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.
Show the authentication check and protected operation in a code excerpt. Compare a check before access with a late or absent check, using only the shown path.
The late-check example reads the protected record before checking the session. The rubric inspects that order in the shown pseudocode; it does not examine callers, middleware or a running server.
A helper with user in its name is not sufficient evidence of a guard. The fixture explicitly says it only logs a name. Conversely, a complete public-help excerpt needs no protected-access classification.
An observed Guard before access label is one review signal. It does not prove that authentication is correct, authorization is enforced, or the broader application has no vulnerability.
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 authentication check order.

Show the authentication check and protected operation in a code excerpt.

Open the decision rules and keep the intended distinction between Guard before access, Guard after access, No guard shown, No protected access, 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 |
|---|---|---|
| Guard first | Guard before access | 100% |
| Late check | Guard after access | 99.0% |
| Check absent | No guard shown | 100% |
| Public operation | No protected access | 100% |
| Named helper is not a visible check | No guard shown | 96.0% |
| Absent 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. Authentication and authorization are separate, and the shown ordering alone establishes neither their correctness nor their coverage.
Supply the relevant evidence or use a separate review scope. This example deliberately judges only the visible excerpt, so hidden middleware cannot be assumed.
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.