NEXT AI chat only uses (a) the prompt you type and (b) the specific customer-evidence supporting your prompt.
Inputs to the chat
Your prompt.
The highlights you choose as context (e.g. all highlights in your teamspace, a search/filter subset, highlights from selected recordings, or just one highlight). You fully control that scope.
Where those highlights come from
Call recordings you import from tools like Zoom/Google Meet/Gong — recordings are processed, key customer moments are identified/clipped, interpreted, and classified, with traceability back to the source.
Support tickets & conversations (e.g., Zendesk, Intercom, Front, Zoho Desk).
Surveys/VoC (e.g., Qualtrics, Typeform, Mopinion, GetFeedback) — each response becomes a highlight with scores/metadata plus a source link.
App reviews (Apple App Store, Google Play) — imported as highlights with rating, version, and a source link.
Communities/other sources (e.g., Khoros) and CRM context (Salesforce accounts/opportunities) to anchor work and automations.
How answers are grounded
NEXT AI generates answers only over the selected highlights, and the UI links back to the exact source artifact (recording/ticket/review), including reels/clips for video so you can verify.
Chats are private to the creator by default (you can explicitly share them with teammates).