Dysgraphia is a learning disability that significantly impacts an individual's ability to communicate effectively, leading to negative consequences for their mental well-being, self-assurance, and overall behavior. This neurological condition results in impaired verbal expression, written communication, and knowledge acquisition, leading to impaired and disoriented writing. The challenging traditional approaches in addressing dysgraphia include individualized occupational therapy sessions, which can be both expensive and time-consuming. This study delved into diagnosing dysgraphia using a machine learning approach, Convolutional Neural Networks (CNN) to distinguish handwriting differences between dysgraphic and non dysgraphic individuals on an alphabetical letter-based dataset of images. The inclusive intent of the paper is to provide well-refined and easy-flowing engagements for individuals suffering from dysgraphia. It aims to reinvent the mainstream education system providing a helping hand for dysgraphic students to attain their first step towards academic excellence.