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 an ad excerpt to identify trial access, a price discount or a bundle. Keep feature descriptions separate from an actual offer and its stated terms.
An offer mechanism describes what the copy explicitly proposes. A feature benefit such as saving time does not establish a reduced price, a trial or a bundle.
The labels do not verify that terms are honored or calculate savings. Exact prices, eligibility and deadlines must come from verified commercial data and ordinary validation.
The source describes tagging ad offers. These fictional excerpts isolate that task without adopting its claimed dataset size or performance measurements.
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 ad offer type.

Paste an ad excerpt to identify trial access, a price discount or a bundle.

Open the decision rules and keep the intended distinction between Trial access, Price discount, Bundle, No explicit offer, 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 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 |
|---|---|---|
| Trial period | Trial access | 100% |
| Price reduced | Price discount | 100% |
| Items packaged | Bundle | 99.0% |
| Feature only | No explicit offer | 93.0% |
| Saving time is not price | No explicit offer | 100% |
| No copy excerpt | 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. The excerpt may describe trial access without stating a price. The classifier must not invent a free offer or its conditions.
Yes. This simple taxonomy assumes one primary mechanism. For equally central mechanisms, extend the contract with mixed or multiple outcomes and test that revision.
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.