The complicated endocrine condition known as Polycystic Ovarian Syndrome (PCOS) affects a large percentage of women. This research study presents a full web application for PCOS screening with a simple and complex testing options and an Artificial Intelligence (AI) chat-bot for support. In order to serve a wide range of users, the web application offers both basic tests which require little input from the user and complicated tests that allow the integration of medical records for a more thorough assessment. The Random Forest (RF) method was used to create a PCOS diagnosis model after comprehensive feature engineering and data gathering using a well-known dataset. To improve the predictive performance of the model, the most efficient method has been chosen through a thorough comparison examination of several algorithms. The Da Vinci model from OpenAI, which is an AI-assisted chat-bot uses via API calls, is a useful tool for people looking for advice, solutions, and assistance with treating PCOS. To guarantee the quality and dependability of the PCOS detection model, extensive data cleaning and feature engineering techniques were implemented. This research demonstrates how AI and web technologies may be used to provide a user-friendly, approachable, and educational PCOS diagnostic and support solution.