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.
Provide a taste preference and fictional dish notes. Compare a match, a conflict and a mixed fit based on stated flavors, without treating the result as nutrition or allergy advice.
The window evaluates taste language, not dietary suitability. A savory dish with a sweet glaze can partly fit a request while violating another stated preference, so Mixed fit preserves both facts.
The citrus example uses different words for a compatible flavor. The house-special example supplies a description that says nothing useful about taste; it cannot establish a match.
These dishes are fictional. The source describes menu matching, but this adaptation does not reproduce a restaurant menu, confirm ingredients, make health recommendations or place an order.
These fictional inputs and decision rules were written for this page. The linked X discussion provides background; the technical implementation follows TypeSafe's Choice contract.

Use the sample to understand the rule, then test your own input for menu taste matching.

Provide a taste preference and fictional dish notes.

Open the decision rules and keep the intended distinction between Taste match, Taste conflict, Mixed fit, Unclear flavor, Need evidence. 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 Unclear flavor, 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 |
|---|---|---|
| Mild requested | Taste match | 100% |
| Hot dish conflict | Taste conflict | 100% |
| Mixed flavor | Mixed fit | 100% |
| Flavor not described | Unclear flavor | 52.0% |
| Different words, same fit | Taste match | 100% |
| No preference | 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. Flavor descriptions do not establish allergen content or preparation conditions. This demonstration does not evaluate those properties.
No. It judges one dish against one stated preference. Comparing several candidates requires their descriptions and a separate ranking objective.
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.