Personal financial management is an important aspect of supporting financial well-being; however, a gap remains between financial literacy and financial inclusion among Indonesian society. This study aims to design and develop a mobile-based personal financial management application called FinAI by utilizing the Large Language Model (LLM) Google Gemini to support transaction recording and management through natural language and provide more personalized financial information. This research employed a Research and Development (R&D) approach using the Software Development Life Cycle (SDLC) Waterfall model, consisting of requirements analysis, system design, implementation, testing, and maintenance. The application was developed using the Flutter framework and Dart programming language, with Firebase and Node.js supporting the backend and Google Gemini API integrated for natural language processing. The developed features include natural-language transaction recording through AI Financial Chat, manual transaction recording, transaction history and filtering, financial analysis and visualization, financial goal management, and financial report export in Excel format. Functional testing was conducted using Black Box Testing, while usability testing employed the System Usability Scale (SUS). The Black Box Testing results based on 11 test scenarios showed that all main functions operated 100% validly according to the specified requirements. Usability testing involving seven respondents produced an average SUS score of 57.14, categorized as OK with a marginal level. These results indicate that FinAI can be used to assist users in recording, monitoring, and managing personal finances in a more structured manner, although improvements are still needed in terms of user convenience and ease of use.
Copyrights © 2026