ecommerce_ops · ecommerce · workflow
Glowe: Agent-Powered Korean Skincare Routine Recommendations Using Weaviate, Gemini, and Elysia
Most skincare recommendation systems fail to capture nuanced relationships between ingredients, user experiences, and outcomes, leaving users overwhelmed by thousands of products with no way to identify effective combinations for their specific skin.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User skin questionnaire
A short, targeted questionnaire collects the user's skin condition, goals, age, and sensitivities to build a structured profile.
Tools used
WeaviateGemini 2.5 FlashGemma 3 12BElysiaWeaviate Query AgentWeaviate Agents
Outcome
Glowe delivers a complete morning and evening skincare routine personalized down to the ingredient level, alongside an agentic chat interface for ongoing guidance tailored to the user's skin type, concerns, and existing products.
What failed first
The common approach of embedding an entire product object into a single vector causes generic fields to dominate the vector space, diluting the importance of specific skincare effects and losing the ability to prioritize products by their actual performance.
Results
Volumearound 1,440
Grounding & classification
Source type: technical build writeup
24 fields verified against source quotes, 1 dropped as unverifiable.
agentic workflowconversational aidata extractionpersonalizationragrecommendation systemknowledge baseproduct catalogbuilder submittedproduction runtime claimedtools describedworkflow describedretailtechnical build writeupecommerce opsagentic task executionrag answering