AI may evolve toward apps designed for agents rather than agents operating today’s interfaces. Human-computer interaction has relied on commands and manipulation of visual representations, such as typing, clicking, dragging, resizing, arranging, and formatting. Productivity tools have therefore treated the interface and the product as the same thing, with outputs like spreadsheets, slide decks, and ticketing systems produced through human interaction. As more work moves to agents, interfaces that require a mouse, menu, or canvas become less necessary. Agents instead need structured state that they can read, reason about, rewrite, and validate. In this model, the deck, document, or dashboard becomes an export, not the source of truth.
"The future of AI may not be agents using today's apps. It may be apps rebuilt around structured representations agents can inspect, modify, and validate directly. The deck, doc, or dashboard becomes the output, not the source of truth."
"Good product. And the interesting part is not the quality, it is the decision behind it: the interface is organized around the reasoning, not the slide. You work on the content. The deck is a consequence. The .pptx comes at the end. It is an export. The work happened somewhere else."
"For decades, the only way to modify an application's state was through a human interface. That assumption is starting to break. Most human-computer interaction has been built around two patterns: issuing commands (typing, clicking, speaking) and manipulating representations (dragging, resizing, arranging, formatting). Every productivity tool ever built is designed around one or both of those."
"But more of that work is going to be done with, and eventually by, agents. And agents do not need a mouse. They do not need a menu. They do not need a canvas. They need structured state they can read, reason about, and rewrite. Code has always worked this way. It is text with clear se"
Read at Mozilla.ai
Unable to calculate read time
Collection
[
|
...
]