Our in‑house agent router: Jev vs Kev-4B vs bge-small

说明与用途

内部代理路由器使用两个本地模型 bge‑small 和 Kev‑4B，将提示路由到正确的代理，检测准确率 99.5%，正确代理选择率 85%，每次调用零成本，数据不离开本地。

问题

Routing prompts to the correct business automation agent while keeping data on premises and minimizing cost.

结果

Using bge‑small and Kev‑4B achieves ~99.5% detection, 8% false alarm, 85% correct agent selection (97% in top 3) with ~0.12 s latency and zero cost per call.

工作流

• Receive prompt
• Run bge‑small (6 ms) to detect off‑goal prompts
• Run Kev‑4B (~0.12 s) to detect off‑goal prompts
• If both models reject, Kev‑4B selects top 3 candidate agents
• Route prompt to selected agent
• If both models accept, keep prompt with current agent

证据

bge‑small (6 ms) is very accurate at catching prompts that don't belong. But it is not good at picking the right agent (in our experiments).

来源

Kev‑4B (local, ~0.12 s) is slightly lower at calling out prompts that don't belong, but good at picking the right target agent: it is in its top 3 for 97% of prompts, against 94% for bge‑small.

来源

Detection: an off‑goal prompt is flagged. False alarm: an on‑goal prompt is wrongly flagged. Right agent for the prompt: an other‑goal prompt is sent to the correct agent.

来源