AvianQuest: A Scalable AI-Driven Framework for Pre-Adoption Avian Care Training Using Conversational Agents and Simulation-Based Learning

Responsible pet ownership is critical for animal welfare, particularly for exotic avian species that require specialized care and environmental management. However, existing educational approaches are limited in scalability and lack interactive, real-time engagement. This paper introduces AvianQuest, a scalable artificial intelligence (AI)-driven framework designed to train prospective bird owners through simulation-based learning, structured educational modules, and a domain-constrained conversational agent. To validate the proposed framework, this study implements and evaluates Phase 1: an asynchronous AI assistant ("Pocket Vet AI") developed using Python, the Flet UI framework, SQLite, and the Google Gemini 2.5 Flash large language model. The system demonstrates a robust, cross-platform architecture capable of delivering real-time, context-aware veterinary guidance while maintaining domain specificity and minimizing model hallucinations. The results establish the feasibility of integrating generative AI with interactive user interface paradigms to enable scalable, proactive pet ownership education prior to adoption.