Recurring payment cues: 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 billing description for explicit renewal, subscription or installment language. Distinguish a stated one-off purchase from absent or conflicting recurrence evidence without predicting future charges.
This label records what the description says. Recurring cue does not prove that another charge will occur; a subscription may later be cancelled or its terms changed.
One-off cue requires an explicit one-time statement. When the text simply names a store or shows a card purchase, No recurrence evidence preserves that gap.
The linked transaction recipe includes a recurrence question. Our synthetic examples isolate the wording check and do not access a bank account, compute payment dates or categorize spending.
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 recurring payment cues.

Read one fictional billing description for explicit renewal, subscription or installment language.

Open the decision rules and keep the intended distinction between Recurring cue, One-off cue, No recurrence evidence, 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 |
|---|---|---|
| Monthly renewal | Recurring cue | 100% |
| Installment series | Recurring cue | 100% |
| Single license | One-off cue | 100% |
| Merchant only | No recurrence evidence | 91.0% |
| Conflicting terms | Review | 98.0% |
| No detail | No recurrence evidence | 51.0% |
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 No detail, the expectation was Review; the observed choice was No recurrence evidence.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 provided wording does not establish recurrence. Another transaction record or the actual billing terms may add information.
This taxonomy includes an explicitly stated payment series. If your product separates installments from subscriptions, define separate choices and retest both.
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.