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.
Read a meeting excerpt to distinguish an adopted decision from a proposal, a deferred choice or a discussion with no decision topic. Keep unresolved context separate from an actual resolution.
The proposal fixture names an option without an acceptance statement. Calling it a decision would add a commitment the notes do not contain. Decision deferred preserves an explicit postponement.
An adopted alternative can follow a rejected proposal. The fifth sample records the final CSV resolution, so the earlier rejected XML suggestion does not make the excerpt unresolved.
The source proposes checking meeting notes before summarization. This adaptation labels the supplied excerpt; it does not attend a meeting, infer consensus from silence or write minutes.
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 decisions in meeting notes.

Read a meeting excerpt to distinguish an adopted decision from a proposal, a deferred choice or a discussion with no decision topic.

Open the decision rules and keep the intended distinction between Decision recorded, Proposal only, Decision deferred, No decision topic, 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 |
|---|---|---|
| Accepted format | Decision recorded | 100% |
| Suggested format | Proposal only | 100% |
| Choice postponed | Decision deferred | 100% |
| Status report | No decision topic | 96.0% |
| Rejected proposal, accepted alternative | Decision recorded | 100% |
| No 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. A suggestion can describe an action without adopting it. The excerpt needs wording that establishes a resolution.
Review one named issue at a time or use multiple questions. This one-label fixture assumes one primary issue and should not erase other decisions.
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.