AI-Powered Tour Planner using Multi-Agent System

Abstract

This paper presents a comprehensive AI-Powered Tour Planner that automates and personalizes travel itinerary creation using an intelligent multi-agent architecture integrated with cloud automation. The system leverages Azure Foundry AI Agents and Amadeus APIs to streamline end-to-end travel planning—from flight searches and hotel bookings to itinerary recommendations. Azure Logic Apps orchestrate API communication and workflow automation, ensuring seamless interaction between user inputs, AI-driven logic, and external travel data sources. The frontend layer combines Flask for the conversational interface and React for visualization, enabling real-time interaction with structured travel data. This research highlights the power of multi-agent systems, cloud orchestration, and API-driven architectures in revolutionizing modern tourism applications.

Introduction

The rapid advancement of AI and cloud computing has transformed travel planning, which traditionally involves time-consuming manual searches across multiple platforms. To address this, an AI-Powered Tour Planner is proposed, using a multi-agent framework to automate flight search, hotel booking, and itinerary generation. The system integrates Azure Foundry AI Agents for agent coordination, Azure Logic Apps for workflow automation, and Amadeus APIs for real-time travel data.

Objectives of the system include:

1. Automating tour planning via AI workflows.

2. Integrating real-time travel APIs for accurate bookings.

3. Leveraging Azure Logic Apps for cloud automation and error handling.

4. Developing a conversational AI interface with Flask.

5. Building a scalable React dashboard for itinerary visualization.

Literature review shows that early rule-based travel systems lacked flexibility, whereas modern AI and cloud platforms enable intelligent, context-aware automation. This system builds on these advancements by combining multi-agent intelligence with cloud orchestration.

System architecture comprises three AI agents:

• Booking Agent: Handles flight and hotel searches.

• Tourist Finder: Suggests attractions based on user preferences.

• Tour Planner: Consolidates the itinerary.

Azure Foundry AI Agents act as a communication hub, triggering Logic Apps to call Amadeus APIs. The backend uses Logic Apps for data processing, while the frontend includes a Flask chatbot and ReactJS dashboard for interaction and visualization. Data is exchanged via JSON to ensure interoperability.

Implementation and results show that the system efficiently retrieves travel data, automates workflows, and presents information intuitively via the chatbot and dashboard, demonstrating reliable and low-latency performance.This research successfully showcases how AI agents and cloud automation can transform tour planning. The combination of Azure Foundry AI Agents, Amadeus APIs, and Logic Apps creates a scalable and efficient framework for automated travel booking. Future enhancements include integrating secure payment gateways, real-time notifications, and advanced personalization using machine learning to recommend destinations based on user history.

Conclusion

This research successfully showcases how AI agents and cloud automation can transform tour planning. The combination of Azure Foundry AI Agents, Amadeus APIs, and Logic Apps creates a scalable and efficient framework for automated travel booking. Future enhancements include integrating secure payment gateways, real-time notifications, and advanced personalization using machine learning to recommend destinations based on user history.

References

[1] Amadeus API Documentation, https://developers.amadeus.com [2] Microsoft Azure Logic Apps, https://azure.microsoft.com/en-us/products/logic-apps [3] Flask Framework Documentation, https://flask.palletsprojects.com [4] ReactJS Official Documentation, https://react.dev [5] Azure AI Foundry, https://ai.azure.com [6] N. Nguyen and T. Ngo, \'AI in Tourism: A Review,\' Journal of Information Systems, 2023. [7] J. Smith et al., \'Intelligent Agents for Automated Travel Planning,\' IEEE Transactions on AI, 2022.

Copyright

Copyright © 2025 Kalyani Sonawane, Amey Raut, Parth Gaikwad, Vikrant Dike, Dhiraj Raysing. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.