Learn how to combine OpenLIT Operator and Grafana Cloud to enable zero-code observability for your AI workloads.

Grafana is an open-source analytics and monitoring platform that allows users to visualize and analyze metrics from various data sources. The Grafana blog covers topics such as data visualization, monitoring best practices, and new features in Grafana software. Developers and data engineers can learn how to leverage Grafana for monitoring infrastructure, analyzing performance metrics, and creating interactive dashboards for data-driven decision-making.

Grafana Labs

OpenLIT Operator enables zero-code observability for AI workloads on Kubernetes by automatically injecting OpenTelemetry instrumentation into pods without requiring code changes or image rebuilds. Combined with Grafana Cloud's AI Observability dashboards, it provides monitoring of LLM costs, token usage, latency, and agent workflows. The setup involves installing the OpenLIT Operator via Helm, creating an AutoInstrumentation custom resource with label selectors and OTLP endpoint configuration pointing to Grafana Cloud, and deploying AI applications normally. Supported frameworks include LangChain, CrewAI, LlamaIndex, and providers like OpenAI, Anthropic, and AWS Bedrock. Pre-built dashboards cover GenAI metrics, vector databases, agent step sequences, and MCP protocol health.

Instrument zero‑code observability for LLMs and agents on Kubernetes

Benefits of zero‑code observability in Grafana Cloud