> ## Documentation Index
> Fetch the complete documentation index at: https://www.qovery.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# AI on Qovery

> Three ways to manage your infrastructure with AI from your coding tool, your AI assistant, or the console.

## Three Ways to Use AI with Qovery

<CardGroup cols={3}>
  <Card title="Agent Skills" icon="wand-magic-sparkles" href="/getting-started/quickstart/agent-skills">
    Install Qovery skills directly in your AI coding tool (Claude Code, Cursor, OpenCode). Your agent deploys, troubleshoots, optimizes, and manages infrastructure without leaving your editor.

    **Best for**: developers using AI coding tools
  </Card>

  <Card title="MCP Server" icon="plug" href="/copilot/mcp-server">
    Connect any MCP-compatible AI assistant (Claude Desktop, etc.) to your Qovery infrastructure. Manage environments and services through natural language.

    **Best for**: ops and platform teams using AI assistants
  </Card>

  <Card title="Copilot" icon="robot" href="/copilot/getting-started">
    Built-in agentic AI in the Qovery console and Slack. No setup — just describe what you want and it executes across your infrastructure.

    **Best for**: teams who live in the console or Slack
  </Card>
</CardGroup>

## What Every AI Entry Point Can Do

Regardless of how you connect, all three share the same capabilities:

<CardGroup cols={2}>
  <Card title="Deploy & Manage" icon="rocket">
    Deploy applications, manage environments, scale services, trigger rollbacks.
  </Card>

  <Card title="Troubleshoot" icon="magnifying-glass">
    Analyze logs, diagnose failures, identify root causes, suggest and apply
    fixes.
  </Card>

  <Card title="Optimize" icon="piggy-bank">
    Analyze costs, right-size resources, set up sleep schedules, reduce waste.
  </Card>

  <Card title="Guardrails built in" icon="shield-check">
    Every action respects your RBAC. Agents can't do what users can't do. Full
    audit trail.
  </Card>
</CardGroup>