SDKs & clients

jev-system-one

@haseeb-heaven2PythonMITupdated 2026-09-17runnable

A polished OpenAI + TypeSafe Jev terminal interface for answers with transparent decision reports

haseeb-heaven/jev-system-one

Where it calls Jev

from typesafe_sdk import Choice, Noul, RetryPolicy, Score, TypeSafeClient

src/jev_system_one/jev.py:3

The link points at the commit we read, so the line number still holds.

What it asks Jev

These question sets are lifted from this project's source exactly as written.

from src/jev_system_one/jev.py:32

  1. requires_uncertainty_noticetrue/false

    Should the answer explicitly disclose uncertainty or limits?

  2. response_depthscore

    How much detail should the answer contain?

    • 0brief: one direct answer with minimal context
    • 1standard: a concise answer with useful explanation
    • 2detailed: a thorough answer with structured reasoning or steps

Run it on your own text

The code
import { experimental_evaluate as evaluate } from 'ai';

const { answers } = await evaluate({
  model: 'typesafe-ai/jev',
  state,
  questions: {
    requires_uncertainty_notice: { type: 'boolean', instructions: 'Should the answer explicitly disclose uncertainty or limits?' },
    response_depth: { type: 'score', instructions: 'How much detail should the answer contain?',
      criteria: ['brief: one direct answer with minimal context', 'standard: a concise answer with useful explanation', 'detailed: a thorough answer with structured reasoning or steps'] },
  },
});

from src/jev_system_one/jev.py:107

  1. requires_revisiontrue/false

    Should OpenAI revise `openai_draft.answer` before it is shown?

Run it on your own text

The code
import { experimental_evaluate as evaluate } from 'ai';

const { answers } = await evaluate({
  model: 'typesafe-ai/jev',
  state,
  questions: {
    requires_revision: { type: 'boolean', instructions: 'Should OpenAI revise `openai_draft.answer` before it is shown?' },
  },
});

Other projects in this category