The article discusses a study analyzing 425 interactions with generative-AI bots like ChatGPT, Bing Chat, and Bard. The research identified six types of conversations: search queries, funneling conversations, exploring conversations, chiseling conversations, expanding conversations, and pinpointing conversations. The study found that different conversation types serve distinct information needs and demand varied UI designs. Also, there is no one optimal conversation length as both short and long conversations can be helpful, depending on different user goals. The article provides tips for both users and interface designers of generative AI chatbots for each type of conversation.
Key takeaways:
Different types of AI conversations serve distinct information needs and demand varied UI designs. These types include search queries, funneling conversations, exploring conversations, chiseling conversations, expanding conversations, and pinpointing conversations.
There is no one optimal conversation length. Both short and long conversations can be helpful, as they might support different user goals.
For specific information needs, detailed, pinpointing prompts are beneficial. For broad, less well-defined needs, users can use the bot’s responses to learn either through breadth or depth.
AI bots should attempt to determine the conversation type early in the exchange and adjust behavior accordingly. This can be done by using the length and the structure of the user’s prompt, as well as the complexity of the answer.
