cooljev.中文
← All scenarios

SCENARIO / LEADS

Find people looking for a solution

Separate requests for help from promotion and experience sharing.

Who this is for Developers and sales teams screening community posts for explicit needs.

Authored examples · No live inference

Define the decision first

  1. Judge what the post explicitly says, not budget or willingness to buy.
  2. A lead needs an explicit problem or request; self-promotion is separate.
  3. Use unknown when context is missing. A person decides whether to contact anyone.
{
  "post": "Our team has eight support agents. Manual ticket assignment is slow. Can anyone recommend a tool that routes tickets by issue type?"
}
How would you classify this using the criteria above?
Read all examples and authored answers

Typical example · Seeking a solution

{
  "post": "Our team has eight support agents. Manual ticket assignment is slow. Can anyone recommend a tool that routes tickets by issue type?"
}

A concrete problem and an explicit request are present. This does not prove purchase intent.

Next action: Add to a review queue; a person checks fit.

Counterexample · Promotion

{
  "post": "We just launched our ticket-routing tool. Try it now, with 20% off the first month."
}

The author promotes their own tool rather than asking for one.

Next action: Exclude from help-seeking leads. Send no automatic message.

Insufficient information · Insufficient information

{
  "post": "Something finally changed with ticket assignment."
}

Neither the change nor a request for help is clear.

Next action: Keep the original and wait for context.

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
intent choice

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 leads --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 leads --mode live --language en --request request.json

    Open the official Playground · Account and environment setup

Understand the method

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