Small decisions. Interesting possibilities.Submit contentSubmit

Jev Gateway

Jev reads the assistant instructions and recent conversation turns, then answers a typed tool Choice and a Noul question about whether a tool call is needed.

Added to Jevfast

How it uses Jev

Jev reads the assistant instructions and recent conversation turns, then answers a typed tool Choice and a Noul question about whether a tool call is needed. When direct-call mode is enabled, it can also answer typed questions for closed-set arguments. The router requires the tool-choice and Noul answers to agree and applies confidence gates before it steers the language model.

What Jev decides

Illustrative tool-need questionExample answers · not a recorded Jev response · Source ↗
Question 1 · needs tool
YOUR APP
INSTRUCTION

Does the assistant need a tool now rather than reply in plain text?

STATE

Assistant instructions and recent conversation turns, including tool-result text when present. Runtime tool names form separate Choice questions which are not charted here.

JEV · NOUL
YesNo

App workflow

  1. Build state and questions

    The gateway keeps recent turns within a state budget. It builds a Choice over the current tool roster and a Noul question about whether a tool is needed; optional closed-set tool arguments add further questions.

  2. Ask Jev

    The router sends state and questions to the configured Jev provider. Large tool rosters are ranked in shards before the final question.

  3. Steer or pass through

    The router checks answer types, confidence, and agreement. It steers only when the checks pass; errors, low confidence, disagreement, and unsupported tools pass through to the language model.

Why it is interesting

It places a fast typed decision step in front of coding-agent tool selection and fails open to the existing language model if the Jev request fails.