---
title: "Configure Assistant rules | Grafana Cloud documentation"
description: "Configure custom rules to guide how Grafana Assistant responds and behaves in every conversation."
---

> For a curated documentation index, see [llms.txt](/llms.txt). For the complete documentation index, see [llms-full.txt](/llms-full.txt).

# Configure Assistant rules

Custom rules guide how Grafana Assistant responds and behaves. Rules are automatically applied to every conversation and can target specific applications. Due to the indeterministic nature of LLMs, there’s no guarantee they are followed exactly as specified, but they strongly influence the Assistant’s output and decision-making.

You can create rules in **Settings > Custom rules** and apply them to specific scopes:

- **Just me**: Rules apply only to your own conversations.
- **Everybody**: Rules apply to everyone in your stack (requires admin permissions).

## Create a rule

1. Navigate to **Assistant > Settings > Custom rules**.
2. Click **Create rule**.
3. Enter a rule **Name** and **content**.
4. Choose the **Scope**: **Just me** or **Everybody**.
5. Select the **Applications** the rule applies to (for example, `Assistant`, `Loop`, or `Infrastructure Memory`).
6. Click **Create rule**.

The Assistant applies your rule automatically in new conversations.

## Rule examples

Use these examples as starting points for your own rules.

### Infra and app hints

Guide the Assistant to use specifics relevant to your environment:

> When discussing CPU metrics, use `container_cpu_usage_seconds_total` instead of generic CPU references. Reference our custom `service_health_score` metric for overall service status. Prefer the `prometheus_prod` datasource when investigating issues in production.

### Communication style

Define how the Assistant formats and structures responses:

> Always be concise and direct in responses. Use bullet points for actionable recommendations. Avoid jargon unless specifically discussing technical implementation.

### Best practices

Encode organizational standards and observability methodologies:

> Use the RED method (Rate, Errors, Duration) wherever possible. Always recommend setting up SLIs before creating SLOs. Suggest using template variables for dynamic dashboards.

### Workflow guidelines

Automate operational recommendations based on specific triggers:

> Suggest declaring an incident if the ecommerce platform response time exceeds 5 seconds. Recommend escalating to the infrastructure team for persistent memory issues. Always ask about recent deployments when troubleshooting performance issues.

## Related features

While Rules provide general behavioral context, other features offer more structured guidance:

- [**Skills**](/docs/grafana-cloud/machine-learning/assistant/guides/skills): Create step-by-step troubleshooting guides for specific alerts or scenarios. Skills are triggered by specific events, whereas Rules apply generally to conversations.
- [**MCP Servers**](/docs/grafana-cloud/machine-learning/assistant/configure/mcp-servers): Extend the Assistant’s capabilities by connecting to external tools and data sources.