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 ad copy to distinguish a problem, a solution approach or a named product. Review mixed messages without guessing what an individual reader knows.
This rubric labels what the copy foregrounds. It does not infer whether an actual reader knows a problem, a solution or a product, and it does not assign psychological traits to an audience.
A product name can be incidental. The fifth example centers a remedy approach despite mentioning ParseBox. Mixed focus keeps equally central message levels visible.
The source discussion includes awareness-stage tagging. This adaptation narrows the task to observable text cues, with fictional excerpts and no predicted ad response.
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 message focus.

Paste ad copy to distinguish a problem, a solution approach or a named product.

Open the decision rules and keep the intended distinction between Problem focus, Solution focus, Product focus, Mixed focus, 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 |
|---|---|---|
| Difficulty only | Problem focus | 99.0% |
| Remedy approach | Need evidence | 81.0% |
| Named product | Product focus | 100% |
| Equal problem and product | Mixed focus | 99.0% |
| Product name is incidental | Solution focus | 97.0% |
| No 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. 5 of 6 results matched the authored fixture expectations. For Remedy approach, the expectation was Solution focus; the observed choice was Need evidence.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 means the message centers a named product. The reader’s prior knowledge is outside the supplied evidence.
No. It is a descriptive text classification. Any relationship to campaign outcomes would require a separate measured study.
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.