Email solicitation: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Provide the email and its account context. Distinguish an optional purchase pitch, service notice and a message that includes both, without trusting urgency or a personal greeting.
An inbox policy often needs the message's purpose separately from its importance. A legitimate service notification may include marketing, and a sales pitch may use the same urgent language as a billing notice.
The source-linked builder article treats commercial solicitation as one of several independent email judgments. This example isolates that question with fictional messages. Its labels do not establish that a sender is genuine or that an account request should be followed.
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 email solicitation.

Provide the email and its account context.

Open the decision rules and keep the intended distinction between Solicitation, Service, Mixed, 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 |
|---|---|---|
| Personalized promotion | Solicitation | 100% |
| Payment failure | Service | 100% |
| Notice with offer | Mixed | 100% |
| Support response | Service | 99.0% |
| Vague account claim | Review | 92.0% |
| Cold proposal | Solicitation | 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
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. A requested export, receipt or account notice can be a Service message. Automation is not the purpose of the email.
That is a separate application decision. Mixed preserves the fact that a message contains service information as well as an offer; this demo does not hide or delete it.
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.