Introduction on Grafana Labs

Journey overview

Tue, 21 Jul 2026 19:40:13 +0100

Review your outcomes

Use this journey to build a foundation for setup, navigation, querying, dashboarding, and guided learning with Assistant.

Enable Grafana Assistant in Grafana Cloud or connect it to a self-managed Grafana deployment.
Navigate Grafana resources using natural language, without browsing folders.
Generate and explain queries for metrics, logs, traces, and other data sources.
Create and edit dashboards without writing queries from scratch.
Use Learn mode to get guided observability lessons tailored to your environment.

Identify the audience

This journey is for users who want to work with Grafana through natural-language prompts.

Developers who want to query observability data and build dashboards without memorizing PromQL or LogQL.
SREs and platform engineers who need fast access to dashboards and data during incidents.
Anyone new to Grafana who wants a conversational way to explore their observability stack.

Review the journey coverage

The journey follows a short sequence from concepts and setup to common Assistant workflows.

Section	Skills
Introduction	Understand what Assistant is, deployment models, privacy and security.
Get started	Enable Assistant in Grafana Cloud or self-managed Grafana, Learn mode.
Use Grafana Assistant	Navigate resources, query data, manage dashboards, and find next steps.

Plan the journey duration

~30-40 minutes

What is Grafana Assistant?

Tue, 21 Jul 2026 19:40:13 +0100

Define Grafana Assistant

Grafana Assistant is an AI assistant that brings a conversational interface to Grafana. You describe what you need in natural language and the Assistant generates queries, finds dashboards, and explains what your data shows without requiring you to memorize syntax.

Compare deployment models

Assistant is available in two deployment models:

Grafana Cloud: Assistant runs directly in your stack with the full feature set, including infrastructure memory and messaging integrations.
Self-managed Grafana: The Assistant app runs in your own Grafana deployment and connects to a Grafana Cloud backend. Core chat, dashboarding, querying, and navigation workflows are available, but features that require the full Grafana Cloud backend are not.

Compare feature availability

Use this table to compare which core Assistant features are available in Grafana Cloud and self-managed Grafana.

Feature	Grafana Cloud	Self-managed Grafana
Chat and prompts	Yes	Yes
Dashboard creation and editing	Yes	Yes
Query generation and explanation	Yes	Yes
Navigation across Grafana resources	Yes	Yes
Rules, quickstarts, and skills	Yes	Yes
MCP server integrations	Yes	Limited
Infrastructure memory	Yes	No
Slack	Yes	No
Grafana Cloud MCP connections	Yes	No

Limited means self-managed deployments don’t enable every MCP management workflow available in Grafana Cloud.

For more information, refer to Set up Grafana Assistant in self-managed Grafana.

Choose Assistant modes

Assistant includes different modes for different types of work:

Chat: Ask questions, run queries, find dashboards, and create or edit visualizations.
Learn: A guided coaching mode that suggests lessons based on your role and environment. Refer to Use Learn mode for more information.
Modes for dashboarding and k6 script authoring.

Privacy and security

Tue, 21 Jul 2026 19:40:13 +0100

Review how Assistant handles your data

Grafana Assistant processes your prompts and conversation context using third-party AI providers. Requests route through Grafana Cloud and never go directly from your browser to third parties.

Grafana Labs makes three commitments:

Data ownership: You retain ownership of your data.
No training on your data: Grafana Labs never uses your organization’s data to train AI models or for marketing.
No third-party retention: Providers process your prompts without storing or training on them.

Review the providers Assistant uses

Assistant uses different providers depending on the feature and the type of request.

Feature	Providers	Provider data retention	Training on your data
Chat	Anthropic, Google Vertex AI, or Amazon Bedrock	Zero retention	No
Web search (used on demand)	Tavily	Zero-day retention	No

Zero-day retention means Tavily doesn’t retain search terms after the day they’re processed.

Grafana selects the provider based on infrastructure configuration. You can’t choose which provider processes your requests.

Configure RBAC and access controls

The Assistant respects your Grafana permissions. If you don’t have access to a dashboard or data source, the Assistant can’t access it either.

Administrators can use RBAC to control who can open Assistant by scoping plugins.app:access to plugins:id:grafana-assistant-app. Refer to Manage Assistant access with RBAC for instructions.

Review when data leaves your environment

Assistant is not enabled by default. You don’t send data to any AI provider until you actively use an Assistant feature. Enabling the plugin in the Plugins catalog doesn’t send any data.

For full details on data handling, encryption, and access controls, refer to Manage your data privacy and security.