End Vibes-Based RAG - Evals as the Control Plane

Abstract

Stop shipping on vibes. Add lightweight, in-loop eval gates that decide iterate or proceed—so bad retrievals retry automatically and bad answers never ship. Tool-agnostic, defensible, fast.

Bio

Jeff Fan is a Solutions Architect at DigitalOcean who designs Kubernetes-based GPU stacks for LLM inference. He speaks on right-sizing LLM serving (vLLM/KServe/llm-d on DOKS), building memory-enabled support agents, and eval-first RAG (“evals, not vibes”). Formerly keeping mission-critical German systems online, he now turns cloud/AI complexity into copy-paste playbooks that help teams move from PoC to cost-efficient production.