International Journal For Multidisciplinary Research

E-ISSN: 2582-2160   •   Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 8, Issue 6 (November-December 2026) Submit your research before last 3 days of December to publish your research paper in the issue of November-December.

MindGuard: An AI-Powered Agentic Student Mental Wellness Monitoring and Intervention System.

Author(s) Ms. Tejaswini M, Dr. Naseer, Dr. Sreenivasa B R
Country India
Abstract Student mental health has emerged as a critical concern in academic institutions worldwide, with increasing rates of anxiety, depression, and burnout going undetected until they significantly impair academic performance and personal wellbeing. Traditional approaches that rely on periodic counselor check-ins or self-referral fail to capture the continuous, evolving nature of student wellness. This paper presents MindGuard, an AI-powered agentic system that continuously monitors multi-dimensional student wellness signals including daily attendance patterns, academic scores, social interaction levels, emotional states captured by teachers, and free-text journal entries and uses a large language model
(LLaMA 3.3 70B via Groq API) to perform structured risk assessment, generate targeted intervention plans, and automatically alert mentor staff. The platform includes a CBT-informed conversational agent called MindGuard AI, a voice journaling feature that converts speech to text using Groq Whisper, and anonymous peer support groups monitored by AI. Role-based permissions (Admin, Teacher, Student) protect privacy and control who sees what. The server side runs on Flask with a MySQL database using parameterized queries, and the front end presents trend visualizations with Chart.js. In tests with a small, seeded dataset of five students over a seven-day period, the system reliably distinguished between Low, Medium, and High risk levels and offered practical, context-sensitive intervention suggestions. By combining continuous behavior tracking with timely, clinically grounded recommendations, MindGuard aims to offer a scalable web solutionthat connects everyday student experiences with appropriate wellness support
Keywords Student Mental Wellness, AI Agent, Large Language Model, LLaMA 3, Groq API, Cognitive. Behavioral Therapy, Voice Journal, Peer Support, Risk Assessment, Flask, Intervention System, Agentic AI.
Field Sociology > Education
Published In Volume 8, Issue 4, July-August 2026
Published On 2026-07-22

Share this