Focused field values: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Give the focused field, user request and candidate text spans. Select the shortest complete requested value, leaving ambiguity or an absent value unmatched.
Typing the entire user instruction into a field is a boundary error. This request selects a value already present in the candidates, using the focused field label to distinguish it from other text in the same request.
The output is a candidate label, so it cannot correct spelling or fill gaps. The application must resolve that label to the exact stored span and verify any actual input afterward. This page does neither device input nor readback.
This original text demonstration adapts a decision in a repository linked by the cited X post. The examples and explicit uncertainty outcomes are ours. The post is a directory reference, not proof that its author built every linked project. No third-party benchmark, business outcome or external action is reproduced.

Use the sample to understand the rule, then test your own input for focused field values.

Give the focused field, user request and candidate text spans.

Open the decision rules and keep the intended distinction between A, B, C, None. 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 uncertain or unexpected results before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Place search | B | 100% |
| Document title | A | 100% |
| Full search phrase | C | 99.0% |
| Two values in request | B | 100% |
| Missing complete value | None | 90.0% |
| Unknown focus | A | 77.0% |
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. 5 of 6 results matched the authored fixture expectations. For Unknown focus, the expectation was None; the observed choice was A.Verified
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
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.
# Offline: inspect the downloaded saved observations. No API key is needed.
python preview_choice_workflow.py samples.json saved-api-results.json
# Optional live request: install the SDK and set TYPESAFE_API_KEY privately.
npm install @typesafe-ai/sdk@0.6.0
node run-choice-sample.mjs samples.json case-1
# The live response prints to the terminal; it does not update saved-api-results.json.The input contract and these limits define what the result means.
No. This contract selects one existing span. Supply a complete candidate or keep None; joining text requires a different explicit step.
No. Only a later independent field readback could confirm that. This demo displays the selection.
It describes the distribution over the supplied choices for this request. These six synthetic examples are functional tests with authored expectations, not a production accuracy benchmark.
No. The demo displays a label and distribution. The downloadable consumer produces a pending preview packet. Application code and a separate authorization policy would control any real action.
Edit the example above to see how a changed fact affects the decision, or open the Playground for another task.