CSV column mapping: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Supply a column definition, sample values and destination fields. Compare buyer, company and delivery-country meanings, then review an ambiguous or unmatched column.
Headers are useful clues, but two columns can share the same name and refer to different entities. Sample values such as country names do not settle whether the field belongs to a buyer, company or delivery.
No field preserves a clearly unmatched concept. Review preserves ambiguity among plausible destinations. A full importer still needs deterministic one-to-one mapping, required-field checks and user approval.
The linked table-import mapper assesses source/destination pairs. This original single-choice adaptation shows one column at a time; it does not upload a CSV, infer an entire schema or write records.
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 csv column mapping.

Supply a column definition, sample values and destination fields.

Open the decision rules and keep the intended distinction between Buyer country, Company country, Delivery country, No field, 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 |
|---|---|---|
| Buyer residence | Buyer country | 97.0% |
| Registration location | Company country | 99.0% |
| Shipping destination | Delivery country | 84.0% |
| Unmatched concept | No field | 98.0% |
| Generic header alone | Review | 94.0% |
| Contradictory ownership | Review | 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.
The same country names could occur in all three destination fields. The column definition needs to identify the entity or address role.
This example maps one supplied column. A full import interface needs additional schema validation and review of the complete mapping.
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.