On-call team routing: 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 affected services and a fictional ownership directory. Select their shared team or a cross-team handoff, keeping missing and conflicting owners visible.
The ownership directory is part of the input, not model memory. Keep it current and identify services using trusted application metadata where possible.
A single service with contradictory owner records needs Review. That is different from two services whose unambiguous owners belong to different teams.
Cross-team describes the supplied ownership map. It does not choose an incident commander or determine which team caused the problem.
The source-linked on-call project demonstrates service-oriented triage. This page returns a proposed match and sends no notifications.
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 on-call team routing.

Give the affected services and a fictional ownership directory.

Open the decision rules and keep the intended distinction between Platform, Search, Payments, Cross-team, 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 |
|---|---|---|
| Search endpoint | Search | 100% |
| Payment path | Payments | 100% |
| Cross-team incident | Cross-team | 100% |
| Unknown service | Review | 99.0% |
| Trace dependency | Platform | 99.0% |
| Conflicting directory | 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.
Not under this rule. Conflicting records for one service leave ownership unresolved. Cross-team requires at least two affected services, each with an unambiguous owner.
Library names and host names do not reliably identify the affected service. This contract requires an explicit affected-service fact and a matching directory entry.
Return the common team when they share an owner. Return Cross-team for several owners, or Review if an owner is missing.
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.