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.
Compare a proposed angle with the update's factual notes. Distinguish a supported focus from exaggeration or an unrelated subject without treating the supplied notes as independently verified news.
The aligned-limitation example explains what changed and what remains unsupported. It provides a concrete editorial focus without converting a small test into a universal performance claim.
Exaggerated angle describes an unsupported extension of a real supplied fact. Unrelated angle changes the subject entirely. Neither outcome is a judgment about whether the wording sounds persuasive.
The source discusses choosing topics and angles for social posts. This window reviews an already proposed angle; it does not discover live news, write an X post or verify the supplied facts externally.
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 news angle review.

Compare a proposed angle with the update's factual notes.

Open the decision rules and keep the intended distinction between Aligned angle, Exaggerated angle, Unrelated angle, Unclear angle, 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 angle, 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 |
|---|---|---|
| Specific parser update | Aligned angle | 100% |
| Universal claim | Exaggerated angle | 100% |
| Different subject | Unrelated angle | 100% |
| Vague angle | Unclear angle | 66.0% |
| Supported limitation | Aligned angle | 100% |
| Facts missing | 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 checks the angle against the supplied notes. External source verification is still required before publication.
Yes. A precise feature change or limitation can give readers a clearer task than an unsupported general claim. This model label does not measure audience demand.
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.