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 an original product description using a small catalog taxonomy. Distinguish hand tools, storage and stationery by stated purpose, preserving equally central mixed uses or missing details.
Tool organizer contains tool, but its purpose is storage. The screwdriver and notebook supply clearer category boundaries, while the equal bundle shows why a mixed outcome is useful.
This task derives a category from a description. It differs from mapping an existing legacy label to a canonical ID: a legacy label may be absent, incorrect or too coarse.
The example is inspired by using Jev in a spreadsheet. It does not connect to Excel, inspect a real shop or overwrite catalog rows. The application should review uncertain items before persisting labels.
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 product category classification.

Read an original product description using a small catalog taxonomy.

Open the decision rules and keep the intended distinction between Hand tool, Storage, Stationery, Mixed product, 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 |
|---|---|---|
| Small screwdriver | Hand tool | 100% |
| Parts organizer | Storage | 100% |
| Paper notebook | Stationery | 100% |
| Equal bundle | Mixed product | 100% |
| Tool word in storage copy | Storage | 100% |
| No product description | 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. This rubric preserves an equally central combination as Mixed product. A real multi-label taxonomy needs a different contract instead of forcing every bundle into one category.
Edit both the decision rule and the choice labels, then test representative rows from that taxonomy. The three authored categories are only a bounded example.
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.