Unverified50% confidenceFactExact time
When using Jev, the user provides a piece of state (such as a customer message) and asks three types of questions about that state: No (yes/no questions), Choice (choosing one category or label among given options), and Score (rating something on a scale).
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Call Decision Model Jev from Python in 10 Minutes: Let AI Make Choices and Score
bilibiliopenclawai11/5/2026
Related Entities
Related Claims
VerifiedJev offers three question types: Select, Score, and Null/Bool, with each response accompanied by a confidence value.78% similarUnverifiedJev works by having users predefine the set of allowed answers, and Jev returns a label, a score, or a yes/no probability value.76% similarUnverifiedJev can handle multiple question types (such as Choice, No, Score) in the same request and return a structured combined result.76% similarUnverifiedJev separates state (the current context) from questions (what to ask): the same state can be reused for multiple sets of questions, and the typed question sets allow the front end to statically infer the return type.71% similarUnverifiedThe --ask mode supports three question forms: yes/no questions, label questions, and rating questions.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1140059API
curl https://kongchang.com/api/v1/knowledge/claims/1140059MCP
get_claim(id=1140059)