AI Based Student Connect Porta

The AI-Based Student Connect Dashboard does what it set out to do — it builds a smarter, more secure communication layer between students, faculty, parents, and administrators. Bringing together AI, NLP, and cloud infrastructure in one platform means less manual work, better transparency, and faster access to academic information for everyone involved. Prompt-to-SQL querying lets faculty retrieve student data in plain English. Students and parents get summarized notices, multilingual updates, and grievance tracking without having to chase anyone down for information. That's a meaningful shift from how most academic portals currently work. The cloud-based architecture means the system can scale as needed and stay available without interruption — which matters in any real institutional setting. IAM-based authentication and role-aware retrieval ensure the right people see the right data, and nothing more. At its core, this project shows that AI-powered automation isn't just a theoretical upgrade for campus communication. It's a practical one — and this system is a concrete step toward making academic environments genuinely smarter and more connected.

[1]     Jooyoung Jeong, Sang-Goo Lee, “Permission-Aware RAG: Identity and Access Management (IAM)-Based Access Filtering in Multi-Resource Environments” IEEE, Dec 2024. [2]     Buchepalli Praneeth, Mohana, Eshitha Chowdary Nattem, et al., “Optimization of Customer Feedback Summarization Using Large Language Models (LLM) and Advanced Augmented Retrieval Generation”, IEEE, July 2025. [3]     Rodrigo Pedro, Miguel E. Coimbra, Daniel Castro, Paulo Carreia, Nuno Santos, “Prompt to-SQL Injections in LLM Integrated Web Applications: Risks and Defence”, 2025. [4]     Y. Gao et al., K. M. Fitria, “Retrieval Augmented Generation for Large Language Models”, Feb 2025. [5]     L. Ammann, S. Ott, C. R. Landolt, and M. P. Lehmann, “Securing RAG: A Risk Assessment and Mitigation Framework”, 2024. [6]     H. Liu, X. Chen, and X. Liu, “Application of Weight Distribution Method”. [7]     Combining Sentiment Dictionary and TF-IDF for Text Sentiment Analysis”, 2022. [8]     K. Muludi, K. M. Fitria, and J. Triloka, “Retrieval Augmented Approach: Document Generation Question Answering Using Large Language Models”, July 2023. [9]     X. Li, Y. Cao, Y. Ma, and A. Sun, “Long Context vs. RAG for LLMs: An Evaluation and Revisits”, 2024. [10]   Pedro et al., Li et al., “Natural Language to SQL Querying”, 2025.