Job preference matching: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Give your work-condition preferences and the posting. Separate an explicit match or conflict from a condition the posting leaves unstated; the comparison does not rank applicants.
A preference mismatch is not an ability judgment. A person may be capable of a role and still choose not to work its schedule or location. This page only uses preferences they explicitly provide.
An omitted condition also differs from a conflict. If a posting says nothing about remote work, the next step is to clarify it rather than infer that remote work is forbidden.
The linked LinkScout workflow separates interests and working conditions from skill fit. This independent exercise keeps only the seeker-controlled preference comparison; it does not screen people for an employer.
This is an independently authored text demonstration inspired by the linked X discussion. Its rules and synthetic inputs are ours. It does not reproduce the author’s application, verify reported outcomes, or perform an external action.

Use the sample to understand the rule, then test your own input for job preference matching.

Give your work-condition preferences and the posting.

Open the decision rules and keep the intended distinction between Match, Conflict, Unstated, Review. 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 Review before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Remote daytime work | Match | 100% |
| Explicit onsite night shift | Conflict | 100% |
| Remote status omitted | Unstated | 84.0% |
| Conflict plus another unknown | Conflict | 99.0% |
| No preferences stated | Unstated | 53.0% |
| Contradictory posting | Review | 84.0% |
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. 5 of 6 results matched the authored fixture expectations. For No preferences stated, the expectation was Review; the observed choice was Unstated.Verified
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
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.
# Offline: inspect the downloaded saved observations. No API key is needed.
python preview_choice_workflow.py samples.json saved-api-results.json
# Optional live request: install the SDK and set TYPESAFE_API_KEY privately.
npm install @typesafe-ai/sdk@0.6.0
node run-choice-sample.mjs samples.json case-1
# The live response prints to the terminal; it does not update saved-api-results.json.The input contract and these limits define what the result means.
No. It describes a mismatch with your stated working preferences. The example does not evaluate skills or qualifications.
Unstated records that gap when no explicit conflict exists. Ask for clarification rather than treating missing information as a refusal.
It describes the distribution over the supplied choices for this request. These six synthetic examples are functional tests with authored expectations, not a production accuracy benchmark.
No. The demo displays a label and distribution. The downloadable consumer produces a pending preview packet. Application code and a separate authorization policy would control any real action.
Edit the example above to see how a changed fact affects the decision, or open the Playground for another task.