The retail leader needed to improve the customer experience on their online platform. Customers frequently asked about product details, such as weight, ingredients, and allergens, but the existing chat system couldn’t provide accurate and detailed responses. This puts pressure on human customer service agents to manually answer these repetitive questions, limiting customer engagement and operational efficiency.

A conversational AI chatbot was developed by integrating Google Cloud’s Dialogflow CX with a custom webhook using retrieval-augmented generation (RAG). The solution utilized Python and cloud functions to extract entities from user queries and leveraged the client’s Hambroker API to retrieve relevant product information. Using a large language model (LLM), the chatbot generated concise and accurate responses. Custom intent routing and session variable management were incorporated to ensure seamless integration, enabling better user intent recognition and improving response relevance.

Improved Customer Engagement: Automated and personalized responses enhanced the customer experience, reducing reliance on human agents.

Operational Efficiency: Streamlined customer service operations, allowing agents to focus on more complex inquiries.

Scalability: The chatbot supported future growth by handling increased customer queries without additional human resource strain.

Increased Sales Potential: Better customer interactions led to more informed purchasing decisions and improved sales opportunities.