AI UI Sandbox

An ongoing batch of inline UI sketches.

When communicating the order of info would be harder with the standard question-and-answer UI.

Also my excuse to make a better-feeling drag-and-dropper. Most mobile drag-and-drops feel clunky.

Chats with agents get long, and the part you need to get back to is often buried. Instead of rereading it all, the app could help by post-processing the chat transcript.

Find the part in the chat you half-remember, plus context labels for near-matches.

UI details for when you cut it off mid-answer.

Helping the agent close the gap.

Generated text restyling as it arrives.

A reply that leans on an earlier turn carries the quote with it, so you can check the source without going to find it.

A memory showing its age.

An ambient sidebar readout of how full the current conversation's context window is — so the diminishing-returns zone is visible before you hit it. Could roll in token cost too, or stay purely about context budget.

How an agent looks while it works — planning, retrieving, deliberating, hesitating.

Quick ways to confirm what an agent did without redoing the work yourself.

Where a claim came from, attached to the phrase.

Hold-to-confirm gestures keyed to how reversible the action is.