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.
Compare the case with the supplied support policy. Distinguish routine procedures, specialist investigation and reserved human decisions without using urgency alone to choose the handling path.
The routine-settings example becomes urgent in its wording without becoming a specialist investigation. A handling path follows the supplied policy and the evidence needed to resolve the issue.
Human review is reserved for a discretionary exception in these fixtures. It does not imply that a customer is risky or difficult. Unresolved makes an uncovered business request visible rather than routing it to the nearest familiar support queue.
This is a small original decision layer inspired by a discussion of support triage. It does not demonstrate processing millions of tickets or reproduce any enterprise automation.
This is an original synthetic demonstration adapted from the cited workflow discussion. It does not reproduce the source application or verify its performance, adoption or security claims.

Use the sample to understand the rule, then test your own input for support handling paths.

Compare the case with the supplied support policy.

Open the decision rules and keep the intended distinction between Routine path, Specialist path, Human review, Unresolved, 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 Human 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 |
|---|---|---|
| Known export setting | Routine path | 100% |
| Unexplained crash | Specialist path | 100% |
| Exception request | Human review | 100% |
| No covered path | Unresolved | 100% |
| Urgent routine request | Routine path | 100% |
| Absent policy | 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 the supplied policy covers it with an established procedure. Urgency can be assessed separately without changing the complexity rule.
No. It is a valid model outcome when the supplied policy does not cover the case. A failed API request provides no fresh routing judgment.
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.