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.
Give an event description to distinguish navigation, purchases, account changes and support requests. The described activity takes precedence over a misleading event name.
The event name can describe a location rather than an outcome. The misleading-name fixture views a checkout page but completes no order, so it belongs under Navigation in this taxonomy.
A profile change and a support submission may both come from a form. Their purposes distinguish Account from Support. The input must describe the activity that actually occurred.
This is a semantic intake label. Event schema validation, payment verification, duplicate detection and aggregate counts belong to separate checks; the model does not reconstruct telemetry from an event name.
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 analytics event categories.

Give an event description to distinguish navigation, purchases, account changes and support requests.

Open the decision rules and keep the intended distinction between Navigation, Purchase, Account, Support, 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 |
|---|---|---|
| Page opened | Navigation | 95.0% |
| Order completed | Purchase | 100% |
| Profile changed | Account | 100% |
| Help requested | Support | 100% |
| Misleading name | Navigation | 100% |
| No 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.
Yes, when their meaning is established, but they are not authoritative in this example. The description and verified activity take precedence over a misleading name.
No. It labels the supplied description. Payment success must come from the transaction system and should not be inferred by this classifier.
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.