Open· Last updated

Jev reference architecture

A reference architecture here is an unofficial box diagram in words: clients → your API → questions module → one TypeSafe door → traces → action / HITL. It is not TypeSafe’s unpublished internals.

Independent. docs.typesafe.ai. No keys.

Independent angle (cover, do not clone)

Win delta (architecture-known-unknowns): reference boxes you can implement; no fake internal diagrams.

Boxes

  1. Clients — product apps; they see enums, not raw Nouls.
  2. Decision service — auth, timeouts, idempotency, door adapter.
  3. Questions module — git-versioned instructions/criteria/floors.
  4. Door — first-party HTTP/SDK or a documented gateway (matrix).
  5. Trace store — model, usage, probabilities, action, question SHA.
  6. HITL — review UI.
  7. Eval job — gold JSONL, pinned model.

Non-boxes (do not add)

Failure domains

None of these require knowing unpublished model architecture.

What this page does not claim

FAQ

Where does LangChain sit? Optional harness in the client or service. See LangChain harness.

Multi-region? Your service + vendor residency. Ask TypeSafe; we will not invent regions.

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: architecture patterns, implementation checklist, for platform teams. Canonical: https://docs.typesafe.ai.

Sources

Public TypeSafe or adjacent documentation only. No private claims.