TokoKaret.com
A live commerce platform for rubber and industrial products with an AI-assisted consultation experience.
Overview
TokoKaret.com is a commerce platform bridging the gap between industrial product catalogs and informed purchase decisions. The Gemini-powered recommendation engine helps customers find the right rubber products based on their symptoms and requirements.
Problem
Industrial and rubber product buyers need guided product selection and consultation, but traditional e-commerce lacks the expertise to recommend products based on symptoms and use cases.
Target Users
Industrial buyers, workshops, and businesses needing rubber and industrial products
My Role
Product builder and designer
Designed and built the landing experience, consultation journey, sales pathways, and AI-assisted recommendation flow.
Key Features
- Conversion-focused landing experience
- AI-powered symptom-to-product recommendation (Google Gemini)
- WhatsApp and marketplace sales pathway integration
- Customer consultation journey with structured intake
- Responsive design optimized for mobile-first Indonesian users
AI System Notes
Google Gemini for symptom-to-category recommendation.
Form input stays lightweight: model, symptom, and category result are used to guide WhatsApp handoff.
AI is intentionally positioned as initial guidance; final size/type confirmation still happens through human consultation and photo evidence.
When uncertainty is high, the interface pushes the user to continue consultation rather than overclaiming a product fit.
The AI flow recommends categories, not guaranteed part compatibility. Physical photo confirmation remains necessary.
Pipeline
- User enters car model plus complaint or use case in a structured form.
- The prompt constrains Gemini to map symptoms to likely product categories instead of inventing exact SKUs.
- The answer becomes a first-pass direction that continues into WhatsApp consultation.
- Sales follow-up uses the AI result plus photo verification for final product matching.
Challenges & Trade-offs
- Translating technical industrial product specifications into accessible user-facing recommendations
- Building a Gemini prompt pipeline that reliably maps symptoms to products
- Integrating AI recommendations with offline sales workflows
Results
Conversion-focused landing experience serving a business with over 4,000 customers and 50,000+ items represented.
Proof Artifacts
