Om Rajendra Deokar,
Ashish Chincholikar,
Suraj Chothe,
Radhakrishna Naik,
- Student, Department of Computer Engineering Sanjivani College of Engineering, Maharashtra, India
- Student, Department of Computer Engineering Sanjivani College of Engineering, Maharashtra, India
- Student, Department of Computer Engineering Sanjivani College of Engineering, Maharashtra, India
- Student, Department of Computer Engineering Sanjivani College of Engineering, Maharashtra, India
Abstract
The Insurance Chatbot for Customer Support is an AI inspired solution designed to streamline customer interactions within the insurance industry. The main purpose of Large Language Models and Generative AI in the chatbot enhances accessibility to policy details, facilitates seamless policy enrollment and enables real time claims tracking. Its ability to process natural language queries ensures accurate and intuitive responses, significantly reducing customer confusion and operational inefficiencies. This chatbot addresses key challenges such as the complexity of insurance documents, delays in claims processing and the high demand for customer support. By automating routine queries and providing personalized guidance, it reduces manual effort, minimizes errors in claims, and enhances customer satisfaction. The chatbot employs vector-based similarity search for efficient document retrieval, integrates with LangServe and LangSmith for monitoring, and offers a scalable, 24/7 interactive interface via Streamlit. Chatbot Engine Powers the conversational aspect using a Large Language Model (LLM), like OpenAI and Generates responses based on user queries Through automation and advanced machine learning techniques, this solution optimizes operational workflows, improves trust and transparency in insurance services, and transforms customer engagement. The implementation of AI-driven chatbots in the insurance domain represents a significant step towards a more efficient, user-friendly, and accessible insurance experience.
Keywords: AI-powered chatbot, large language models (LLMs), generative AI, natural language processing (NLP), LangServe, LangSmith
[This article belongs to Journal of Computer Technology & Applications ]
References
- Javaid M, Haleem A, Singh RP. ChatGPT for healthcare services: An emerging stage for an innovative perspective. BenchCouncil Transactions on Benchmarks, Standards and Evaluations. 2023 Feb 1;3(1):100105.
- Grassini E, Buzzi M, Leporini B, Vozna A. A systematic review of chatbots in inclusive healthcare: insights from the last 5 years. Universal Access in the Information Society. 2025 Mar;24(1):195-203.
- Patil MV, Shree P, Singh P. AI based healthcare chat bot system. International Journal of Scientific & Engineering Research. 2021 Jul 25;12(7):1-4.
- Athota L, Shukla VK, Pandey N, Rana A. Chatbot for healthcare system using artificial intelligence. In2020 8th International conference on reliability, infocom technologies and optimization (trends and future directions)(ICRITO) 2020 Jun 4 (pp. 619-622). IEEE.
- Jegadeesan R, Srinivas D, Umapathi N, Karthick G, Venkateswaran N. Personal healthcare chatbot for medical suggestions using artificial intelligence and machine learning. European Chemical Bulletin. 2023;12(3):6004-12.
- Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S. Language models are few-shot learners. Advances in neural information processing systems. 2020;33:1877-901.
- Ouyang L, Wu J, Jiang X, Almeida D, Wainwright C, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A, Schulman J. Training language models to follow instructions with human feedback. Advances in neural information processing systems. 2022 Dec 6;35:27730-44.
- Zhang Y, Sun S, Galley M, Chen YC, Brockett C, Gao X, Gao J, Liu J, Dolan WB. Dialogpt: Large-scale generative pre-training for conversational response generation. InProceedings of the 58th annual meeting of the association for computational linguistics: system demonstrations 2020 Jul (pp. 270-278).
- Dekkal M, Prom Tep S, Arcand M, Rajaobelina L, Ricard L. “Ready for Your Insurance Quote?” the Impact of Chatbot Empathy on Emotions and User Experience. InInternational Conference on Marketing and Technologies 2023 Nov 30 (pp. 155-171). Singapore: Springer Nature Singapore.
- Zhao WX, Zhou K, Li J, Tang T, Wang X, Hou Y, Min Y, Zhang B, Zhang J, Dong Z, Du Y. A survey of large language models. arXiv preprint arXiv:2303.18223. 2023 Mar 31;1(2):1-24.
- Dange BJ, Kshirsagar DB. Hashing based re-ranking of web images using query-specific semantic signatures. In2017 1st International Conference on Intelligent Systems and Information Management (ICISIM) 2017 Oct 5 (pp. 164-170). IEEE.
- Ndimbo EV, Luo Q, Fernando GC, Yang X, Wang B. Leveraging retrieval-augmented generation for swahili language conversation systems. Applied Sciences. 2025 Jan 8;15(2):524.
- Painter JL, Chalamalasetti VR, Kassekert R, Bate A. Automating pharmacovigilance evidence generation: using large language models to produce context-aware structured query language. JAMIA open. 2025 Feb;8(1):ooaf003.
- Huang M, Yang W, Wu Y, Jiang J, Chen W, Feng Q. Brain tumor segmentation based on local independent projection-based classification. IEEE transactions on biomedical engineering. 2014 May 19;61(10):2633-45.
Journal of Computer Technology & Applications
| Volume | 17 | |
| Issue | 02 | |
| Received | 19/01/2026 | |
| Accepted | 13/05/2026 | |
| Published | 30/08/2026 | |
| Publication Time | 223 Days |