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.
Describe what the interface needs to present. Match one-item summaries, shared-attribute comparisons and ordered procedures to supplied component roles without generating or implementing a layout.
The model can select a role from the application’s supplied set. It does not create a component implementation or grant permission to render arbitrary markup. A comparison table still needs rows and shared columns validated by code.
The setup-card fixture names a card but requests an ordered procedure. The role follows the actual display need. No fitting role keeps an unsupported map from being forced into a summary card.
The source describes an experiment with typed decisions and a rendering system. This original example only returns a role label; it does not generate or execute UI code.
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 ui component role matching.

Describe what the interface needs to present.

Open the decision rules and keep the intended distinction between Summary card, Comparison table, Step list, No fitting role, 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 |
|---|---|---|
| One item preview | Summary card | 100% |
| Shared attributes | Comparison table | 100% |
| Ordered setup | Step list | 100% |
| Unsupported interactive chart | No fitting role | 100% |
| Several steps called a card | Step list | 100% |
| No display requirement | 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 chooses a role. The application still supplies validated fields and renders the existing component.
Keep the request for review or extend the component catalog deliberately. Do not silently fabricate fields that an existing Block does not support.
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.