Small decisions. Interesting possibilities.Submit contentSubmit

How it uses Jev

Before generating a turn response, the agent sends a bounded task and conversation state to Jev with a typed `action` Choice. The answer routes the turn to respond, clarify, or end; a missing or unrecognized answer halts the route. A separate shell-round judgment can pass, retry, or stop the command loop.

What Jev decides

Check whether an acceptance test is faithful to the taskExample answers · not a recorded Jev response · Source ↗
Question 1 · faithful
YOUR APP
INSTRUCTION

The acceptance test in `test` was written before the task in `task` was solved, to check the requirements in `requirements`. Does every assertion in the test follow from what the task states, from its examples, or from its rules, with nothing the task doesn’t ask for, and does every input the test builds follow the input format the task describes?

STATE

A single acceptance test with the task instruction, the requirements it is meant to check, and the test ID, kind, purpose, and clipped source.

JEV · NOUL
YesNo

App workflow

  1. Build turn state

    The agent combines the current task, bounded conversation transcript, and repository member names into the classification state.

  2. Ask for an action

    It sends that state with the `action` Choice question to the configured Jev client.

  3. Route the turn

    The returned choice maps to respond, clarify, or end; unanswered or unlisted actions halt, while a failed or absent classifier leaves generation unrouted.

  4. Generate and continue

    For a response or clarification route, the generation door produces the next turn; shell outcomes can receive a separate pass, retry, or stop judgment.

Why it is interesting

Jev sits as a first-stage router in the agent loop, and its typed answer is mapped to explicit application routes. The current question set keeps the turn decision focused on one action rather than treating several unused judgments as routing signals.