Interface screen roles: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Provide redacted interface labels to distinguish authentication, payment, private account content and ordinary content. The result describes the supplied metadata rather than inspecting a screen or granting access.
All examples contain synthetic labels and explicitly removed values. This page does not capture a browser screen or inspect your account.
The source-linked focus app considers screen purpose and privacy. Our adaptation classifies redacted metadata; it is not a privacy filter that authorizes uploading the original screen.
A real integration must apply permissions, data minimization and deterministic redaction before a hosted request. Ordinary content is a descriptive label, not a guarantee that no sensitive text exists.
This is an independently authored text demonstration inspired by the linked X discussion. Its rules and synthetic inputs are ours. It does not reproduce the author’s application, verify reported outcomes, or perform an external action.

Use the sample to understand the rule, then test your own input for interface screen roles.

Provide redacted interface labels to distinguish authentication, payment, private account content and ordinary content.

Open the decision rules and keep the intended distinction between Authentication, Payment, Private account content, Ordinary content, Review. 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 Review before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Sign-in form | Authentication | 100% |
| Checkout fields | Payment | 100% |
| Private inbox | Private account content | 98.0% |
| Public documentation | Ordinary content | 97.0% |
| Missing role | Review | 97.0% |
| Unresolved extraction | Review | 95.0% |
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. 6 of 6 results matched the authored fixture expectations.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. Permission and redaction must be enforced before sending data. This text exercise is not an authorization mechanism.
No. It describes the supplied public-content role. It does not verify every field, remove personal data or override application permissions.
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.