This experimental research examined the effectiveness of using chatbots in English as a Foreign Language (EFL) classrooms at a Chinese elementary school. Seventy-four students were divided into two groups: one employing traditional methods, and the other using chatbots. Before and after the 3-month teaching period, pre- and post-tests were used to measure students' oral English proficiency, and a questionnaire was employed to assess their willingness to communicate (WTC). Data from interviews with teachers and students provided insights into chatbot usage and modification. Data analysis involved using SPSS to identify significant differences in pre- and post-test scores and NVivo 11 to code qualitative feedback from student and teacher interviews. The results show that chatbot integration significantly improved oral English proficiency and WTC in the experimental group compared with the control group. Teachers can enhance instruction by adopting tailored chatbot features to refine teaching methods, thus creating a more adaptive learning path for students. Further, chatbot improvements such as personalised error correction and user-centric features pave the way for immersive and fruitful language learning. This study provides valuable insights for integrating chatbots into language classrooms and suggests opportunities for further chatbot enhancements.