Shipped in 2024
AI Sommelier Chatbot
I made 1,000+ wines into easy picks, and grew sales 10% in 2 months
Timeline
Sep - Dec 2023
Role
UX Designer, Researcher
Platform
Mobile Web App
Stakeholder
CTO
Data Team Lead
Dev Team Lead
Top Challenge
Gemini was all new in 2023.
I had no AI experience, no wine knowledge,
and only 4 months to ship
User Pain
"I don't know where to start.
The 100+ bottles all look the same.
I can't tell the $6 bottle from the $20 one."
— Customer feedback
74% of shoppers walk away when overwhelmed by choice.
Business Concern
The post-COVID market stopped growing.
Carrefour needed a new way to move bottles
— and they bet on AI
Growth collapsed from +8.5%/yr to 0% since 2020.
Carrefour needed to find a way to move bottles.
Solution
On-demand AI sommelier turns 100+ options into 1 confident pick.
Turns overwhelmed shoppers into confident buyers.
Step-by-step guidance inspired by sommeliers for confident wine choice
I turned sommelier questioning into simple guided choices, to empower customers with expert-level selection.
Number scales and profile snapshots make wine easily imaginable
Replaced jargon like 'tannic structure' with 1-5 scales and plain-language profiles shoppers can compare at a glance."
Food-pairing icons turned wine shopping into dinner planning
Mirrored recommendations to real meals, so customers pick by what they're eating, not by grape varieties they don't recognize.
Impact
Market momentum restored. Revenue climbing again.
+10%
revenue growth within 2 months
1st
Google Gemini chatbot in Taiwan retail
95%
Users added wine to cart in ≤3 searches
"AI sommelier can give you the right wine, in just a few seconds."
Henry Ting
CTO, Carrefour Taiwan
Full Story
Research
To ship AI under tight timeline
I dove into technology, domain, and users
"What great AI UX looks like"
"How experts guide decisions"
"What users actually ask"
Sommeliers have a proven system. Wine jargon locks people out.
Sommelier's 3-step guidance
Knowledge barriers blocked shoppers
Key Feature 1
Expert-informed AI conversation flow
Context
People leave empty-handed when wines all look the same without guidance.
Challenge
AI conversation was too slow, too costly, and too unpredictable for a 4-month MVP
Key Decision 1
Step-by-step guidance inspired by sommeliers for confident wine choice
I turned sommelier questioning into simple guided choices, to empower customers with expert-level selection.
Key decision 2
To ensure reliable, fast responses, I designed structured choices to lead conversation
Structured selections guaranteed reliable recommendations without model training. Reduced decision anxiety for beginners.
Key decision 3
To prevent hallucination, I designed a workflow to pre-process wine profiles with AI and human verification
Final Product
On-demand AI sommelier turns 100+ options into 1 confident pick.
Turns overwhelmed shoppers into confident buyers.
Key Feature 2
AI-simplified wine profiles and illustrations
Context
Wine jargons confused customers and stop them from buying
Challenge
How to make AI tone approachable without losing expert credibility?
Key Decision 1
Number scales and profile snapshots make wine easily imaginable
Replaced jargon like 'tannic structure' with 1-5 scales and plain-language profiles shoppers can compare at a glance."
Key Decision 2
Food-pairing icons turned wine shopping into dinner planning
Mirrored recommendations to real meals, so customers pick by what they're eating, not by grape varieties they don't recognize.
Key Learnings
