User intent identification and classification has turned into a fundamental subject of question figuring out in human computer dialogue applications. The identification of user’s intent is particularly pivotal for helping frameworks to figure out user’s questions to group the queries precisely to improve users’ satisfaction. Likewise, the utilization of chatbots advanced quickly in various fields as of late, including Marketing, Supporting Systems, Education, Health Care, Cultural Heritage, and Entertainment. In this paper, a literature study on intent classification is done. Moreover, a conceptual architecture of the chatbot technology is proposed which defines a general architecture explaining the components of the chatbot technology. Finally, the paper explains the studies related to chatbot technology, approaches of intent classification, transformer models used for chatbot technology and response generation. In implementation, a chatbot for FAQs of the Python programming language using Python and Flask to test responses with a Deep Learning Sequential model using intents is done. The literature review reveals that transformer models do the best when it comes to intent classification. Machine learning techniques are crucial for intent classification. In conclusion, we explain the paper by expressing our opinions in regard to the path of technology so that decision-making in chatbots can be enhanced.