FAQ

Does Rivan send replies without my approval? Only if you let it. By default, anything sensitive is routed to Slack for human approval. You control the auto-send policy.

Whose brand do replies use? Yours. Rivan drafts and sends replies through your Crisp inbox under your support identity, not a third-party bot.

How does Rivan "reproduce" an issue? For app-behaviour questions, Rivan can open a sandboxed, headless browser session (via Browserbase) to reproduce what the merchant is seeing before drafting a reply. Sessions are isolated and short-lived.

Is my data used to train models? No. Tickets are sent to Anthropic for inference only. See the Privacy Policy and our subprocessor list in the DPA Template.

How is my data isolated from other customers? Every tenant's data is row-level-security scoped in Postgres, and per-tenant credentials are encrypted with AES-256-GCM using isolated keys.

What happens if I hit my plan's ticket limit? Trial blocks new tickets at the cap (with a warning beforehand). Paid plans meter overage per ticket. See pricing for details.

Can I export or delete my data? Yes. Contact [email protected] for data export or deletion requests.

Where can I see uptime / incidents? The public status page: https://status.rivan.ai.