words
EXPERT CREDIBILITY
Maintain trust and authority while being approachable
Description accuracy
Ensure descriptions genuinely match wine favors
I translated wine expertise into visual scales and everyday language
Simple descriptors like 'micro-bubbles' and 'fruit aroma' paired with numerical scales transformed complex wine attributes into scannable, relatable information.
The Design 2
Approachable wine profiles with everyday descriptions and visual aids
I combined three elements to make wine expertise accessible: numerical scales (Acidity: 3) for quick comparison, everyday descriptions ('fresh and smooth' instead of 'medium-bodied'), and food pairing icons (beef, cheese, sweets) that relate to real dining experiences
Key Learnings
AI flows evolved as users became more confident and direct
After launch, user behavior evolved. Initially, beginners needed structured guidance through choices, but as they became familiar with the system, they started entering complete requests upfront. I adapted by allowing direct input alongside guided flows and added 'I don't know' options for uncertain beginners
Multilingual AI requires cultural adaptation, not just word translation
Direct Chinese translation reduced recommendation accuracy significantly. I learned that multilingual AI needs culturally appropriate concepts and examples to maintain accuracy and relevance.
