Rental claim verification: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Read one fictional listing claim to choose a viewing check, a document request or a review of vague promotion. The result suggests an evidence channel rather than deciding legality or liability.
This example makes a checklist suggestion for one claim. It does not verify the property, establish legal rights or recommend a tenant or landlord.
Some claims need more than one kind of evidence. Separate them into clear statements or keep the combined item in Review.
The linked rental prototype turns listing statements into checks. Our fictional text samples cover the evidence-channel part and do not reproduce its full assessment.
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 rental claim verification.

Read one fictional listing claim to choose a viewing check, a document request or a review of vague promotion.

Open the decision rules and keep the intended distinction between Viewing check, Document request, Vague promotion, 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 |
|---|---|---|
| Physical condition | Viewing check | 100% |
| Renovation history | Document request | 99.0% |
| Subjective praise | Vague promotion | 100% |
| Contract term | Document request | 98.0% |
| Two claim channels | Review | 95.0% |
| Unspecified claim | Vague promotion | 94.0% |
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 Unspecified claim, the expectation was Review; the observed choice was Vague promotion.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. It means the claim concerns information that cannot be established by the supplied listing sentence alone.
No. A viewing provides limited observations. Qualified inspections, records and local requirements may still matter; this demo does not evaluate them.
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.