Customer message tone: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Paste the customer's actual wording to compare calm reporting, civil dissatisfaction and anger. Keep the seriousness of the issue separate from the expressed tone.
Tone and urgency answer different questions. The calm outage preset still needs an operational severity assessment; the tone label cannot decide how quickly support should act.
This example uses the text of a message, not a profile of its author. It does not infer mental health, personality or hidden emotional state. Sarcasm and missing conversational context can leave the judgment uncertain.
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 customer message tone.

Paste the customer's actual wording to compare calm reporting, civil dissatisfaction and anger.

Open the decision rules and keep the intended distinction between Calm, Dissatisfied, Angry, Unclear. 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 Unclear before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Calm outage | Calm | 98.0% |
| Polite complaint | Dissatisfied | 100% |
| Forceful demand | Angry | 100% |
| Acknowledged limitation | Calm | 93.0% |
| Second-hand urgency | Unclear | 100% |
| Disappointed but courteous | Dissatisfied | 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.
Calm describes the supplied wording. It does not mean the incident is harmless or can wait.
A summary may lose the language that reveals tone. Supply the actual wording or keep the result unresolved.
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.