The chat experience
What your users see in a conversation — streaming replies, suggestions, action cards, disclosures, and more.
Here’s what a conversation in the widget actually looks like for your end users.
Streaming replies
Answers stream in as they’re generated, so there’s no waiting for a full response. The panel shows the answer and nothing else — no reasoning trace, no source list, no note about what the assistant remembers.
Suggestion chips
Action-oriented suggestion chips appear above the composer; tapping one sends it as the next message.
Action cards
When the assistant wants to do something, it shows it clearly before anything happens:
- An action plan previews multi-step work; nothing runs until the user approves it.
- A confirm card gates a write or destructive action, with a summary of the side effects — and, where required, a typed-confirmation phrase.
- Progress and result cards show what ran and what came back.
Step-up & consent
For sensitive actions, a focus-trapped step-up dialog asks the user to re-confirm their identity (MFA, a passkey, or their password). If you’ve enabled it, a one-time 'act on your behalf' consent is shown the first time and remembered after.
AI disclosures
The widget makes clear the user is talking to AI: a persistent indicator, plus a dismissable banner on the first message. This supports transparency obligations such as the EU AI Act.
History
- Sources — every grounded answer records the passages it used. You see them in the conversation transcript; the widget shows your end users the answer alone.
- History — past conversations are kept (encrypted on the device) so users can return to them.