Documentationbreadcrumb arrow Grafana Cloudbreadcrumb arrow AI and machine learningbreadcrumb arrow Grafana Assistantbreadcrumb arrow Guidesbreadcrumb arrow Navigate Grafana resources
Grafana Cloud

Navigate Grafana resources

The Assistant acts as a navigator for your Grafana environment. You can use it to find dashboards, discover data sources, and even launch Explore views with pre-loaded queries. This guide covers how to locate resources and coordinate navigation during incidents.

Find dashboards and panels

Instead of browsing folders manually, describe what you need using tags, metric names, or queries.

Search by content

Ask the Assistant to find dashboards based on their content or tags.

Find dashboards tagged “production” that include checkout metrics.

You can also find specific panels by describing the data they visualize.

Locate panels that query rate(http_requests_total[5m]) and share the dashboard links.

Open resources

Once you identify the right resource, you can ask the Assistant to open it directly.

Open the dashboard with UID <DASHBOARD_UID> and switch to edit mode.

Compare results

If multiple dashboards match your request, ask for a comparison to decide which one to use.

Compare the checkout and cart dashboards.

Discover data sources and metrics

When onboarding to a new environment or building queries, use the Assistant to inventory what’s available.

List data sources

Filter data sources by type, name, or environment.

List Prometheus data sources available to me.

List Loki data sources with names containing “prod”.

Explore metrics

Drill into available metrics and labels without leaving the chat.

Search for metrics matching cart.* error rates in @prometheus-ds.

List label values for namespace in @prometheus-ds for the last six hours.

Format findings

Request specific output formats to make inventory lists easier to read or share.

List Prometheus data sources as a markdown table.

Coordinate incident response

During an incident, use the Assistant to direct responders to the right views and tools quickly.

Gather relevant assets

Collect all dashboards and runbooks related to a specific service or problem.

Surface dashboards and runbooks relevant to the checkout latency incident.

Summarize which dashboards and tools we are using for the checkout incident and include links.

Launch tools with context

Direct the Assistant to open Explore with a specific query already loaded, saving setup time for responders.

Open Explore with a LogQL query that filters checkout-service errors in the last 30 minutes.

Next steps