Introduction to Grafana AI
Grafana AI brings together advanced machine learning, generative AI, and intelligent assistance to help you get more value from your observability data in Grafana Cloud. With features that accelerate investigations, automate analysis, and provide actionable insights, Grafana AI empowers teams to be proactive and efficient—whether you’re troubleshooting incidents, forecasting trends, or building smarter dashboards.
What is Grafana AI?
Grafana AI is a suite of capabilities in Grafana Cloud that leverages both traditional machine learning and the latest advancements in large language models (LLMs).
These features are designed to help you:
- Detect anomalies and outliers in your systems automatically
- Forecast trends and anticipate future states of your infrastructure
- Accelerate incident investigations with AI-powered diagnostics and summaries
- Streamline workflows and reduce manual toil with intelligent assistance
Key features
Grafana Assistant
Grafana Assistant is an agentic LLM integration that provides intelligent, context-aware help directly in the Grafana interface. It can streamline common workflows, answer questions, and help you get the most out of your observability data. Learn more about Grafana Assistant.
Grafana AI Observability
Grafana AI Observability is built on OpenTelemetry and gives teams running LLM agents in production a single place to monitor agent activity, trace conversations, track costs, and evaluate quality. It provides SDKs for Go, Python, TypeScript, Java, and .NET with built-in framework integrations for automatic instrumentation, and a Grafana plugin to browse conversations, drill into traces, and use pre-built dashboards for metrics, logs, traces, and profiles. Learn more about Grafana AI Observability.
Anomaly detection and forecasting
Grafana AI learns from your historical data to identify unusual patterns and predict what’s likely to happen next. Use these insights to set smarter alerts, plan capacity, and stay ahead of potential issues. Learn more about anomaly detection and forecasting.
Sift: AI-powered investigations
Sift is your diagnostic assistant in Grafana Cloud, automatically surfacing potential causes of incidents by analyzing metrics, logs, and traces, so you can resolve problems faster and with greater confidence. Learn more about Sift.
gcx: AI-native CLI
If you’re using as code workflows, the gcx CLI allows you and your AI coding agent structured access to your Grafana stack and resources. For more information refer to the
gcx CLI documentation.
Supported data sources
Grafana Machine Learning (Forecasting and Outlier detection) works with a wide range of data sources:
- Prometheus
- Graphite
- Loki (metric queries only)
- Postgres
- InfluxDB
- Snowflake
- Splunk
- Elasticsearch
- BigQuery
- MongoDB
- Datadog
Why use Grafana AI?
- Accurate forecasting: Learn patterns from historical data to anticipate future states and optimize resources.
- Confidence in predictions: Make informed decisions with clear confidence bounds on forecasts.
- Versatile applications: Apply AI-driven insights to alerting, capacity planning, and anomaly detection.
- Open-source extensibility: Use the open-source LLM app to build and extend LLM-powered features in Grafana.
- AI-powered tools: Leverage features like Sift, incident auto-summary, and generative AI for dashboard metadata to streamline monitoring and incident response.
Explore the rest of the documentation to learn how to enable and use Grafana AI features in your environment.
