Customer Support Chatbot for the Chemistry Industry

Situation

Customers frequently contacted the company with product and application questions
Most answers were already available on the company’s website but difficult to find due to the large number of products and technical documents
As a result, sales teams spent significant time answering repetitive information requests instead of focusing on actual sales conversations

Solution

AI-powered customer support chatbot that answers product and application questions using information from the company’s website and internal documents
Transparent recommendation mechanisms that justify suggested products and increase user trust through Responsible AI methods
Automated handling of information requests, forwarding only genuine sales-related inquiries to the sales team and reducing repetitive workload

Tools

Python Microsoft Azure MLflow Docker CI Prompt Engineering LLM RAG NLP GenAI XAI RAI

In this project, I led the development of an intelligent chatbot solution tailored for customer support and product recommendations in the chemistry industry. The chatbot leveraged state-of-the-art Retrieval-Augmented Generation (RAG) to process vast amounts of product information sourced from the company’s website and internal documents. Within just three months, I successfully delivered a fully functional, end-to-end solution that smoothly integrated with the company’s workflows.

By employing advanced techniques such as prompt engineering, text summarization and a two-layer search system, I significantly improved the chatbot’s ability to deliver precise and contextually relevant responses. The innovative search mechanism combined product name filtering with relation matching, enabling the chatbot to handle complex multi-hop questions effectively. To ensure transparency and user trust, I incorporated Responsible AI mechanisms, providing clear justifications for product recommendations and aligning the solution with the company’s ethical standards.

This modular chatbot system not only addressed the company’s immediate needs but also offered flexibility for future customizations and scalability. By combining technical expertise in Natural Language Processing and Explainable AI with a deep understanding of business requirements, I created a robust and impactful tool that enhanced customer support capabilities and streamlined operations.

← Previous