AI TEACH Innovators: A Privacy-First Conversational Business Intelligence Platform using Hybrid RAG, Knowledge Graphs, and Agentic AI with Local LLM Inference
DOI:
https://doi.org/10.15662/IJEETR.2026.0802390Keywords:
Retrieval-Augmented Generation, Knowledge Graph, Agentic AI, LangGraph, Local LLM, Ollama, Conversational Business Intelligence, LLM Guardrails, Hallucination Mitigation, Privacy-Preserving AI, ChromaDB, Neo4j, LiteLLMAbstract
Modern enterprises face growing complexity in extracting actionable intelligence from distributed, heterogeneous data sources while simultaneously facing regulatory pressure to maintain data privacy and sovereignty. Traditional cloud-based AI solutions require transmitting sensitive business data to external servers, making them fundamentally incompatible with GDPR, HIPAA, and sector-specific compliance frameworks. This paper presents AI TEACH Innovators, a production-grade, fully offline conversational business intelligence (BI) platform that integrates Hybrid Retrieval-Augmented Generation (RAG), Knowledge Graphs, and a three-node Agentic AI pipeline to enable natural-language querying of enterprise data entirely on-device. The system leverages Ollama as a fully local Large Language Model (LLM) inference engine routed through a LiteLLM proxy, guaranteeing that no data leaves the user's premises at any stage. A five-layer guardrail engine enforces input safety, document scoping, semantic relevance filtering, Personally Identifiable Information (PII) redaction, and hallucination detection. Knowledge Graphs powered by Neo4j provide causal reasoning over Key Performance Indicator (KPI) relationships, while ChromaDB and sentence-transformer embeddings enable dense semantic retrieval. Evaluation results demonstrate sub-15-second end-to-end response times, 100% offline operation, and robust hallucination mitigation with an 87.5% detection rate in the self-critique layer.
References
1. S. Pan, L. Luo, Y. Wang, C. Chen, J. Wang, and X. Wu, "Unifying large language models and knowledge graphs: A roadmap," IEEE Trans. Knowl. Data Eng., vol. 36, no. 7, pp. 3580-3599, Jul. 2024. DOI: 10.1109/TKDE.2024.3352100
2. T. Procko and O. Ochoa, "Graph retrieval-augmented generation for large language models: A survey," in Proc. IEEE Conf. Artif. Intell. (IEEE CAI), Singapore, 2024. DOI: 10.1109/CAI59869.2024.00205
3. R. Kumar, K. Ishan, H. Kumar, and A. Sharma, "LLM-powered knowledge graphs for enterprise intelligence and analytics," in Proc. IEEE Int. Conf. (ICSPCS), 2025. DOI: 10.1109/ICSPCS64044.2025.11088890
4. Fayazi, C. Wang, M. Bettini, and A. Trezza, "From data to decisions: Enterprise-level domain-specific graph retrieval-augmented generation systems for advanced question answering," in Proc. IEEE Int. Conf. Big Data, 2025. DOI: 10.1109/BigData62323.2024.10936909
5. E. Kutlu, S. Gul, and Y. T. Ic, "Retrieval augmented generation (RAG) and LLM integration," in Proc. IEEE Int. Conf. Comput. Sci. Eng. (UBMK), 2025. DOI: 10.1109/UBMK63289.2024.10845308
6. M. Devino, E. Ju, and P. M. Caldeira Junior, "Designing and implementing LLM guardrails components in production environments," in Proc. IEEE/ACM 4th Int. Conf. AI Eng. (CAIN), 2025, pp. 12-17. DOI: 10.1109/CAIN62612.2025.11029999
7. M. Cheung, "Hallucination detection with small language models," in Proc. IEEE Int. Conf. Inf. Technol. (ICIT), 2025. DOI: 10.1109/ICIT62883.2025.11108162
8. C.Nagarajan and M.Madheswaran - ‘Stability Analysis of Series Parallel Resonant Converter with Fuzzy Logic Controller Using State Space Techniques’- Taylor &Francis, Electric Power Components and Systems, Vol.39 (8), pp.780-793, May 2011. DOI: 10.1080/15325008.2010.541746
9. C.Nagarajan and M.Madheswaran - ‘Experimental verification and stability state space analysis of CLL-T Series Parallel Resonant Converter’ - Journal of Electrical Engineering, Vol.63 (6), pp.365-372, Dec.2012. DOI: 10.2478/v10187-012-0054-2
