How to save an artifact to your library and reuse it
JJamesJuly 26, 2026
Every artifact the assistant builds — a doc, a sheet, a deck, a diagram — is disposable by default: useful in this chat, gone once you move on. Save it, and it becomes a living document you can find, edit, and reuse anywhere.
one-chat.app — it builds things
Turn that into a budget I can play with.
Done — live budget on the right. Drag any number.
Japan · Aprillive
Flights$1,840
Hotels$1,310
Food + fun$900
Total $4,050 · under budget
Documents and spreadsheets build live beside the chat.
1. Save it from the inspector
Whenever the assistant builds something, open the artifact inspector to view it full-size. There's a save action right there — use it to send the artifact to your library instead of leaving it stranded in the conversation it was born in.
2. Find it in your library
Everything you save lands on the library page at /app/library. From there you can organize artifacts into folders and subfolders — group a client's documents together, keep spreadsheets separate from decks, whatever structure matches how you actually work. The library is the one place to browse everything you've ever saved, regardless of which chat created it.
3. Pull it into any chat
You don't need to go back to the library to use a saved artifact. In any chat, type # followed by its name — the same pattern as @ for agents — and attach it directly into your message. Reference last month's budget sheet while planning next month's, or pull a saved doc into a totally unrelated conversation without copy-pasting a word of it.
4. Edit it — safely
Open a saved artifact and edit it like any other. The important part: every edit creates a new version. Nothing is overwritten silently. That means a saved artifact behaves like a living document — you can keep improving it over weeks or months — while still being able to see how it looked before your latest change.
5. Build once, use everywhere
The pattern that makes this worth doing: build a sheet, doc, or deck once, save it, then attach it into every relevant chat from then on instead of asking the assistant to regenerate it. A living artifact stays in sync with your work in a way a one-off answer never does.
That's the whole loop — save, organize, attach, edit — and it turns artifacts from chat output into something closer to your actual file system.
Try it yourself
Every model, one memory, and agents that work the way you do.