Project role 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 the task with a fictional responsibility roster. Select the role explicitly responsible, or keep no-match and conflicting ownership visible without ranking people or assigning real work.
The role names are labels, not evidence of expertise. The responsibility descriptions supplied with each task determine the intended match.
Review keeps incomplete scope and shared ownership visible. No match has a different meaning: the task is clear, but none of the listed responsibilities covers it.
The linked Paca project uses described members for task assignment suggestions. This adaptation uses fictional roles and displays a proposal; it does not rank employees, check capacity or assign a ticket.
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 project role matching.

Compare the task with a fictional responsibility roster.

Open the decision rules and keep the intended distinction between Docs role, UI role, Platform role, No match, 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 No match, Review before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| API reference | Docs role | 100% |
| Small-screen layout | UI role | 100% |
| Runtime deployment | Platform role | 100% |
| Outside this roster | No match | 98.0% |
| Two owners | Review | 100% |
| Missing task | Review | 71.0% |
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.
This demo uses fictional role labels. A real application should rely on consented responsibility information and separate assignment permissions; do not infer private traits or staffing suitability.
Provide an explicit ownership or tie-break rule, or keep the task in Review. A model preference is not a team agreement about responsibility.
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.