Glaucoma is a serious, chronic, and progressive eye disease that can lead to irreversible blindness. The early phase of the condition is particularly critical, as it often remains unnoticed by the patient. Glaucoma is a leading cause of vision loss worldwide, which underscores the importance of screening and continuous monitoring of disease progression. Traditional diagnostic methods include intraocular pressure measurement, gonioscopy, fundus examination, optical coherence tomography, and visual field testing. However, the subjective nature of result interpretation and the time-intensive character of procedures have prompted growing interest in artificial intelligence. In recent years, substantial advances in artificial intelligence applications have significantly improved workflow and efficiency across various medical domains. The implementation of artificial intelligence in glaucoma diagnostics may lead to considerable improvements in ophthalmology by enabling earlier detection of individuals at risk, reducing the number of patients who lose their vision, and decreasing the burden on physicians while improving the overall quality of patient care. This paper presents a review of literature published over the past decade, examining the foundations of operation of artificial intelligence, the effectiveness of algorithms in identifying glaucomatous changes, and their capacity to assess disease risk. The review includes an in-depth evaluation of the diagnostic potential and possible limitations of artificial intelligence in diagnosing glaucoma.