Genkit Flows on Kubernetes, Routed by a Decision Model: senro + jev in Go

说明与用途

在 Kubernetes 上运行 Genkit 流程的工作流，使用 jev 做路由和安全决策，使用 Gemini 编写回复，实现快速、类型化的决策和隔离的 Pod 执行。

问题

Using a chat model alone to route support tickets and verify replies is slow, uncertain, and prone to errors.

结果

The pipeline achieves millisecond routing decisions, typed safety verification, and isolated pod execution with retries and caching, improving reliability and reducing latency compared to a pure chat‑model approach.

工作流

• Seed raw email into run workspace
• Ingest email with Gemini to produce ticket.json
• Triage with jev to decide department, urgency, frustration, human need
• Collect ticket.json and decision.json
• Draft reply with Gemini per department playbook
• Verify draft with jev against playbook
• Send reply if verification passes
• Escalate to human with brief if jev indicates
• Skip steps based on earlier decisions

证据

Gemini writes. jev decides.

来源

A decision model is built for exactly that call.

来源

senro’s Kubernetes executor never reads KUBECONFIG, ~/.kube/config or your current context.

来源