10. C.Nagarajan and M.Madheswaran - ‘Performance Analysis of LCL-T Resonant Converter with Fuzzy/PID Using State Space Analysis’- Springer, Electrical Engineering, Vol.93 (3), pp.167-178, September 2011. DOI 10.1007/s00202-011-0203-9
11. S.Tamilselvi, R.Prakash, C.Nagarajan,“Solar System Integrated Smart Grid Utilizing Hybrid Coot-Genetic Algorithm Optimized ANN Controller” Iranian Journal Of Science And Technology-Transactions Of Electrical Engineering, DOI10.1007/s40998-025-00917-z,2025
12. S.Tamilselvi, R.Prakash, C.Nagarajan,“ Adaptive sliding mode control of multilevel grid-connected inverters using reinforcement learning for enhanced LVRT performance” Electric Power Systems Research 253 (2026) 112428, doi.org/10.1016/j.epsr.2025.112428
13. S.Thirunavukkarasu, C. Nagarajan, 2024, “Performance Investigation on OCF and SCF study in BLDC machine using FTANN Controller," Journal of Electrical Engineering And Technology, Volume 20, pages 2675–2688, (2025), doi.org/10.1007/s42835-024-02126-w
14. C. Nagarajan, M.Madheswaran and D.Ramasubramanian- ‘Development of DSP based Robust Control Method for General Resonant Converter Topologies using Transfer Function Model’- Acta Electrotechnica et Informatica Journal , Vol.13 (2), pp.18-31,April-June.2013, DOI: 10.2478/aeei-2013-0025.
15. C.Nagarajan and M.Madheswaran - ‘DSP Based Fuzzy Controller for Series Parallel Resonant converter’- Springer, Frontiers of Electrical and Electronic Engineering, Vol. 7(4), pp. 438-446, Dec.12. DOI 10.1007/s11460-012-0212-0.
16. C.Nagarajan and M.Madheswaran - ‘Experimental Study and steady state stability analysis of CLL-T Series Parallel Resonant Converter with Fuzzy controller using State Space Analysis’- Iranian Journal of Electrical & Electronic Engineering, Vol.8 (3), pp.259-267, September 2012.
17. C.Nagarajan and M.Madheswaran, “Analysis and Simulation of LCL Series Resonant Full Bridge Converter Using PWM Technique with Load Independent Operation” has been presented in ICTES’08, a IEEE / IET International Conference organized by M.G.R.University, Chennai.Vol.no.1, pp.190-195, Dec.2007
18. Suganthi Mullainathan, Ramesh Natarajan, “An SPSS and CNN modelling based quality assessment using ceramic materials and membrane filtration techniques”, Revista Materia (Rio J.) Vol. 30, 2025, DOI: https://doi.org/10.1590/1517-7076-RMAT-2024-0721
19. M Suganthi, N Ramesh, “Treatment of water using natural zeolite as membrane filter”, Journal of Environmental Protection and Ecology, Volume 23, Issue 2, pp: 520-530,2022
20. Rasheed et al., "Agentic AI: A comprehensive survey of technologies, architectures, applications, and challenges," IEEE Access, vol. 13, pp. 43059-43089, 2025. DOI: 10.1109/ACCESS.2025.3549268
21. X. Li et al., "LLM-powered multi-agent systems: A technical framework for collaborative intelligence," in Proc. IEEE Int. Conf. Adv. Artif. Intell. (ICAAI), 2025. DOI: 10.1109/ICAAI64093.2025.11077480
22. M. Baldini, G. Curia, and D. Pedrazzi, "Privacy-preserving LLM-based chatbots for hypertensive patient self-management," Smart Health, vol. 35, p. 100512, Mar. 2025. DOI: 10.1016/j.smhl.2025.100512
23. Y. Chen, H. Li, W. Zhao, and J. Yin, "Mitigating privacy risks in retrieval-augmented generation via locally private entity perturbation," Inf. Process. Manage., vol. 62, no. 4, p. 104138, 2025. DOI: 10.1016/j.ipm.2025.104138
24. L. Yan, C. Tang, Z. Ye, J. Zhao, P. Yu, and Y. Chen, "On protecting the data privacy of large language models (LLMs) and LLM agents: A literature review," Comput. Secur., vol. 152, p. 104413, May 2025. DOI: 10.1016/j.csa.2025.100083
25. Gopinathan, V. R. (2024). Real-Time Fault-Tolerant Multi-Cloud Database Architectures for High Availability Ap-plications. International Journal of Future Innovative Science and Technology (IJFIST), 7(4), 13148.
