API · Last updated

Jev API policy endpoint

Policy around Jev is a layer you write: encode language-y rules in instructions/criteria, and encode hard constraints plus floors in code. Jev is not a drop-in PAP/PDP.

This page is for builders who searched an extra “endpoint” name. jev.pro is an independent unofficial field guide — not affiliated with TypeSafe AI. We do not sell or issue keys. Confirm first-party routes on docs.typesafe.ai/api.

The public API reference documents one evaluation route — POST https://api.typesafe.ai/v1/systemone — plus GET /v1/models. This title is not a separate first-party URL in that reference. Treat the capability as something you implement around the official call.

Steps

  1. Keep denylists, velocity caps, and entitlement checks deterministic.
  2. Ask Jev only the gray-zone questions (tone, implied intent, citation support).
  3. Compute block | review | allow after answers. Log which clause fired.
  4. Do not call /v1/policy.

Request / response shape

Still one evaluation POST. Policy config (floors, denylists) never needs a new TypeSafe route. Answers stay Choice/Score/Noul.

Pitfalls

See also

FAQ

Is this a documented TypeSafe URL?

No. Application pattern only.

Where do I store policy version?

In your service next to the questions module. Pin the model too.

Moderate vs policy?

Moderation screens untrusted text. Policy is any domain rule — they can share a request.

What this page does not claim

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.

Sources