Evan Rylor

Indie hacker building AI tools

About

Building and launching small AI products fast. Focused on simple ideas, real traction, and learning from what works. Always experimenting, always shipping. 🚀

Badges

Gemologist

Tastemaker

Gone streaking

Forums

p/vocera

•

1mo ago

LLM-as-a-judge based monitoring is not enough for Voice AI

Most teams scaling Voice AI think they can monitor quality with a simple LLM prompt. They are wrong.

An LLM can t hear a "crunchy" voice line, it can t accurately measure a 500ms "barge-in," and it struggles with the nuances of true conversational flow.

When we built Cekura Monitoring, we realized we had to go beyond the LLM. We combined Heuristic and Statistical models with our Metric Optimizer to solve the "Scaling Wall."