你能用 Jev 构建什么
Jev 擅长软件整天都在做的那些又小又快、高频的判断。这里是团队用它构建的一些具体例子——每一个都在 playground 里以真实的 API 调用实时运行。
套路始终不变:把一个 state 和几个类型化问题(choice / score / noul)交给 Jev,拿回你的代码可以据此分支的已校准答案。挑一个场景来加载确切的请求:
Coding & AI agents
The small, high-frequency decisions inside an agent loop — routing, gating, retrieval and verification.
Agent skill routing
choicenoulPick which skill or tool a coding agent should use for a request — or decline when none fit.
查看该用例 →Repo context selection
scorenoulRank which files are actually relevant to a task before spending context (and tokens) on them.
查看该用例 →Task-completion check
noulscoreBefore an agent stops, ask Jev whether the work is actually finished and the claims hold up.
查看该用例 →Content & marketing
Judge, score and tag content at scale — the analysis jobs, not the writing.
Support & operations
Triage, route and screen inbound work before a human touches it.
Moderation & data
Keep/flag/remove calls and turning messy input into typed fields.