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{189096,
        author = {Kalyani Umate and Chetana Khandale and Tanvi  Uchake and Chetan Funde and Kajal Wagh and Aditya Gowardhan},
        title = {LangGraph Using Customer Service & Multiagent Workflow (E-commerce Platform)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {4886-4891},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189096},
        abstract = {This research delineates the design and execution of an intelligent multi-agent workflow system developed with LangGraph and driven by Groq's high- velocity, complimentary large language models (LLMs). The system is designed to automatically send tasks to the right agents based on their difficulty and type, with the goal of maximising speed, scalability, and accuracy.
A router agent first looks at incoming tasks and sends simple questions to a fast-response agent, complex reasoning tasks to an advanced analysis agent, and multi- modal inputs with images to a vision agent that uses an open-source multi-modal model.
The architecture includes a human-in-the-loop (HITL) review step for tasks that need human judgement. This makes sure that the system is strong and that the quality is good. LangGraph's ability to model complex state machines is used in the workflow to make orchestration clear and easy to keep up with.
The primary contribution of this work is a scalable framework that illustrates the practical implementation of free, performance-optimized large language models (LLMs) in developing cost-effective automation solutions for enterprise-level applications, encompassing customer support, visual data processing, and intricate decision- making pipelines.},
        keywords = {Multi-Agent Systems, LangGraph, Groq, Large Language Models (LLMs), Task Routing, Human-in-the- Loop (HITL), Workflow Automation, Multi-Modal AI, Scalable Architecture, Decision Pipelines.},
        month = {December},
        }