"Meanwhile AI chat suffers from the same problem from command lines to Alexa - how can i remember what to ask? Only this time the problem is exacerbated by the fact that AI is capable of practically anything making the task less one of remembering commands but a creative one of coming up with great questions or delivering an interface to discover them and then wrapping the resulting prompts as buttons."
"AI buttons are different from, say Photoshop menu commands in that they can just be a description of the desired outcome rather than a sequence of steps (incidentally why I think a lot of agents' complexity disappears). For example Photoshop used to require a complex sequence of tasks (drawing around elements with a lasso etc.) to remove clouds from an image. With AI you can just say 'remove clouds' and then create a remove clouds button. An AI interface is a 'semantic interface'."
Modern prompts can be simple, with AI handling execution, but users struggle to remember what to ask, turning prompt creation into a creative discovery task. Wrapping frequently used prompts as buttons provides affordances for storage, reuse, and sharing. AI buttons differ from traditional menu commands because they describe desired outcomes instead of procedural steps, collapsing agent complexity and removing interface bureaucracy. For tasks like removing clouds from images, a single intent such as 'remove clouds' can replace long sequences of manual edits. Framing interfaces around intent enables semantic controls that map user goals directly to AI capabilities.
Read at Interconnected, a blog by Matt Webb
Unable to calculate read time
Collection
[
|
...
]