BACKGROUND: The potential of natural language processing tools such as chatbots in learning a second or foreign language has not yet been fully realised (Dale, 2016; Fryer et al., 2019). Language learning occurs through interaction with classmates and teachers, which provides comprehensible input, feedback on output and the opportunity to modify output (Mackey, 2012). Chatbots can serve as an always-on source of interaction. In this study, a chatbot was designed and deployed using Dialog flow Messenger. It acts as a conversational interface for English learners and is available on our website or as a mobile application (app). Language learning is most effective when it is immediate and contextual, so this chatbot not only ‘chats’ but also guides learners to appropriate language study resources. It puts students in control of their learning by answering specific questions (e.g., How do I refer to sources in written texts and oral presentations?, Where can I find IELTS materials?, What is the present perfect?); providing customised learning options; and allowing students to learn at their own level, pace, and at a time of their choosing. This study investigates English language students’ attitudes, beliefs, and perceptions towards using a customised chatbot to enhance language learning.METHODS: Participants consisted of students and teachers (n=4) from a compulsory English for Academic Purposes course at the largest public university in Hong Kong. In this study, the students (n=76) had access to the chatbot for two months. Data on attitudes, beliefs and perceptions regarding the chatbot were collected using a questionnaire and focus groups; transcripts were collected to identify questions put to the chatbot. This mix of methods was chosen to provide rich, detailed, and complex accounts of users’ experiences.RESULTS: Findings from the questionnaire and focus groups are consistent with previous research that reported positive learning experiences with chatbots (Fryer & Carpenter