Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{204016,
        author = {Sakshi Auti and Sangita Jaybhaye and Shraddha Mankar and Gaurang Wankhade and Pranav Bagade and Aditya Kulkarni},
        title = {GlobalBridge AI - An Autonomous Multi-Agent System for Trade Compliance and Logistics},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {877-885},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204016},
        abstract = {International trade operates in a rapidly changing and highly regulated environment where businesses frequently face challenges such as policy updates, inconsistent documentation, and fragmented logistics systems. These issues are particularly difficult for small and medium-sized enterprises (SMEs) that still depend on manual compliance procedures, which are time-consuming, error-prone, and often result in shipment delays, penalties, and financial losses. This paper introduces GlobalBridge AI, an intelligent multi-agent framework developed to improve compliance verification and logistics decision-making by combining generative AI with an agent-based architecture. The system uses specialized agents connected through the Model Context Protocol (MCP) to enable smooth communication with multiple data sources and external services. To enhance reliability and transparency, the framework applies a hybrid validation method that combines Retrieval-Augmented Generation (RAG) with rule-based verification. Testing on more than 15,000 international trade documents achieved a compliance accuracy of 99.2% while reducing manual effort by 94.7%. The framework also includes a buyer recommendation module that uses semantic embeddings and real-time market data to achieve 96.8% precision, while its edge-optimized design supports faster and more efficient performance, making it a scalable and practical solution for intelligent trade automation.},
        keywords = {Agentic AI, Multi-Agent Systems, Generative AI, Model Context Protocol, Trade Compliance Automation, Harmonized System Classification, Retrieval-Augmented Generation, Cognitive Logistics, Cross-Border Trade Intelligence.},
        month = {June},
        }