diff --git a/submissions.json b/submissions.json
index b03a161..0328f0d 100644
--- a/submissions.json
+++ b/submissions.json
@@ -53,6 +53,12 @@
     "repository_url": "https://github.com/abhay-7-7-7/ResqRoute.git",
     "description": "Introduction Every second counts in a medical emergency. In heavy traffic, ambulances struggle to reach hospitals on time, costing precious lives. Our integrated system combines AI-powered traffic management with Digital Twin technology inside the ambulance to ensure seamless emergency response. Problem Statement\n\nTraffic congestion causes significant delays in emergency response times.\nLack of real-time traffic management leads to inefficiencies in clearing paths for ambulances.\nManual intervention by traffic police is often slow and ineffective.\nMedical professionals in hospitals lack real-time patient data before arrival.\nCritical treatments are delayed due to lack of immediate health insights.\nDoctors often have to make instant decisions with limited patient data, increasing the risk of errors. Proposed Solution: AI-Powered Emergency System Our AI-driven system integrates two key technologies:\nResQRoute: AI-based traffic management that detects ambulances and clears traffic automatically.\nDigital Twin for Health: Inside the ambulance, AI builds a real-time patient clone using medical data to predict their health status and guide doctors before arrival.\nDoctor Preparation System: AI provides hospitals with real-time patient insights, ensuring the medical team is prepared for immediate treatment upon arrival. How It Works\nAmbulance Detection: AI cameras recognize ambulance symbols and prioritize traffic light changes.\nReal-Time Traffic Adjustment: AI controls traffic signals dynamically to create an open path.\nPatient Cloning Inside Ambulance: Medical devices inside the ambulance monitor vital signs and feed data to an AI model to simulate future health conditions.\nDoctor & Hospital Preparation:\nAI provides a real-time patient health clone to doctors.\nDoctors analyze vital trends and predict possible complications before arrival.\nAI suggests probable treatments based on patient history and symptoms.\nHospital staff prepares the necessary operation theaters, ICUs, or emergency rooms based on AI risk assessment.\nOptimized Emergency Care: Predictive analytics help doctors make faster, more accurate decisions for treatment.\n\n\nHere is the website like we deployed using streamlit: https://resqroute.streamlit.app/"
   },
+  {
+    "name": "Arathy B S",
+    "project_name": "Intelligent Legal Research for Enhanced Decision Making",
+    "repository_url": "https://github.com/abhiabhi1474/Intelligent-Legal-Research-For-Enhanced-Decision-Making.git",
+    "description": "This project is a Flask-based API designed to analyze legal scenarios, retrieve relevant laws, and predict legal outcomes using Natural Language Processing (NLP) and Machine Learning (ML). It helps users by identifying applicable laws, finding past legal precedents, and estimating case success probabilities."
+  },
   {
     "name": "Ram Madhav",
     "project_name": "Blood result analyzer",