IJIRCSTJournal International Journal of Innovative Research in Computer Science and Technology I S Volume 13 Issue 6 Computer Science English November - December 2025 N N Y 2025 12 19 Computer Sciences AI-Based Personalized Fitness Trainer: AI Real-Time Pose Estimation and Form Correction Using Computer Vision English Y 101 110 Suchetha N V English Y Skandan M J English N Suchint M Shetty English N Sagar D Patgar English N Nikhil M C English N https://doi.org/10.55524/ijircst.2025.13.6.11 Over the past few years, workout tech was able to utilise smart software and camera tracking to enhance training alone. This paper presents a fitness assistant that is a browser-based implementation that works on AI, automatically counting the reps and identifying the incorrect postures in real-time using a standard web camera. It takes the place of special gear by using tools such as MediaPipe and TensorFlow to map significant body points when exercising. These systems accompany your limbs in examining the way in which joints bend and move as time goes on. When something is out of place, feedback appears immediately - assistance in correcting the technique in time. This correctly improves the accuracy of learning and reduces the risk of exercise injury. The device is paired with an interactive online training program to train, monitor progress or review previous outcomes - no wearable devices are required. It has passed tests with regards to its ability to detect correct form during the execution of such moves as squats, lunges, or push-ups and pose checks. The proposed option would be effective in terms of online fitness, monitoring progress in recovery, or upgrading gym equipment - it provides a low-cost solution to exercise progression smarter. English Posture Analysis, Real-Time Feedback, Repetition Counting, Exercise Monitoring, Workout Tracking, MediaPipe Pose, Real-Time Detection, Pose Estimation, Skeleton Tracking, Motion Analysis https://ijircst.org/abstract.php?article_id=1420