Experiment: change missing functionality into a failure
A previously working function now fails. Compare Bug report with the original Feature request and check whether the distinction is consistent.
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": "Feedback: I can export one report at a time, but I need to download every report for the month together. Could you add a bulk export button?",
"questions": {
"decision": {
"type": "choice",
"instructions": "Which product feedback theme best describes the main request?",
"criteria": {
"Bug report": "Bug report",
"Feature request": "Feature request",
"Usability friction": "Usability friction",
"Positive feedback": "Positive feedback",
"Other / review": "Other / review"
}
}
},
"provider": {
"allow_fallbacks": false
}
},
"note": "AIJev Playground request shape only. For application integration, visit https://docs.typesafe.ai."
}
How to evaluate this workflow
Have reviewers independently label a sample and resolve category disagreements. Measure per-category precision and review rate. Keep duplicate comments separate from unique affected users when analyzing volume.
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
Can I use these labels as sentiment scores?+
No. Themes and sentiment answer different questions. A frustrated customer may report a bug or request a feature; add a separate rubric only if that distinction helps your workflow.
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 assigning categories to text. This Jev example is an independent implementation exercise, not a Microsoft integration. See Microsoft Learn: Custom text classification.
For the underlying decision primitives, read TypeSafe’s System One documentation and our guide to Choice, Score, and Noul.
AIJev