26. Chandra, S., Rengarajan, A., Sahoo, G. S., & Sharma, S. (2023, December). Identifying Neuronal Damage and Plasticity by Analyzing Changes in Diffusion Tensor Imaging. In International Conference on Data Science, Ma-chine Learning and Applications (pp. 433-438). Singapore: Springer Nature Singapore.
27. Sugumar, R. (2025). Federated AI in Offline-First Mobile Health Architectures for Privacy-Preserving Clinical In-telligence. International Journal of Science, Research and Technology, 8(4), 14589-14600.
28. Murugeshwari, B., Rajalakshmi, S., & Sudharson, K. (2023). Hybrid Approach for Privacy Enhancement in Data Mining Using Arbitrariness and Perturbation. Computer Systems Science & Engineering, 44(3).
29. Pandey, V. K., Mishra, S., Rengarajan, A., Savita, & Roomi, M. M. (2024, March). Enhancing Weather Forecasting with Machine Learning Techniques. In International Conference on Renewable Power (pp. 147-156). Singapore: Springer Nature Singapore.
30. Soundappan, S. J. (2025). Next Generation AI Enabled Holistic Cognitive Platform for Secure Cloud Network In-telligence Enterprise Systems and Digital Trust Optimization. International Journal of Computer Technology and Electronics Communication, 8(5), 11534-11542.
31. Mathew, A. (2022). Leveraging Big Data Analytics to Power AI and ML (Machine Learning) Automation. Educa-tional Research (IJMCER), 4(5), 131-134.
32. Sugumar, R. (2024). AI-Augmented Quality Engineering for Performance Optimization and Test Orchestration in Distributed Systems. International Journal of Science, Research and Technology, 7(5), 12835-12846.
33. Akila, R. (2024). A deep reinforcement learning approach for optimizing inventory management in the agri-food supply chain. J. Electrical Systems, 20(4s), 2238-2247.
34. Mahendran, M., Anbazhagan, K., Pavithran, G., Nivas, A., & Pandey, S. D. (2022). Earthquake Damage Prediction using Machine Learning. Grenze International Journal of Engineering & Technology (GIJET), 8(1).
35. Gopinathan, V. R. (2025). Enterprise AI Frameworks for Financial Data Engineering Behavioural Analytics and Intelligent Cloud Solutions. International Journal of Research Publications in Engineering, Technology and Man-agement (IJRPETM), 8(4), 12499-12506.
36. Kondalsamy, P., & Kaliappan, K. (2025). An Optimal Prediction of Leaf Disease Based on Hybrid Deep Learnings and Metaheuristic Technique. Traitement du Signal, 42(1), 363.
37. Deivendran, P., Babu, P. S., Malathi, G., Anbazhagan, K., & Kumar, R. S. (2023). Emotion Recognition for Chal-lenged People Facial Appearance in Social using Neural Network. arXiv preprint arXiv:2305.06842.
38. Sugumar, R. (2025). Unified AI Framework for Predictive Data Engineering and Real Time Prescription and Billing Systems. International Journal of Advanced Engineering Science and Information Technology (IJAESIT), 8(5), 17261.
39. Vekariya, V., Kumar, S., & Rengarajan, A. (2024). A distinctive and smart agricultural knowledge-based frame-work using ontology. In Sustainability in Digital Transformation Era: Driving Innovative & Growth (pp. 207-213). CRC Press.
40. Gopinathan, V. R. (2025). Software engineering practices for AI-driven systems: From development to deployment (MLOps perspective). International Journal of Science, Research and Technology, 8(1), 13493-13500.
41. Mathew, A. R. (2022). Threats and protection on E-sim: a prospective study. Novel Perspectives of Engineering Research, 8, 76-81.
42. Naveena, S., & Kavitha, K. (2025). Gossypium herbaceum: Folium disease identification and classification using Efficient Net-Coordinate Convolutional Neural Network (EcoNet). Engineering Applications of Artificial Intelli-gence, 152, 110701.
43. Rengarajan, A., Mishra, A., Kulhar, K. S., Shrivastava, V. P., & Alawneh, Y. J. J. (2024, March). Role of Deep Reinforcement Learning in Mitigating Cyber Security Issues: A Review. In International Conference on Renewa-ble Power (pp. 37-48). Singapore: Springer Nature Singapore.
