SQL question matching: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Compare a SELECT with the question, schema and metric definitions. Review filters, grouping and detail level for a semantic mismatch without executing the query or certifying its result.
Syntax, safety and meaning are separate checks. A read-only, bounded query can still use the wrong aggregation or select a different population from the one requested.
The demo reads small SELECT statements with supplied schema assumptions. Complex joins, custom functions and unstated metric policies may require more context or a different validation tool.
This original SQL-reading exercise adapts the relevance review in the linked Natural Language Data Analyst Agent. Queries and schemas are synthetic. The demo does not execute SQL, validate database permissions or reproduce that application’s thresholds.

Use the sample to understand the rule, then test your own input for sql question matching.

Compare a SELECT with the question, schema and metric definitions.

Open the decision rules and keep the intended distinction between Match, Mismatch, 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 |
|---|---|---|
| Correct grouped count | Match | 100% |
| Wrong metric | Mismatch | 100% |
| Wrong population | Mismatch | 100% |
| Grouping lost | Mismatch | 100% |
| Explicit all-time scope | Match | 100% |
| Undefined active metric | Unclear | 93.0% |
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. Syntax checks, permissions, resource limits and execution approval are separate. This label concerns the requested meaning only.
It can encode an assumption, but that does not make the assumption the user’s intent. Supply the agreed definition before judging the match.
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.