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

# Quickstart

> Connect your data, build your first agent, and run your first analysis in under 10 minutes.

## Prerequisites

Before you begin, make sure you have:

* Access to a **Turntwo Interact** workspace (if you don't have one, contact your Turntwo account manager)
* A **Google BigQuery** project with at least one dataset you want to analyse
* A BigQuery **service account** with the `BigQuery Data Viewer` and `BigQuery Job User` roles

<Note>
  If your organisation already has a connector set up, you can skip Step 1 and go straight to building your agent.
</Note>

## Step 1: Connect your BigQuery data

<Steps>
  <Step title="Open Connectors in Settings">
    In the left sidebar, go to **Settings** → **Connectors** and click **Add connector**.
  </Step>

  <Step title="Choose Google BigQuery">
    Select **Google BigQuery** from the list of available data sources.
  </Step>

  <Step title="Upload your service account credentials">
    Paste in your service account JSON credentials and enter your **Google Cloud Project ID**.

    <Tip>
      Your credentials are encrypted at rest using Google Cloud KMS — they are never stored in plain text.
    </Tip>
  </Step>

  <Step title="Select datasets to expose">
    Choose which BigQuery datasets your agents are allowed to query. You can whitelist specific tables if needed.
  </Step>

  <Step title="Save and test the connection">
    Click **Save connector**. Interact will verify the connection and list the accessible tables.
  </Step>
</Steps>

<Card title="Full BigQuery setup guide" icon="database" href="/org-settings/connectors/google-big-query">
  Detailed instructions including IAM permissions, dataset whitelisting, and query cost limits.
</Card>

## Step 2: Build your first agent

<Steps>
  <Step title="Go to Agents">
    From the sidebar, click **Agents** and then **Create agent**.
  </Step>

  <Step title="Give your agent a name and description">
    Use something descriptive like *"Campaign Performance Analyst"*. The description helps the agent understand its purpose.
  </Step>

  <Step title="Add your connector">
    In the **Subagents** section, add a **Database Query Agent** and attach the BigQuery connector you just created.
  </Step>

  <Step title="Add context (optional)">
    In the **Organisation context** field, describe your data model in plain language — for example:

    > "The `events` table tracks ad impressions and clicks. The `campaigns` table contains campaign metadata including budget and flight dates."

    This helps the agent write accurate queries without needing to be corrected.
  </Step>

  <Step title="Save your agent">
    Click **Save**. Your agent is ready to use.
  </Step>
</Steps>

<Card title="Learn more about agents" icon="robot" href="/agents/building-agents">
  Full guide to configuring orchestrators, subagents, model selection, and tools.
</Card>

## Step 3: Run your first analysis

<Steps>
  <Step title="Open the agent chat">
    Click on your newly created agent to open the chat interface.
  </Step>

  <Step title="Ask a question in plain language">
    Type a question about your data. For example:

    > "How many impressions did each campaign get last week?"

    The agent will translate your question into a SQL query, run it against BigQuery, and return the results.
  </Step>

  <Step title="Explore the results">
    Results appear as a **table** or **chart** directly in the chat. You can ask follow-up questions or refine your analysis:

    > "Can you break that down by device type and show it as a bar chart?"
  </Step>
</Steps>

## What's next?

<CardGroup cols={2}>
  <Card title="Schedule a job" icon="clock" href="/agents/jobs-scheduling">
    Automate your analysis to run on a daily, weekly, or custom schedule.
  </Card>

  <Card title="Set up notifications" icon="bell" href="/org-settings/notifications/setting-up-channels">
    Get Slack or email alerts when your agent finishes a run.
  </Card>

  <Card title="Build a report" icon="chart-bar" href="/reports/overview">
    Create structured, repeatable reports from your agent's output.
  </Card>

  <Card title="Use the API" icon="code" href="/api-reference/quickstart">
    Trigger agent runs programmatically from your own systems.
  </Card>
</CardGroup>