Interactive answers in chats
The cards, charts and question sets an agent can put in a reply, which ones you can act on, and where they end up.
An agent can put more than text in a reply. Alongside its words it can render cards, charts and sets of questions, and some of them you can answer by tapping.
What an agent can show you
| What appears | What it is | Can you act on it |
|---|---|---|
| Stat cards | Labelled numbers, each with an optional up, down or flat trend | No |
| Bar chart | A bar chart with a legend | No |
| Line chart | A line chart with a legend | No |
| Table | A table with defined columns | No |
| Expandable list | Items you tap to open, with one open to start | No |
| Buttons | Buttons that send a follow-up message for you | Yes |
| Single choice | Options where picking one sends its message | Yes |
| Multi select | Several options and a submit button | Yes |
| Question sequence | A short run of questions, each free text or a choice | Yes |
Read-only cards are wrapped in a titled card. The ones you can act on are rendered bare, so they read as part of the conversation rather than as an attachment.
Only the latest reply is live
Buttons and question sets are only active on the most recent agent reply. Older ones become inert, so scrolling back through a long chat cannot re-fire a question you already answered three turns ago.
They stay with the message
Cards arrive one at a time as the reply is written, and they are saved with the message. Closing a chat and coming back to it renders them again, charts and all, without asking the agent to redo the work.
The Artifacts tab
The read-only cards from the whole thread are also gathered in the Artifacts tab, next to the reports, each labelled by its own title. Buttons, choices, multi selects and question sequences are treated as part of the conversation and are left out of it, since a prompt you already answered is not an artefact.
Charts are drawn the same way everywhere, so a chart in a chat, in Ask Auron and in a report all read alike.