The human body is a highly complex structure, and the presence of disorders further complicates its understanding. Gastrointestinal disorders are one of the issues that affect approximately 40% of the global population. In cases of intestinal disorders, diagnosis can sometimes be challenging, thereby necessitating the use of Wireless Capsule Endoscopy (WCE) for accurate internal observation. Different algorithms have boosted the use of AI and DL for medical imaging. In our research, we propose a DL-based algorithm for the identification and classification of GI tract issues from endoscopic images. The CNN is the base architecture with the highest accuracy rate for medical imaging. The system combines multiple layers into the algorithm using various image pre-processing techniques to enhance the accuracy rate. The algorithm is applied to eight different classes of intestinal diseases and achieves an accuracy of more than 90% for each class. Early detection is a blessing to the patient to giving them time to recover. We aim to narrate the potential of AI, DL techniques for endoscopic investigations and try to provide insights for future research directions through this paper.