Jev review templates
Review templates are screens and reason codes. If the UI says “Jev thought…”, you are lying — Jev did not generate a thought.
Unofficial. docs.typesafe.ai.
Screen
Show: source text, question instructions, top-2 options with probabilities, confidence, suggested action, override control.
Reason codes
wrong_intent, missing_context, policy_exception, model_overconfident, other — feed feedback.
Do not generate a rationale for the reviewer
If you want a paragraph, call an LLM after and label it as generated assistance, never as “Jev’s reason.” Reviewers anchor on fluent lies.
What this page does not claim
- Not a full HITL product spec.
FAQ
Should reviewers see the prompt? Yes. Criteria are the explanation surface.
Re-ask Jev after notes? Optional second pass; don’t treat agreement as proof.
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: evidence templates, human in the loop, feedback guide. Canonical: https://docs.typesafe.ai.
Sources
Public TypeSafe or adjacent documentation only. No private claims.