44. Achari, A. P. S. K., & Sugumar, R. (2024, November). Performance analysis and determination of accuracy using machine learning techniques for naive bayes and random forest. In AIP Conference Proceedings (Vol. 3193, No. 1, p. 020199). AIP Publishing LLC.
45. Mathew, A., & Alex, H. (2022). Detect & protect-medical device cybersecurity. Curr. Overview Sci. Technol. Res, 1, 60-68.
46. Sammy, F., Chettier, T., Boyina, V., Shingne, H., Saluja, K., Mali, M., ... & Shobana, A. (2025). Deep Learning-Driven Visual Analytics Framework for Next-Generation Environmental Monitoring. Journal of Applied Science and Technology Trends, 114-122.
47. Anbazhagan, K. (2024). Trustworthy and Adaptive AI Systems for Enterprise Analytics Cybersecurity and Decision Optimization Using API-First and Cloud-Native Architectures. International Journal of Technology, Management and Humanities, 10(03), 65-74.
48. Mathew, A. (2021). Deep reinforcement learning for cybersecurity applications. Int J Comput Sci Mob Compu, 10(12), 32-38.
49. Dhinakaran, D. (2022). Joe Prathap P. M, Selvaraj D, Arul Kumar D and Murugeshwari B," Mining Privacy-Preserving Association Rules based on Parallel Processing in Cloud Computing,". International Journal of Engi-neering Trends and Technology, 70(3), 284-294.
50. Karthika, K., Anusha, K., Kavitha, K., Harshadha, R., Dharshini, D. S., & Sundhar, N. A. (2025, April). Frequency Reconfigurable Antenna using Advanced Materials: A Study. In 2025 3rd International Conference on Advance-ments in Electrical, Electronics, Communication, Computing and Automation (ICAECA) (pp. 1-6). IEEE.
51. Thavamani, C., & Rengarajan, A. (2024). Clustering related behaviour of users by the use of partitioning and parallel transaction reduction algorithm. International Journal of Advanced Intelligence Paradigms, 29(2-3), 122-132.
52. Sugumar, R. (2025). Unified AI Framework for Predictive Data Engineering and Real Time Prescription and Billing Systems. International Journal of Advanced Engineering Science and Information Technology (IJAESIT), 8(5), 17261.
53. Soundappan, S. J., & Sugumar, R. (2016). Optimal knowledge extraction technique based on hybridisation of im-proved artificial bee colony algorithm and cuckoo search algorithm. International Journal of Business Intelligence and Data Mining, 11(4), 338-356.
54. SakthiPreetha, A., Kavitha, K., Karthika, K., & Manohari, R. G. (2025, April). A Novel Metasurface-Embedded Antenna for WBAN Communications. In 2025 3rd International Conference on Advancements in Electrical, Elec-tronics, Communication, Computing and Automation (ICAECA) (pp. 1-4). IEEE.
55. Murugeshwari, B., Selvaraj, D., Sudharson, K., & Radhika, S. (2023). Data Mining with Privacy Protection Using Precise Elliptical Curve Cryptography. Intelligent Automation & Soft Computing, 35(1).
56. Gopinathan, V. R. (2025). Software engineering practices for AI-driven systems: From development to deployment (MLOps perspective). International Journal of Science, Research and Technology, 8(1), 13493-13500.
57. Anbazhagan, K., Kumar, R., Thilagavathy, R., & Anuradha, D. (2024, March). Shortest Job First with Gateway-based Resource Management Strategy for Fog Enabled Cloud Computing. In 2024 4th International Conference on Data Engineering and Communication Systems (ICDECS) (pp. 1-6). IEEE.
58. Kannadhasan, S., Vasuki, S., Kavitha, K., Karthikeyan, P., & Usha, S. G. A. (Eds.). (2025, April). Preface: Role of Artificial Intelligence and IoT in Engineering, Technology & Science [ICRAETS 2024]. In AIP Conference Pro-ceedings (Vol. 3258, No. 1, p. 010001). AIP Publishing LLC.
59. Dhinakaran, D., Prathap, P. J., Selvaraj, D., Kumar, D. A., & Murugeshwari, B. (2022). Mining privacy-preserving association rules based on parallel processing in cloud computing. International Journal of Engineering Trends and Technology, 70(3), 284-294.
