This project proposes a next-generation intrusion detection system (IDS) using modern AI technologies. To improve threat identification and automate reporting, it makes use of deep learning, large language models (LLMs), federated learning, and other machine learning techniques. The system is built upon exhaustive preprocessing, feature extraction, and PCA (Principal Component Analysis) based dimensionality reduction on the CIC-IDS 2017 dataset. Random Forest's accuracy was 99.77% which was better than Logistic Regression (86.99%) and KNN (98.87%) in multi-classifier evaluations with Decision trees, Naive Bayes, Support Vector Machines (SVM), K-Nearest Neighbours (KNN), and Logistic Regression. A deep neural network based on LSTM is also used for learning temporal patterns, achieving 98.71% accuracy which proves effective against zero-day and advanced persistent threat attacks. To support adaptive privacy-preserving learning in distributed frameworks, a reinforcement-enhanced federated learning approach is applied which achieves near 90% accuracy at a global model level. After classifying the cyber threat, a custom LLM assistant is developed which takes three different outputs as inputs and automatically generates cyber threat summaries and reports. One can view or query these reports to extract pertinent information from the SQLite database. The system can be hosted on cloud platforms like AWS EC2 using Flask and Gradio for easier scalability. The approach blends interpretability, automation, and robustness which is true for the proposed IDS framework to significantly reduce false positives while maintaining real-time multi-task detection, responsiveness, and adaptability to swiftly changing network environments.