Analytics question clarity: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Supply the question, schema and known business definitions. Check whether the metric, population and relevant comparison are clear before anyone calculates an answer.
A question can be grammatically clear but analytically incomplete. Terms such as active, best or improved can refer to several calculations unless the question or an existing policy defines them.
Ready concerns interpretability from supplied data definitions. It does not mean the query has run, the data is complete, or the requested business decision is appropriate.
This original question-review exercise adapts the clarity check in the linked Natural Language Data Analyst Agent. Schemas, questions and labels are authored examples. The demo neither queries a database nor chooses business metrics on the user’s behalf.

Use the sample to understand the rule, then test your own input for analytics question clarity.

Supply the question, schema and known business definitions.

Open the decision rules and keep the intended distinction between Ready, Clarify, NeedSchema. 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 NeedSchema before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Best is undefined | Clarify | 100% |
| Metric and period supplied | Ready | 90.0% |
| All-time request | Ready | 95.0% |
| Active lacks policy | Clarify | 99.0% |
| Comparison absent | Clarify | 100% |
| Schema missing | NeedSchema | 89.0% |
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. An all-time count or a task unrelated to time can already be complete. The question needs only the definitions that materially affect its answer.
No. It returns a label. A separate interface can present the missing definition and ask the user for 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.