便宜 vs 贵模型路由

用 Jev 判难度/风险，再由代码路由模型。

Who: Platform / AI eng owning multi-model stacks. Steps: (1) State = user request (+ risk tags). (2) Choice difficulty/risk or Score complexity. (3) Code picks small LLM vs frontier vs abstain. Expected effect: spend frontier tokens only when needed.

提示词

Audience: platform / AI eng.
Steps:
1) State: user request, tools, budget, risk tags.
2) Choice difficulty/risk or Score complexity; Noul needs_strong_model.
3) Code routes cheap vs frontier vs abstain/human.
Expected effect: spend frontier tokens only when justified.

需要授权：typesafe-sdkllm-gateway

它是怎么搭起来的

以下说明为英文原文（来自社区作者），提示词本身建议保留英文。

Sources: LangChain · Building a harness with Jev · confidence-routing · awesome-jev-usecases · Harness.

Treat confidence as a second axis beside category: cheap default model when confidence is high; escalate to frontier / human when low. Community harness numbers are author-reported.

Sources (wave-2 deepen)

为什么它好用

Harness pattern: System One decides when System Two is worth paying for.

本案例收集自公开的 Jev 社区，版权归原作者所有。提示词属于参考资料：运行前请先审阅内容，并且不要让 bot 超出你实际授予的权限行事。