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's purpose, verified behavior notes and policy. Distinguish routine evidence, prohibited behavior and conflicting or inconclusive signals before a separate enforcement decision.
The suspicious-click fixture checks a misleading name against ordinary behavior notes. The rule relies on stated evidence, so a dramatic identifier does not establish abuse.
Conflicting signals preserves a record with both ordinary and prohibited behavior. Inconclusive keeps a sparse observation visible without treating missing evidence as innocence or guilt.
This toy record does not expose a real detection method or assess a visitor’s identity. WAF, rate limits and authorization remain separate controls. The model label is only a pending review signal.
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 event-policy evidence.

Give an event's purpose, verified behavior notes and policy.

Open the decision rules and keep the intended distinction between Routine evidence, Abuse evidence, Conflicting signals, Inconclusive, 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 |
|---|---|---|
| Ordinary usage | Routine evidence | 100% |
| Explicit prohibited behavior | Abuse evidence | 95.0% |
| Conflicting record | Conflicting signals | 96.0% |
| Sparse observation | Need evidence | 52.0% |
| Suspicious name alone | Routine evidence | 48.0% |
| No policy or signals | 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 Sparse observation, the expectation was Inconclusive; 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 supplied notes describe routine use under the given policy. Hidden behavior and incomplete telemetry remain outside the input.
No. Preserve the whole record for review. The example deliberately avoids hiding an observed prohibited signal behind ordinary activity.
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.