Discussion argument types: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Provide a comment and its thread context. Distinguish criticism of evidence, concern about hype and an accusation of promotion without endorsing any of those claims.
The thread and parent comment can change what a short reply means. Supply them when the reply refers to an earlier claim.
Marketing accusation records what the writer alleges. It does not identify bots, prove sponsorship or evaluate the writer.
The source-linked sorter lets readers define comment buckets. This page uses an original fixed taxonomy and displays one proposed label.
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 discussion argument types.

Provide a comment and its thread context.

Open the decision rules and keep the intended distinction between Evidence criticism, Hype concern, Marketing accusation, Other, 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 |
|---|---|---|
| Missing control | Evidence criticism | 100% |
| Inflated promise | Hype concern | 99.0% |
| Promotion allegation | Marketing accusation | 100% |
| Practical question | Other | 99.0% |
| Unresolved reference | Review | 85.0% |
| Two central objections | Review | 96.0% |
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. Several categories can contain positive or negative wording. The question concerns what the argument is doing.
Choose Review when neither is dominant. Split the comment into separate units only if your downstream task needs argument-level annotation.
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.