Use TypeSafe

TypeSafe makes units of AI intelligence usable like programming primitives: small judgments you can compose into larger capabilities. Its System One models return fast, focused judgments that software can consume directly. Jev is TypeSafe's flagship and first System One model. It understands natural language and returns typed answers and probabilities rather than generating text or reasoning explanations. Code owns the workflow; the model supplies programmable common sense where ordinary code needs semantic understanding.

Review documents with the CLI

For document review or triage, use the installed typesafe command when it fits the request. Check typesafe --help for the installed version. It reads UTF-8 text or Markdown paths, or - for stdin; typesafe [--rubric FILE] DOCUMENT... emits one JSON result per document. A JSON rubric can define multiple Score dimensions in one request. See the CLI README for its rubric format and limits.