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.

use-jev