GrowthBook

Missed us at the The AI Conference? Here's the write-up behind the LLM traces handout we were giving out. Your evals stop at deploy. They tell you a new model or prompt clears your quality bar. They can't tell you what it does to revenue, activation, or token spend once it's in front of real users. GrowthBook now reads your Langfuse and Arize Phoenix traces as experiment metrics. Cost, latency, error rate, and eval scores sit in the same experiment as your business metrics, so you can test a cheaper model and see whether quality or conversions slip before it goes to everyone. Learn how it works and how to set up your first test ➡️ https://lnkd.in/eD_xvxUE