cooljev.中文
← All scenarios

SCENARIO / ARTICLES

Editorial article screening checklist

Screen articles against an editorial rubric with examples and editable JSON. Check actionable steps, observed results and completeness, not AI authorship.

Use the supplied editorial criteria to decide whether an article deserves further review. This example does not detect AI-written text, verify every factual claim or automatically publish a draft.

Edit the decision templateDownload request JSON

Positive, negative and missing-evidence examples follow. Authored answers do not change when you edit a request. Read the practical guide

Who this is for Researchers and content teams building a practical reference library.

Authored examples · No live inference

Define the decision first

  1. Check whether steps and results are present; do not certify the claim.
  2. General advice is not an actionable step. A number is not proof of a sound experiment.
  3. An excerpt cannot establish that something is absent from the full article.

Decide first, then compare

01 / EXERCISE
{
  "article": "Reduced the signup form from seven fields to three: removed job title and company size, and combined name fields. Completion rose from 28% to 39% in two weeks, with a comparison table.",
  "complete_material": true
}
How would you classify this using the criteria above?
Read all examples and authored answers

Typical example · Add to verification list

{
  "article": "Reduced the signup form from seven fields to three: removed job title and company size, and combined name fields. Completion rose from 28% to 39% in two weeks, with a comparison table.",
  "complete_material": true
}

Actions and results are present; sample size, controls and sources still need verification.

Next action: Save with a source-verification task, not a proven improvement claim.

Counterexample · Missing practical material

{
  "article": "The key to conversion is understanding users, improving experience and thinking long term.",
  "complete_material": true
}

No concrete changes or checkable results are described.

Next action: Do not add to the practical reference library yet.

Insufficient information · Insufficient information

{
  "article": "Here is how we improved conversion… (remaining article unavailable)",
  "complete_material": false
}

Only an introduction is available; the full article cannot be assessed.

Next action: Obtain the full material before screening.

Adapt the template to your task

02 / CONFIGURE

Edit the material and question criteria to create a request. Stable field names stay in English for code. Editing does not run a model or change the authored answers above.

Questions and criteria

Stable field IDs; editable criteria and options
has_steps noul
has_results noul
complete_material noul

REQUEST.JSON

View the Python call
Download the original request 
Run in your own environment
03 / BUILD
  1. Download and extract the examples
    Python 3.10+; no third-party dependencies. Run from the directory containing examples/.
    Download all example code
  2. Start with authored offline examples
    python -m examples.hello_jev articles --mode offline --language en
    This checks the local workflow, not model quality. Changed inputs cannot replay old fixture answers.
  3. Use a real account when you are ready
    Set TYPESAFE_API_KEY locally and put request.json in the project root. Live calls send material to TypeSafe and may incur charges. Live interoperability has not been tested in this edition.
    python -m examples.hello_jev articles --mode live --language en --request request.json
    Open the official Playground · Account and environment setup
Understand the method
Related build: pre-publication checks Question design 
Request fields checked against the official API reference on 2026-09-20. API reference