I Built TicketTriage AI: An NLP-Based Support Ticket Classification System

A developer built TicketTriage AI, an open-source NLP system that classifies and routes customer support tickets, with the repository documenting synthetic-data generation, model training, macro-F1 evaluation, automated testing, Docker configuration, and GitHub Actions CI. The developer notes the training data is synthetic and that the tool is meant to assist support agents rather than replace human decisions, and points to model confidence and human-in-the-loop workflows as areas for improvement.

Customer support teams spend significant time reading and routing incoming requests. I developed TicketTriage AI to explore how natural language processing can assist this workflow. The repository documents synthetic-data generation, model training, evaluation, automated testing, Docker configuration, and GitHub Actions. Macro F1 is used as a primary evaluation metric because performance across different ticket categories matters. The training dataset is synthetic. Real support conversations contain more variation, ambiguity, and changing language patterns. The system is intended to assist support agents, not replace human decisions. GitHub repository: https://github.com/tasnem-tech/ticket-triage-ai https://github.com/tasnem-tech/ticket-triage-ai I'm particularly interested in improving model confidence and practical human-in-the-loop workflows.