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.
Describe an ad's content to compare a product demonstration, customer testimonial and problem-solution format. The result labels its structure, not its performance.
A demonstration shows use, a testimonial centers on a customer’s account, and a problem-solution creative organizes its message around a difficulty and remedy. Those structures can be described without estimating conversions.
The misleading-title fixture tests the description rather than an existing label. Mixed format preserves an equally central combination that a one-format taxonomy would otherwise hide.
These are fictional text descriptions. They do not copy an ad library, verify a testimonial or reproduce the source post’s claimed volume, time or cost.
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 creative format.

Describe an ad's content to compare a product demonstration, customer testimonial and problem-solution format.

Open the decision rules and keep the intended distinction between Demonstration, Testimonial, Problem solution, Mixed format, 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 |
|---|---|---|
| Product walkthrough | Demonstration | 100% |
| Customer account | Testimonial | 99.0% |
| Problem and remedy | Problem solution | 95.0% |
| Two equal parts | Mixed format | 100% |
| Named testimonial without customer | Demonstration | 99.0% |
| No creative description | 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 identifies the creative structure described in the input. Authenticity and factual support require separate evidence.
Yes. This rubric uses Mixed format when two are equally central. A production library may need multi-label fields instead.
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.