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

Описание и применение

Поток работы, использующий Genkit и senro для обработки заявок поддержки в Kubernetes, где модель jev принимает решения о маршрутизации и безопасности, а Gemini пишет ответы, обеспечивая быстрые, типизированные решения и изолированные шаги в подах.

Задача

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

Результат

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.

Рабочий процесс

• 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

Доказательства

Gemini writes. jev decides.

Источник

A decision model is built for exactly that call.

Источник

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

Источник