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

# Your First Session

> Walk through your first MIRA session — from connecting a provider to getting a reasoned answer.

This guide walks you through setting up MIRA for the first time and running your first query with a concrete example at each step.

## Before you start

Make sure MIRA is installed and the status bar shows **NAE ready**. If it shows `Initializing`, wait for the one-time setup to complete (\~60 s).

If it shows `Failed`, see [Engine Settings](/configuration/nae-settings) to diagnose.

## Step 1 — Connect a provider

Open **Settings** (⌘, on macOS / Ctrl+, on Windows/Linux).

<Tabs>
  <Tab title="AWS Bedrock">
    Click the **Bedrock / AWS** tab and enter your credentials:

    | Field             | Example                    |
    | ----------------- | -------------------------- |
    | Access Key ID     | `AKIA...`                  |
    | Secret Access Key | `wJalr...` (shown as ●●●●) |
    | Region            | `eu-west-1`                |

    Click **Test Connection**. On success, MIRA displays your AWS Account ID and IAM ARN — confirming credentials are valid and the Bedrock API is reachable.

    <Info>
      Credentials are stored in your OS keychain (macOS Keychain / Windows Credential Manager /
      libsecret). They are never written to disk or log files.
    </Info>
  </Tab>

  <Tab title="Anthropic or OpenAI">
    Click the **API Tokens** tab → **Add Token**.

    * Label: `ANTHROPIC_API_KEY` or `OPENAI_API_KEY`
    * Value: your key from [console.anthropic.com](https://console.anthropic.com) or [platform.openai.com](https://platform.openai.com)

    Click **Save**. The token count badge updates to `1 token configured`.
  </Tab>

  <Tab title="Ollama">
    1. Install and start [Ollama](https://ollama.com): `ollama pull llama3`
    2. In **Settings → Engine**, set the provider to `ollama` and confirm the base URL is `http://localhost:11434`
    3. No API key required

    All inference runs on your machine — no outbound calls.
  </Tab>
</Tabs>

Click **Save** and close Settings.

## Step 2 — Choose your engine

The engine selector is in **Settings → Engine**. Two cards are shown:

* **Native Agent Engine** (default) — multi-agent orchestration, adaptive memory. Best for open-ended questions, long sessions, and multi-domain reasoning.
* **RLM Engine** — code-executing recursive reasoner. Best for data analysis, calculations, and tasks where a verified answer matters most.

For your first session, leave it on **Native Agent Engine**.

## Step 3 — Start a chat

1. Click **New Chat** (⌘N) in the sidebar
2. An empty chat window opens
3. Type a question. For example:

```
Summarise the key differences between transformer and state space models,
focusing on their computational complexity and what kinds of tasks each
architecture is best suited for.
```

4. Press **Enter** (or click the send button)

Watch MIRA think in real time. You'll see:

* A streaming response appearing token by token
* A status update in the Activity Center (⌘4) showing the query is in flight
* The session title auto-generated from your question

## Step 4 — Upload a document (optional)

Click the **Paperclip** icon in the message input toolbar (or press **⌘D**) to open the Document Panel on the right side of the chat window.

1. Drag and drop a PDF, DOCX, CSV, or text file onto the panel — or click **Upload**
2. Wait for the status to change from `Parsing` to `Ready`
3. The document is now automatically included in your next query

Ask a follow-up question about the document's contents:

```
Based on the uploaded document, what are the three most important points?
```

MIRA injects the document content into the reasoning context automatically.

## Step 5 — Explore the views

Use the icon bar on the left to navigate:

| View      | Shortcut | What's there                                                           |
| --------- | -------- | ---------------------------------------------------------------------- |
| Chat      | ⌘1       | Your conversation                                                      |
| Skills    | ⌘2       | Reasoning personas — try applying "Financial Analyst" to a new session |
| Workflows | ⌘3       | Multi-step pipelines — try "Research Report Pipeline"                  |
| Activity  | ⌘4       | Real-time in-flight query monitor                                      |
| Evals     | ⌘5       | Evaluation framework for systematic quality tracking                   |

## What's next?

<CardGroup cols={2}>
  <Card title="Apply a Skill" icon="wand" href="/features/skills/built-in-skills">
    Five built-in domain experts ready to use
  </Card>

  <Card title="Run the Research Pipeline" icon="git-branch" href="/features/workflows/built-in-workflows">
    Multi-step research → analysis → report
  </Card>

  <Card title="Add an MCP Tool" icon="plug" href="/features/mcp-tools/what-is-mcp">
    Connect web search, databases, or custom APIs
  </Card>

  <Card title="Open the REPL Console" icon="terminal" href="/features/repl-console">
    See every reasoning step in real time
  </Card>
</CardGroup>