Case studies

Fashion & Home E-commerce — Latam · Retail & E-commerce

Multimodal Sales Assistant & Personal Shopper

28%

AOV increase

18%

Sales conversion

45%

Fewer empty carts

The challenge

Customers struggled to find products matching their personal style within a very extensive catalog, leading to low conversion rates and abandoned shopping carts.

The solution

We developed a WhatsApp AI agent capable of receiving descriptions and photos from users (e.g., of an outfit or a room to decorate). The agent visually analyzes the images, searches for similar items in the store's vector catalog, and offers personalized recommendations with checkout links.

Tech stack

Gemini 2.0 Flash, FastAPI, Vector Search, Next.js, n8n

Timeline

2.5 months

Have a similar challenge?

Team in Medellín, Colombia. Free 45-minute consultation.

Let's talk