PIPEDA-aligned handling
We collect the minimum needed to answer, book, and dispatch. Call recordings and transcripts belong to you. We don't sell them, and we don't use them to train foundation models.
Security & compliance
Right On Call is a boutique receptionist, not a consumer app that trains on whatever you type. Recordings exist so we can dispatch, book, and debug, not so we can sell a dataset.
We collect the minimum needed to answer, book, and dispatch. Call recordings and transcripts belong to you. We don't sell them, and we don't use them to train foundation models.
Ontario is one-party consent for most business calls. We still put a short recording disclosure on the line, and if a caller asks whether it is a person, the agent says it is an AI assistant.
Availability and booking rules are enforced in code: the receptionist can only offer a time the calendar returned. Diagnosis and repair pricing are hard rules in its instructions. Gas, smoke, or spark reports take a bounded safety script and a human callback.
A dashboard kill switch stops the included Twilio number from answering. Tokens for third-party tools are encrypted at rest. Database access is row-level restricted per client. Sign-in is by Google account on an allowlist, and repeated failed sign-ins are rate-limited.
Voice AI cannot live entirely inside one Canadian closet. Telephony, speech, and models run with named vendors. We keep that list short, and we do not claim a data-residency story we cannot keep.
| Vendor | Role | Region |
|---|---|---|
| Twilio | Telephony and SMS | US / CA numbers |
| Vapi | Live voice pipeline | US |
| Anthropic | Conversation and summaries | US |
| Supabase | Call log and dashboard data | configurable |
| Render | Application hosting | US / EU |
Vapi runs speech-to-text and the voice through its own vendors. Tools you connect yourself, like Cal.com, Calendly, Jobber, or Zoho, get the booking details under your own account with them. The full vendor list is available on request.
For the longer, plain-language version of this page, read PIPEDA, Recordings, and US Subprocessors.