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 a scheduling message and whether the event already exists. Distinguish adding, modifying and removing an event from a request for information.
Rescheduling an existing event is a modification, not a new event, when the request explicitly preserves its identity. The read-only fixture asks for information and forbids a change.
This question does not select which existing event a vague reference means. It also does not calculate time zones, extract a date or confirm that a slot is available. Those fields need separate validation.
The source describes a computer-use calendar demonstration. These original messages expose one text decision only; no calendar window is opened and no event is created.
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 calendar edit intent.

Give a scheduling message and whether the event already exists.

Open the decision rules and keep the intended distinction between Add event, Modify event, Remove event, No edit requested, 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 |
|---|---|---|
| New meeting | Add event | 99.0% |
| Change existing title | Modify event | 100% |
| Cancel event | Remove event | 100% |
| Read only | No edit requested | 99.0% |
| Reschedule remains modification | Modify event | 100% |
| No scheduling message | 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. It describes the operation. The application must resolve the intended event and validate permissions before any edit.
No. Time extraction, normalization and availability checks are outside this question. Missing or ambiguous times must remain unresolved.
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.