Jev is a newly released general classifier. Give it text or application state and typed questions; it returns decisions and probabilities your code can use for routing, ranking, extraction, or verification.
Read the upstream llms.txt to find current documentation, then follow the pages relevant to the task:
- Use cases: explore applications; see worked examples for function calling, reranking, and citation checks.
- Best practices: provide relevant state, ask focused questions, define clear criteria, and batch independent questions. Keep workflow logic in code.
- Confidence: use uncertainty to decide when to escalate, and validate thresholds on representative data.
- Python SDK, JavaScript SDK, or HTTP API: read before integrating.
Choice, Score, and Noul
| Primitive | Example use | Result |
|---|---|---|
| Choice | Route a support request to a team | One option, option probabilities, and confidence |
| Score | Rate a bug's impact | Probability-weighted position on ordered levels, plus confidence |
| Noul | Check whether a refund is requested | Probability of yes; 0.5 means uncertainty, not medium intensity |
Install typesafe-sdk and check that JEV_API_KEY is set in the environment,
otherwise ask the user to provide it.
This Python example asks one question of each type in a single call:
import os
from typesafe_sdk import Choice, Noul, Score, TypeSafeClient
with TypeSafeClient(api_key=os.environ["JEV_API_KEY"]) as client:
result = client.system_one(
state={"ticket": "PDF export fails, but CSV works. Please refund this month."},
questions={
"team": Choice(
instructions="Which team should handle the main issue in the ticket?",
criteria={"billing": "Charges and payments",
"technical": "Broken product features", "other": "Neither"},
),
"impact": Score(
instructions="How much does the reported bug affect functionality?",
criteria=["Cosmetic only", "Feature broken; workaround available",
"Work blocked; no workaround available"],
),
"refund": Noul(instructions="Does the ticket explicitly request a refund?"),
},
)
print(result.choices["team"].choice)
print(result.scores["impact"].score)
print(result.nouls["refund"].noul)