Building Production AI Observability on Kubernetes: OpenTelemetry, Langfuse, Prometheus & Grafana From Zero to Scale
Building Production-Grade AI Observability on Kubernetes
Most AI teams are solving the wrong problem.
Everyone is benchmarking models.
Very few teams are benchmarking infrastructure.
Production failur
edwinjonathand-devops.hashnode.dev19 min read
Talha
Senior AI / Full-Stack Engineer | Building & running production AI systems
langfuse is quite good, the only issue is that they dont have gateway and tool versioning