Agent routing
Define the question, receive a typed signal, and connect the result to the next step in your workflow.
TypeSafe AI · DECISION MODEL
TypeSafe’s Jev 1.14 decision model returns typed probabilities for routing, classification, scoring, and yes-or-no judgments over text and images.
MODEL PROFILE
TypeSafe AIMODEL ID
typesafe/jev-1.14
STRUCTURED OUTPUT
choice
score
noul
01 / Workbench
Try OpenAI Decisions API with GPT-6 Luna, or choose another decision model. Edit the input, define typed questions, and inspect the results before connecting the workflow to your backend.
Live requests require sign-in and use your available account credits.
WHERE IT FITS
Use typesafe/jev-1.14 to pin this release or ~typesafe/jev-latest to follow updates. Jev 1.13 remains available separately. This platform accepts up to 8 questions and a 32 KiB request body.
Define the question, receive a typed signal, and connect the result to the next step in your workflow.
Define the question, receive a typed signal, and connect the result to the next step in your workflow.
Define the question, receive a typed signal, and connect the result to the next step in your workflow.
ONE CONTRACT
The model changes, but your integration can keep a state, typed questions, and a predictable response contract.
Read the API docsREQUEST EXAMPLE
POST /v1/systemone{
"model": "typesafe/jev-1.14",
"state": "A customer reports a duplicate charge and needs a fast resolution.",
"questions": {
"route": {
"type": "choice",
"criteria": {
"billing": "send to billing support",
"account": "send to account support",
"urgent": "escalate for immediate review"
}
},
"urgent": {
"type": "noul",
"instructions": "Does this request need attention now?"
}
}
}