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 resource excerpt to identify whether it teaches steps, shows a result or announces a development. Preserve equally central mixed purposes instead of guessing from its source label.
A resource can teach a procedure, show a result or announce a release. The original excerpts make those functions explicit, so the judgment does not depend on a platform name or an unseen linked page.
The tutorial fixture contains actual fictional steps. The demonstration shows an outcome while explicitly omitting setup. Mixed purpose retains an equally central announcement and procedure instead of forcing one role.
This example does not search live platforms or claim to reproduce the source author’s research agent. It classifies supplied original descriptions as an intake step.
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 research resource types.

Read a resource excerpt to identify whether it teaches steps, shows a result or announces a development.

Open the decision rules and keep the intended distinction between Tutorial, Demonstration, Announcement, Mixed purpose, 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 |
|---|---|---|
| Setup walkthrough | Tutorial | 100% |
| Result shown | Demonstration | 88.0% |
| Release note | Announcement | 84.0% |
| Equal instruction and news | Mixed purpose | 93.0% |
| Demo in the title | Tutorial | 88.0% |
| 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. It identifies the resource’s purpose. Reproducibility, failure coverage and measurement quality require their own evidence.
Yes. Mixed purpose applies when both functions are equally central. If one function is clearly primary, classify that primary role.
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.