This thesis asks, how can an AI-enabled Dialogue Assistant in the form of a chatbot suggest new and unexpected forms of response to English Language Learners? The thesis draws upon theories of improvisation and play, alongside computer science to facilitate text-based conversation in English for non-native speakers. ImprovChat is a digital solution for communication issues that I encounter every day. My experience with improvisational theatre also informs the ImprovChat project. For my thesis research-creation, I developed the web application by implementing API powered by machine learning to generate AI phrases. The phrase generation model is pre-trained using the Twitter feeds created by people who speak English as a first language. ImprovChat dialogue assistant will provide phrase suggestions; these could potentially be used in online chatting scenarios where the participants have two different native languages. It can also be used to inspire unexpected and playful forms of response.