The "Open Input" pattern has become the cornerstone of interactive AI design, fostering a dialogue between users and AI systems. This pattern is characterized by its simple interface that feels familiar, inviting the user to converse with the model underneath.
By using natural language, it doesn't take long for someone to get comfortable with the general interactivity. Where the pattern's limitations show is after the first few interactions, when someone doesn't know what to say next.
There's a false perception that simple means easy. When someone knows what they are looking for then this way of interacting with the model makes sense. This could apply to use cases like a search portal, or customer support.
However, when someone reaches an open chat bar and doesn't know what they are looking for (content generation sites, ChatGPT, etc), it can lead them to feel crippled by the choices - the blank canvas effect.
On top of that, prompting skills are not widespread. Most users will not understand how to craft a prompt to get the result they have in their head.
Wayfinding patterns like ice breakers can help users get the conversation started. However, this pattern so far lacks affordances to help people construct better prompts that get them the outcomes they are looking for–the patterns are limited to hints and clues to get started. As result, users report feeling frustrated by the lack of consistency, predictability, or perceived quality in what is returned.
An open ended input pattern allows users to fully express themselves. They can use the words and framing that is more natural to them to construct a query. Open chat won't be going away, but we will likely see it evolve.
- Templates can help users craft better prompts without having the full skillset
- Nudges to improve your prompt can show users what "better" looks like
- Putting filters and parameters at the users' fingertips can make this more complicate feature accessible
Think past the initial interaction. What's step two?
