We live in the age of automation, and businesses have made great strides in recent years toward fully mechanizing their industrial processes. In the proposed research, we use AI to help us carry out responsibilities and jobs normally performed by humans, and we advise automating the required procedures for both the industry and the people involved. These days, candidates often try to have their interview prep done in advance. Those unfamiliar with the process turn to books and multiple-choice questions (MCQs) online to help them get ready. Nevertheless, they still need to figure out what questions are acceptable and how to pass the interview. In this modern age, our proposed study adds to the human self-evaluation gap between interview-related emotions and question responses. The self-interview bot analyses the candidate's previous interview footage and provides a synopsis of his interview preparation in this work. Emotion classification in the proposed study was done using Fear-2013, a publically available dataset. In preparation for the next interview, people can take a pre-test; the results summary may include issue monitors for applicants, depending on the test. We can analyze the video effectively using CNN for image processing and NLP for semantic analysis of the candidates' interview questions and answers. Using natural language processing for semantic similarity and convolutional neural networks (CNNs) for image processing, we were able to build a model that accurately answers queries and uses them. Finally, we can assess the candidate's readiness for the next interview by combining the two sets of results. Future research findings and the AI bot's current assessment of the applicant. The person-in-the-loop evaluation method involves a human assessor who converses with the bot and gives it comments about how it did. The evaluator can accomplish this by posing a series of questions to the bot or starting a dialogue with it, after which the bot will be evaluated based on its responses and overall performance.