Workflow guide

When not to use Jev

Keep Jev on System One judgments. Do not send it work that needs generation, tools with arguments, or slow reasoning.

  1. Step 1

    No prose, no tool arguments

    Jev answers typed questions. It does not write emails, patches, or function-call arguments. Pydantic-AI's TypeSafe integration even raises ToolCallProposed when a tool needs arguments.

  2. Step 2

    Split fat questions

    Analyze this and decide the best course of action is a System 2 prompt. Split it into independent Noul/Choice/Score questions and combine them in code.

  3. Step 3

    Do not copy unofficial mode fields

    Some community pages show a mode field such as compaction or router. Official TypeSafe requests use model, state, and questions. This hub rejects mode on purpose.

  4. Step 4

    Local Jev-like models are not Jev

    jevlike and similar experiments share a type signature, not weights, calibration, or the hosted API. Label them as local experiments in any catalog you keep.

Related projects

  • jevlikeIndependent starter model with a Jev-like input/output shape: text plus options in, probabilities out. Not TypeSafe Jev.
  • system-one-adapter-pythonOfficial TypeSafe adapter that speaks the same system_one interface, backed by OpenAI or Anthropic instead of Jev.

All guides · Request builder