Authors : S. Saraswathi; Thamizharasu S.; Adarsh P.; Sourashish Roy

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/bdfnvz7x

DOI : https://doi.org/10.38124/ijisrt/26apr950

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Modern AI-assisted software development tools improve productivity but face key challenges such as context loss, fragmented knowledge access, lack of standardized communication, and poor workflow integration. This paper presents Contextiva, a context-aware knowledge management and AI task orchestration platform that addresses these limitations through a unified architecture integrating Retrieval-Augmented Generation (RAG), Model Context Protocol (MCP), and intelligent web crawling. Contextiva employs a multi-strategy Agentic RAG framework combining semantic, keyword, and hybrid retrieval with adaptive reranking to enhance accuracy and relevance. The MCP layer enables standardized communication between AI agents and system services, supporting real-time knowledge access and task management. Additionally, intelligent document processing techniques such as chunking, code extraction, and embedding generation enable scalable knowledge representation. Experimental results demonstrate improved retrieval performance, contextual accuracy, and workflow efficiency compared to traditional approaches. Overall, Contextiva transforms AI from a passive assistant into an active, contextaware collaborator in software development.

Keywords : Context-Aware Systems, Retrieval-Augmented Generation (RAG), Model Context Protocol (MCP), Agentic RAG, Knowledge Management, Semantic Search, AI Task Orchestration.

References :

1. Padmavathi, Sreenivasachar, Raghavendra., “An AI Enabled Solution for Generating Executable Code from Architectural Specification,” Internation Journal of Engineering Research & Technology (IJERT)., Volume 14, Issue 06, June 2025.
2. Jayanti, M.A., & Han, X.Y., "Enhancing Model Context Protocol (MCP) with Context-Aware Server Collaboration", ArXiv, abs/2601.11595, 2026
3. Parwani, K, Das S, Vijay D.K., “Model Context Protocol (MCP): A Scalable Framework for Context-Aware Multi-Agent Coordination,” International Journal of Multidisciplinary Research., Volume 1, Issue 4, September 2025.
4. K. Muludi, K. M. Fitria., "Retrieval-Augmented Generation Approach: Document Question Answering using Large Language Model," International Journal of Advanced Computer Science and Applications (IJACSA)., Volume 15, Issue 3, 2024.
5. P. Singh, A. Jamdar, P Kaul., "Agentic Retrieval Augmented Generation: Advancing AI-Driven Information Retrieval and Processing," International Journal of Computer Trends and Technology., Volume 73, Issue 1, January 2025.
6. Surya Kuchibhotla, Sri Kuchibhotla., "Retrieval-Augmented Generation System for Dynamic Document Tagging and Query-Driven Retrieval," International Journal of Science and Research Archive (IJSRA)., Volume 16, Issue 1, July 2025
7. N. Kolhare, R. Dhapse, Om Patil, B. Kore., "Proposing a RAG-Based System for Context-Aware Healthcare Monitoring," International Journal of Engineering Research & Technology (IJERT)., Volume 14, Issue 4, May 2025.
8. Padmavathi, Sreenivasachar, Raghavendra., "IRIS: Intelligent Retrieval Information System," International Journal of Engineering Research & Technology (IJERT)., Volume 14, Issue 6, June 2025.
9. W. Huang, Z. Gu, C. Pen., "AUTOSCRAPER: A Progressive Understanding Web Agent for Web Scrapper Generation," In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing., pages 2371–2389, Miami, Florida, USA. Association for Computational Linguistics , November 2024.
10. M. J. Elliot, M. Luciano, J. Fortes., "AI-Assisted Exploration, Curation, and Extension of Biodiversity Data Using iChatBio," Biodiversity Information Science and Standards, 9. e181968, December 2025.
11. B. Jiang, Q. Fan, J. Zhou., "Effectiveness Evaluation and Application of Large Language Model in Data-Driven Teaching Decision-Making," International Journal of Evaluation and Research in Education (IJERE)., Volume 14, Issue 3, June 2025.
12. L. Chaimaa, S. Swetha, E. Myriam, L. Imen., "Web Scrapping Techniques and Applications: A Literature Review", SCRS Conference Proceedings on Intelligent Systems., 2021
13. Sanikommu N. R., “Model Context Protocol: Enhancing LLM Performance for Observability and Analytics”, European Journal of Computer Science and Information Technology,13(29),112-126, May 2025
14. Yu, H., Gan, A., Zhang, K., Tong, S., Liu, Q., Liu, Z.., “Evaluation of Retrieval-Augmented Generation: A Survey”. Communications in Computer and Information Science, vol 2301, 2025.
15. Puri, Ruchir & Kung, David & Janssen, Geert & Zhang, Wei & Domeniconi, Giacomo & Zolotov, Vladmir & Dolby, Julian & Chen, Jie & Choudhury, Mihir & Decker, Lindsey & Thost, Veronika & Buratti, Luca & Pujar, Saurabh & Finkler, Ulrich. “Project CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks”. 10.48550/arXiv.2105.12655, 2021.
16. Chen, Mark et al. “Evaluating Large Language Models Trained on Code.” ArXiv abs/2107.03374., 2021.
17. Gan, Aoran et al. “Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey.” ArXiv abs/2504.14891., 2025.
18. Chanhee Park, Hyeonseok Moon, Chanjun Park, and Heuiseok Lim., “MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation”. In Findings of the Association for Computational Linguistics: NAACL, 2025.
19. Abdallah, Abdelrahman et al. “RerankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback.” Proceedings of the 34th ACM International Conference on Information and Knowledge Management., 2025.

20. Shahul Es, Jithin James, Luis Espinosa Anke, and Steven Schockaert., “RAGAs: Automated Evaluation of Retrieval Augmented Generation”. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 150–158, 2024.