When interacting with computer-based assistants like those used in everyday applications such as ordering food or making transactions, it's often unnecessary to engage in small talk that may not be relevant or useful for the user's goal. While natural language processing (NLP) and machine learning capabilities have improved, they still struggle with unstructured conversations and can lead to frustration if not designed properly. Designing assistants around a specific objective in mind helps create a more efficient and effective conversation experience. Focusing on core flows and intents that meet the user's needs is key, rather than trying to replicate human-like characteristics or humor that may not be suitable for all contexts.