Use Grafana Assistant on Grafana Labs

Navigate Grafana resources

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

Find dashboards and resources

Describe what you need in plain language. Assistant can find dashboards, list data sources, and open Explore with a query already loaded, for example:

Find dashboards tagged “production” that include checkout metrics.

List Prometheus data sources available to me.

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

For more prompts and workflows, refer to Navigate Grafana resources.

Query your data

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

Query data with natural language

Assistant can write, explain, and optimize queries across your observability stack. For every supported data source, the workflow is the same: describe what you want, refine the result, and optionally add the visualization to a dashboard.

Use @ to mention a specific data source in your prompt, for example, @prometheus-ds, so Assistant queries the correct one.

Review supported data sources

Assistant supports natural-language query workflows across your observability stack, including:

Signal	Example data sources	Query language
Metrics	Prometheus	PromQL
Logs	Loki	LogQL
Traces	Tempo	TraceQL

It also supports other sources such as profiles, SQL databases, and cloud provider backends. For the full list, refer to Query data.

Try example prompts

Query metrics

Use metrics prompts when you want Assistant to generate PromQL or refine a metrics query.

Create a PromQL query in @prometheus-ds that shows p95 latency for checkout_service over the last hour.

Group by region and sort by highest error rate.

Query logs

Use logs prompts when you want Assistant to filter, parse, or summarize log data.

Find logs from @loki-logs where job=“checkout” and level=“error” in the last 15 minutes.

Parse the JSON payload and show the top five error codes.

Query traces

Use traces prompts when you want Assistant to find slow traces or summarize trace details.

Query @tempo-traces for traces longer than 2 seconds.

Show the slowest spans and include their service names.

Explain and optimize queries

Use explanation prompts when you already have a query and want to understand or improve it.

Explain what this PromQL query does: rate(http_requests_total{job="api"}[5m])

This query is returning too much data. Help me filter it to only the production namespace.

For more information, refer to Query data.

Manage dashboards

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

Find, create, and edit dashboards

Assistant can find dashboards by meaning (not just exact names), create panels from a plain-language goal, and help you edit what you already have, for example:

Find dashboards related to payment processing latency.

Create a dashboard called ‘Checkout Health’ with panels for error rate, p95 latency, and request volume.

When you edit, open the dashboard or select the panels you want to change so Assistant has the right context.

For panel-menu actions, variables, and more examples, refer to Manage dashboards.

Resources and next steps

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

Continue with Grafana Assistant

Use these topics to build on the Assistant workflows covered in this guide.

Topic	Description	Where to start
Learn mode	Get guided observability lessons tailored to your role and environment.	Use Learn mode
Alerting	Use Assistant to create and manage alerting rules.	Alerting with Assistant
Infrastructure memory	Automatically build context about your services to speed up troubleshooting.	Use infrastructure memory
Slack	Use Assistant from Slack without opening Grafana.	Slack
Extend with SDKs	Integrate Assistant into plugins and external applications.	TypeScript SDK

Read documentation

Refer to these docs for setup, configuration, and product details.

Join the community

Use these community resources to ask questions and learn how other teams use Grafana.