Technical Transparency
How Your Data Is Handled
A plain-language breakdown of what happens to your transcripts, and when.
Section 1 — What you upload
Meeting transcripts are saved to your project in Supabase, a secure hosted database. The transcript is stored as entered by you so your meeting history remains complete in your account.
Section 2 — What the AI sees
| Privacy Mode | What AI Receives |
|---|---|
| Fully Open | Original transcript |
| Semi-Private | Transcript with emails, phones, URLs, addresses, and names filtered out |
| Fully Private | Heavily redacted transcript — most identifying terms are replaced before processing |
The server applies this filter before the AI request is made. The AI processes only what your selected mode allows through.
Section 3 — Who processes it
AI analysis is performed by Anthropic's Claude API. Anthropic does not use API data to train its models. See Anthropic's privacy policy: anthropic.com/privacy.
Section 4 — What we log
The privacy mode applied to each parse is recorded as privacyModeApplied for auditability. Transcript content is not included in logs.
Section 5 — Your control
You set privacy mode per project. The server resolves and enforces this setting on every parse request. If no privacy mode is configured, the system defaults to Fully Private as a conservative fallback.