cooljev.中文
← All scenarios

SCENARIO / REVIEWS

Find product issues in reviews

Check quality, delivery and usability separately; a review may have multiple labels.

Who this is for Product and commerce teams organizing feedback with original evidence.

Authored examples · No live inference

Define the decision first

  1. Allow multiple labels rather than forcing a single main issue.
  2. Separate packaging damage from product damage. Do not invent missing facts.
  3. No reported issue differs from insufficient information; review ambiguity manually.
{
  "review": "It keeps drinks warm, but the lid started leaking after two days. The delivery box was crushed; the cup itself was not broken."
}
How would you classify this using the criteria above?
Read all examples and authored answers

Typical example · Quality + delivery

{
  "review": "It keeps drinks warm, but the lid started leaking after two days. The delivery box was crushed; the cup itself was not broken."
}

The leak is a quality issue and the crushed box is a packaging issue. The cup was not reported broken.

Next action: Count both labels and retain the original for review.

Counterexample · No reported issue

{
  "review": "One month of use, no leaks, easy to clean, packaging intact."
}

The text denies the issue. Mentioning the word leak is not evidence of a leak.

Next action: Keep as no reported issue; exclude from issue counts.

Insufficient information · Insufficient information

{
  "review": "It is what it is. Not quite what I expected."
}

No specific defect, delivery or usability problem is described.

Next action: Ask a person to inspect context; do not force a category.

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
quality noul
delivery noul
usability noul
enough_information noul

REQUEST.JSON

View the Python call
Download the original request
  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 reviews --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 reviews --mode live --language en --request request.json

    Open the official Playground · Account and environment setup

Practice review and export

Edit labels manually, inspect the distribution and save a local project file.

Open the review exercise

Understand the method

Request fields checked against the official API reference on 2026-09-20. API reference