Source and example scope
Compare each saved result with its authored expectation. A disagreement remains in the fixture review; the call is not repeated to obtain a preferred label.
Paste the posting's platform requirements. Distinguish AWS, Azure and Google Cloud from multiple required clouds or a posting that specifies none.
The label describes what a fictional posting explicitly requires. It does not rate an applicant, infer experience or make a hiring decision. A posting that names no cloud belongs under No cloud specified.
Multiple clouds preserves an explicit AWS-and-Azure requirement. The classifier should not select one because it appears first. An incidental platform mention would need wording that distinguishes it from the actual requirement.
The latest API-collected source names cloud classification in job postings. These authored excerpts expose that text task without reproducing its dataset or claiming coverage of a real labor market.
This is an original synthetic demonstration adapted from the cited workflow discussion. It does not reproduce the source application or verify its performance, adoption or security claims.

Use the sample to understand the rule, then test your own input for job-posting cloud requirements.

Paste the posting's platform requirements.

Open the decision rules and keep the intended distinction between AWS, Azure, Google Cloud, Multiple clouds, No cloud specified. Edit the choices only when testing your own rule.

Use a sample first, then try your own input. Compare the selected label with the other returned probabilities.

Review Need evidence before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| AWS requirement | AWS | 100% |
| Azure requirement | Azure | 100% |
| Google Cloud requirement | Google Cloud | 100% |
| Multi-cloud requirement | Multiple clouds | 100% |
| No named requirement | No cloud specified | 100% |
| Posting absent | Need evidence | 100% |
These are six original synthetic inputs, tested once per request revision. The percentage is the leading option probability, not measured accuracy. Authored expectations and any disagreements remain in the downloadable evidence. 6 of 6 results matched the authored fixture expectations.Verified
Compare each saved result with its authored expectation. A disagreement remains in the fixture review; the call is not repeated to obtain a preferred label.
The single-request SDK runner uses your private TYPESAFE_API_KEY. The offline consumer reads saved observations, checks request hashes and prints a pending output. It does not call the model or change any external system.
npm install @typesafe-ai/sdk@0.6.0
# Set TYPESAFE_API_KEY privately in your shell.
node run-choice-sample.mjs samples.json case-1
python preview_choice_workflow.py samples.json saved-api-results.jsonThe rubric explains the decision; the application owns the next step.
No. It means the supplied posting explicitly requires AWS under this rubric. Actual infrastructure would need separate evidence.
No. No applicant is supplied or evaluated. The task classifies the text’s technical-platform requirement.
No. It is the model distribution for this one request. The six examples are functional checks with authored expectations, not a representative benchmark. Inspect disagreements and evaluate your own examples before using the label.
The window shows an error and supplies no fresh judgment. The downloadable runner sends one request without retries. Need evidence is a valid outcome about incomplete input; it does not stand in for a network or provider failure.
Edit the evidence above or use the Playground to test another bounded question.