Normalized claim
Time: 50% decrease
Reduced search and recommendation response times by more than 50%.
GCPEvidence: Medium50/100
CN2U.AI uses Gemini 2.5 Flash on Vertex AI to improve cross-border ecommerce search & recommendations
Use case typeShopping recommendationsUpdated Jun 13, 2026
CN2U. AI is a cross-border ecommerce platform for international shoppers buying products from China at local prices or below. The company implemented chat-based product discovery and personalized recommendations powered by Gemini 2.5 Flash on Vertex AI to support multilingual search and persona-aware recommendations across more than 2 million products. The solution uses explainable, LLM-generated personas and contextual signals to rewrite queries in real time and improve discovery quality across Asia, Europe, and North America.
Reported outcomes
−20%
timeTime & speed
−50%time+10%accuracy+15%quantified impact+5%time
Strategic outcomes
New product / capabilityLaunched chat-based multilingual product discoveryMarket & geographic expansionSupported discovery across global regions
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Accuracy: 10% increase
Improved response accuracy by more than 10%.
Normalized claim
Quantified impact: 15% increase
Increased CTR by 15%.
Normalized claim
Time: 20% decrease
Reduced backend service setup times by 20%.
Normalized claim
Time: 5% increase
Improved service uptime by 5%.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- CN2U.AI
- Provider
- GCP
- Maturity
- Unknown
- Linked source
- Google Cloud Customer Stories
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 3 of 3
- 1Search and Recommendation
- 2Personalization
- 3Conversational AI
- Reduce AI search and recommendation latency.
- Improve recommendation accuracy for multilingual product discovery.
- Support chat-based discovery across more than 2 million products.
- Implemented an AI-native retrieval and re-ranking layer using Gemini 2.5 Flash on Vertex AI.
- Used LLM-generated personas and contextual signals to rewrite queries in real time.
- Scaled supporting backend services on Compute Engine for higher throughput and low-latency operation.
Technologies
- Reduced search and recommendation response times by more than 50%.
- Improved response accuracy by more than 10%.
- Increased CTR by 15%.
- Reduced backend service setup times by 20%.
- Improved service uptime by 5%.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: May 23, 2026Publisher: Google CloudEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
AI patterns
Browse the catalog
Was this useful?
Community
Comments
Loading comments...