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

# Talk to your infrastructure

> Ask your infrastructure questions in plain English. Chat is RubixKube's conversational gateway, backed by the SRI Agent and the whole Agent Mesh.

Chat is RubixKube's conversational surface. No `kubectl` memorisation, no grepping logs, no clicking through five dashboards. Ask the question you would ask a senior engineer, get a cited answer backed by the Agent Mesh.

This tutorial set takes you from first query to daily driver. Start at Basics if you are new, skip ahead if you are not.

## Why Chat

<CardGroup cols={3}>
  <Card title="Natural language" icon="message">
    Plain English. No query language to learn.
  </Card>

  <Card title="Answers with evidence" icon="file-magnifying-glass">
    Every claim cites the underlying signal. Verify in one click.
  </Card>

  <Card title="Context aware" icon="link">
    The session remembers the thread. Follow-ups do not start from scratch.
  </Card>

  <Card title="Multi-agent backend" icon="robot">
    Observer, RCA Pipeline, Memory, and Guardian all feed the answer.
  </Card>

  <Card title="Works across environments" icon="server">
    Same prompts work for Kubernetes, AWS, GCP, and VMs in one workspace.
  </Card>

  <Card title="Runs skills on demand" icon="sparkles">
    Invoke any enabled skill with a slash command or by intent.
  </Card>
</CardGroup>

## The difference, in two lines

The old way on Kubernetes:

```bash theme={null}
kubectl get pods -n production
kubectl describe pod api-gateway-xyz
kubectl logs api-gateway-xyz
kubectl top pod api-gateway-xyz
# five more commands, then stitch it together in your head
```

The Chat way:

```
Why is api-gateway slow in production?
```

One cited answer, no context-switching. The same prompt works whether `api-gateway` is a Kubernetes pod, an ECS task, a GCE instance, or a process on a VM.

## The tutorial series

<CardGroup cols={2}>
  <Card title="Chat Basics" icon="comments" href="/tutorials/chat-basics">
    Open the interface, type your first query, read the response. About ten minutes.
  </Card>

  <Card title="Troubleshooting with Chat" icon="wrench" href="/tutorials/chat-troubleshooting">
    Real debug flows: OOMKilled, ImagePullBackOff, CrashLoopBackOff, latency spikes. About fifteen minutes.
  </Card>

  <Card title="Advanced Chat" icon="star" href="/tutorials/chat-advanced">
    Role-shaped workflows for SREs, DevOps, and platform engineers. About twenty minutes.
  </Card>

  <Card title="Chat for cost analysis" icon="chart-line" href="/tutorials/chat-cost-analysis">
    Rightsizing, anomaly hunting, weekly budget reviews, all through Chat. About fifteen minutes.
  </Card>
</CardGroup>

## The four prompt shapes that work

<AccordionGroup>
  <Accordion title="Health checks" icon="heart-pulse">
    Use for the daily read.

    ```
    What is the health of every production environment?
    Which workloads are degraded right now?
    Any hosts above 80% memory in the last hour?
    ```
  </Accordion>

  <Accordion title="Change correlation" icon="timeline">
    Use when something just broke.

    ```
    What changed in the checkout service in the last hour?
    Which deployments rolled back in the last 24 hours?
    Show me configuration drifts on prod-cluster-us-east this week.
    ```
  </Accordion>

  <Accordion title="Investigation" icon="magnifying-glass">
    Use to pull a specific slice for a deep dive.

    ```
    Why is the payments API slow in ap-south-1?
    Which pods restarted most in the last 24 hours, grouped by namespace?
    Top five CPU consumers on host-42 in the last hour.
    ```
  </Accordion>

  <Accordion title="Cost and capacity" icon="chart-line">
    Use for weekly rightsizing.

    ```
    Which services have the most headroom on CPU limits?
    RDS instances with the lowest average utilisation this month.
    GCE instances over-provisioned on memory, sorted by spend.
    ```
  </Accordion>
</AccordionGroup>

## Slash commands worth knowing

The slash menu shows up when you type `/` in the chat box.

| Command         | Purpose                                                     |
| --------------- | ----------------------------------------------------------- |
| `/environments` | Switch which environment the next question runs against     |
| `/new`          | Start a fresh session when the context gets muddy           |
| `/resume`       | Pick up an earlier investigation where you left off         |
| `/rename`       | Name the session so you can find it later                   |
| `/send`         | Push the last shell output into chat                        |
| `/skills`       | Invoke a saved skill (runbook) against the current question |

## Where to start

<Tabs>
  <Tab title="New to Chat">
    Work through the series in order:

    1. [Chat Basics](/tutorials/chat-basics), ten minutes.
    2. [Troubleshooting with Chat](/tutorials/chat-troubleshooting), fifteen minutes.
    3. [Advanced Chat](/tutorials/chat-advanced), twenty minutes.
    4. [Chat for cost analysis](/tutorials/chat-cost-analysis), fifteen minutes.

    About an hour, end to end, with one real cluster.
  </Tab>

  <Tab title="Already using Chat">
    Skip to the guide that matches your current need.

    * Troubleshooting a live incident: [Troubleshooting with Chat](/tutorials/chat-troubleshooting).
    * Daily workflow for your role: [Advanced Chat](/tutorials/chat-advanced).
    * Quarterly cost review: [Chat for cost analysis](/tutorials/chat-cost-analysis).
  </Tab>

  <Tab title="Specific question">
    * Debugging a failing pod: [Troubleshooting with Chat](/tutorials/chat-troubleshooting).
    * Building a daily health check routine: [Advanced Chat](/tutorials/chat-advanced).
    * Wasted spend on over-provisioned resources: [Chat for cost analysis](/tutorials/chat-cost-analysis).
  </Tab>
</Tabs>

## Quick reference

Five prompts that cover most of daily use:

1. `What is failing?` - morning triage.
2. `Why is <service> slow?` - focused investigation.
3. `What changed in <namespace> in the last hour?` - post-deploy check.
4. `Validate this` (with YAML uploaded) - pre-deploy safety.
5. `Explain <concept>` - learn a Kubernetes or AWS concept using your own resources as examples.

Fastest way to open Chat: `⌘K` in the console, or `rubix` in your terminal.

## Common questions

<AccordionGroup>
  <Accordion title="Does Chat work across environments?">
    Yes. The same prompts work for Kubernetes, AWS, GCP, and Linux VMs. Use `/environments` to scope to one, or ask broadly and Chat will include every environment in the workspace.
  </Accordion>

  <Accordion title="Where does Chat run?">
    The SRI Agent that powers Chat runs in RubixKube Cloud. The Observer in your environment provides signals. Raw logs stay with you unless you explicitly enable broader streaming.
  </Accordion>

  <Accordion title="Can Chat apply changes to my infrastructure?">
    Chat can recommend and draft changes. Applying anything requires explicit approval and is bounded by Guardian policies. See [How to Automate Incident Remediation](/tutorials/automate-incident-remediation).
  </Accordion>

  <Accordion title="Is there a terminal version?">
    Yes. Install with `npm install -g @rubixkube/rubix`, launch with `rubix`. Same agent, same skills, terminal-native UX.
  </Accordion>
</AccordionGroup>

## Related guides

<CardGroup cols={2}>
  <Card title="How to add custom agent skills" icon="sparkles" href="/tutorials/add-custom-agent-skills">
    Turn your best prompts into reusable skills.
  </Card>

  <Card title="How to Monitor Infrastructure Health" icon="heart-pulse" href="/tutorials/monitor-infrastructure-health">
    Dashboard-first view of the same data.
  </Card>
</CardGroup>