Experiment: introduce overlapping ownership
Decide whether payment recovery or restoring access is the priority. If your team disagrees, clarify the routing policy before treating any label as correct.
Use the second scenario tab above to load this variation. Compare the returned decision as well as any probabilities: a changed answer can reveal an unclear policy, and an unchanged answer can reveal that the relevant detail was not captured by your question.
Use this pattern in your application
This playground request shape uses the original scenario. It is a reference for the input, not a public integration endpoint. For application integration, follow the official TypeSafe documentation linked in our Jev API guide. Keep API keys on the server and validate the returned type before taking action.
{
"playground": "https://aijev.net",
"language": "JavaScript",
"request": {
"model": "typesafe/jev-1.13",
"state": "Customer says: \"I was charged twice for my subscription and need a refund.\"",
"questions": {
"decision": {
"type": "choice",
"instructions": "Which team should handle this request?",
"criteria": {
"Billing": "Billing",
"Technical Support": "Technical Support",
"Sales": "Sales",
"Other": "Other"
}
}
},
"provider": {
"allow_fallbacks": false
}
},
"note": "AIJev Playground request shape only. For application integration, visit https://docs.typesafe.ai."
}
How to evaluate this workflow
Review a labeled sample of historical tickets. Track first-owner accuracy, reassignment rate, and the share sent to Other. Split results by department so a large billing queue does not hide weak technical routing.
Save a held-out set before changing your instructions. Compare new versions against the same examples, and review disagreements instead of assuming a valid response is a correct one. For escalation design, see confidence-based routing.
Frequently asked questions
Should I route by the largest probability alone?+
Not automatically. Compare the top categories and evaluate a review threshold on held-out tickets. A confident wrong route still creates extra work for the customer.
Are these results from a real customer deployment?+
No. These are original educational scenarios. The expected outcomes are editorial hypotheses; clicking Run Jev sends the displayed input to the model and shows its actual response.
Can I adapt this example to my own workflow?+
Yes. Replace the context, define your choices or rubric, and test against examples from your domain. The playground uses text input. Do not include credentials or unnecessary personal information.
References & further reading
Background on routing and evaluation workflows. Our requests and experiments below are original educational examples, not customer deployments. See Anthropic: Building effective agents.
For the underlying decision primitives, read TypeSafe’s System One documentation and our guide to Choice, Score, and Noul.
AIJev