Procurement brief classification: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Match a purchase brief to supplied fictional printer goods, maintenance and rental categories. Compare mixed or conflicting scopes without presenting the shortlist as official procurement codes.
Procurement classification depends on the purchased deliverable. Similar equipment names can describe a goods purchase, a rental or a maintenance service, so the shortlist needs usable descriptions rather than bare code numbers.
The identifiers here are fictional teaching labels. An operational CPV workflow needs the relevant official vocabulary, the full procurement scope and review by the responsible person.
The source author describes Jev choosing among a supplied procurement-code shortlist. This original example demonstrates that selection pattern without copying the application, choosing a supplier or claiming legal classification accuracy.
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 procurement brief classification.

Match a purchase brief to supplied fictional printer goods, maintenance and rental categories.

Open the decision rules and keep the intended distinction between G, M, R, Mixed, 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 |
|---|---|---|
| Buy the equipment | G | 100% |
| Maintain existing devices | M | 100% |
| Rent for an event | R | 100% |
| Two equal deliverables | Mixed | 98.0% |
| Vague purchase | Review | 99.0% |
| Contradictory ownership | R | 59.0% |
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. 5 of 6 results matched the authored fixture expectations. For Contradictory ownership, the expectation was Review; the observed choice was R.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. They are deliberately fictional IDs for this demonstration. Use an authoritative code list and competent review for a real procurement classification.
A vague or equally mixed purchase may not support one category. Keeping Mixed and Review prevents the interface from presenting an arbitrary shortlist choice as resolved.
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.