Sales qualification evidence: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Supply call notes and one qualification criterion. Distinguish concrete evidence from a passing mention or an undiscussed subject, keeping conflicting notes visible rather than inferring qualification.
This example covers one evidence method across several MEDDPICC-style dimensions. The criterion is part of the input: metrics need a measure, a budget owner needs stated authority, and a champion needs an observed internal action.
Established means the supplied notes meet the supplied criterion. It does not verify that the speaker was truthful, that the notes are complete or that the opportunity will close. Keep the underlying notes available for a human review.
This original text demonstration adapts a decision in a repository linked by the cited X post. The examples and explicit uncertainty outcomes are ours. The post is a directory reference, not proof that its author built every linked project. No third-party benchmark, business outcome or external action is reproduced.

Use the sample to understand the rule, then test your own input for sales qualification evidence.

Supply call notes and one qualification criterion.

Open the decision rules and keep the intended distinction between Established, Mentioned, Notdiscussed, 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 |
|---|---|---|
| Measured target | Established | 100% |
| Vague improvement | Mentioned | 83.0% |
| Budget owner confirmed | Established | 100% |
| Friendly contact | Mentioned | 97.0% |
| No procurement discussion | Notdiscussed | 100% |
| Conflicting authority | Unclear | 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.
npm install @typesafe-ai/sdk@0.6.0
# Set TYPESAFE_API_KEY privately in your shell.
node run-choice-sample.mjs samples.json case-1
python preview_choice_workflow.py samples.json saved-api-results.jsonThe input contract and these limits define what the result means.
They share the same evidence-checking method. Change the dimension and criterion together, then compare what the notes establish rather than treating every label as a different workflow.
No. Under the supplied criterion the notes must name a person and explicitly establish budget control. A title by itself is insufficient.
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.