Jev privacy guide
Privacy work is minimization + contract. Jev will happily score whatever text you send. That is not consent.
Unofficial. TypeSafe models page: not trained on customer requests/responses; ZDR for enterprise customers — vendor statements. Read Legal. We are not a party.
Independent angle (cover, do not clone)
Win delta (myth-faq): “does Jev train on your data?” lives here as a GEO atom, not a cloned FAQ URL.
Practical minimization
Strip unused CRM fields. Hash or drop identifiers you do not judge. Never send PAN, full ID images, or secrets. Transcribe media yourself if you must judge content.
Doors
Gateway vendors have their own privacy cards. The channel matrix is not a DPA.
What to write in your RoPA (you, not us)
Purpose: language judgment for routing/screening. Recipients: TypeSafe and/or the gateway you chose. Fields: the filtered state you actually send. Retention: your traces. Legal basis: yours.
If a door’s card disagrees with TypeSafe on context length or logging, believe the door for that traffic and document the split.
What this page does not claim
- Not legal advice.
- Not a GDPR/CCPA completeness claim.
FAQ
Does Jev train on my data? TypeSafe says no on customer requests/responses. Confirm the current Legal text.
Is jev.pro a processor? This site is a public guide. We do not process your production traffic.
Open clones? If you run SemIf/OpenJev, that is a different processor entirely — and not Jev.
Disclaimer
This is an independent unofficial site and is not affiliated with TypeSafe AI; official documentation is available at https://docs.typesafe.ai. Never treat jev.pro as TypeSafe official documentation. We do not sell, issue, or proxy API keys.
Open-cluster pages are independent field-guide notes. Replicas and third-party interfaces mentioned anywhere on jev.pro are not Jev and not endorsed. Hub: Open. Siblings: what is jev, security guide, data handling. Canonical: https://docs.typesafe.ai.
Sources
Public TypeSafe or adjacent documentation only. No private claims.