Open-deal activity: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Give the open opportunity and one account event. Compare concrete progress, a competitor evaluation, sponsor departure or pause with routine activity under the stated rule.
A CRM event is useful only in context. The same departure matters differently when the person is a named internal sponsor, an unrelated employee or someone moving between offices. The input must establish that relationship.
This classification records the meaning of one event. It does not predict a win, calculate a risk score or count activities over a time window. Dates, event aggregation and any CRM changes belong in code and an authorized review process.
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 open-deal activity.

Give the open opportunity and one account event.

Open the decision rules and keep the intended distinction between Competitor, Escalation, Championexit, Stall, Progress. 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 |
|---|---|---|
| Alternative pilot | Competitor | 100% |
| Competing offer rejected | Progress | 100% |
| Sponsor leaves | Championexit | 100% |
| Pause requested | Stall | 100% |
| Routine download | Routine | 84.0% |
| No account context | Championexit | 42.0% |
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 No account context, the expectation was Unclear; the observed choice was Championexit.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.
Not in this rule. Supply an explicit pause or add a separately documented policy. Counting silent days is a deterministic step, and silence alone does not establish why a deal stopped.
Yes. Split independent events or clarify the dominant event before using a single-label contract. The demo does not turn several risks into a composite score.
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.