Travel planning can be challenging as it requires balancing user preferences, budget, time constraints, and destination details. Many travellers rely on multiple platforms to organize their trips, which makes the process time-consuming and complex. With the advancement of Artificial Intelligence (AI), automated itinerary planners can now generate personalized and optimized travel schedules more efficiently.

This paper presents an AI-driven itinerary planner developed using the Iterative Software Development Model to allow continuous improvement through repeated cycles of analysis, design, and testing. The system uses machine learning and natural language processing techniques to recommend relevant points of interest, organize routes, and adapt plans based on user input. Real-time data from APIs such as Google Places and Open Weather ensures that recommendations remain accurate and context aware.

Unlike traditional static travel tools, the proposed system offers flexibility, customization, and scalability. By combining personalization with real-time data integration, the system reduces manual effort and enhances the overall travel planning experience.