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

# Quickstart

> Get up and running with Duckie in 10 minutes

This guide walks you through setting up your first Duckie agent and deploying it to handle customer conversations. By the end, you'll have an AI agent responding to messages in your support channel.

## Prerequisites

Before you begin, make sure you have:

* A Duckie account ([sign up here](https://app.useduckie.ai/login) or [book a demo](https://calendly.com/valerie-li-duckie/meet))
* Admin access to at least one support channel (Zendesk, Intercom, Slack, etc.)
* Some documentation or help content for your agent to reference

## Step 1: Connect Your Support Channel

First, connect the platform where you want Duckie to respond to customers.

<Steps>
  <Step title="Go to Connections">
    Navigate to **Settings → Connections** in your Duckie dashboard.
  </Step>

  <Step title="Find Your Platform">
    Browse by category (Ticketing, Messaging) or search for your platform.
  </Step>

  <Step title="Click Connect">
    Click **Connect** and complete the OAuth authorization flow.
  </Step>
</Steps>

{/* Screenshot: Connections page showing integration cards with categories */}

<Info>
  **Popular starting points:**

  * **Zendesk** — Respond to support tickets
  * **Intercom** — Handle chat conversations
  * **Slack** — Answer questions in shared channels
</Info>

For detailed setup instructions, see our [integration guides](/integrations/overview).

## Step 2: Add Knowledge

Give your agent information to work with by connecting your documentation.

<Steps>
  <Step title="Go to Knowledge">
    Navigate to **Train → Knowledge** in your dashboard.
  </Step>

  <Step title="Connect a Source">
    Click **Add Source** and connect your documentation platform (Notion, Confluence, Google Drive) or add a website URL.
  </Step>

  <Step title="Wait for Sync">
    Duckie will index your content. This usually takes 2-5 minutes depending on volume.
  </Step>
</Steps>

{/* Screenshot: Knowledge page showing connected sources and sync status */}

<Tip>
  **Quick start option:** If you don't have documentation ready, you can create a few [custom knowledge articles](/knowledge/custom-knowledge) directly in Duckie to get started.
</Tip>

## Step 3: Create Your Agent

Now create the AI agent that will handle conversations.

<Steps>
  <Step title="Go to Agents">
    Navigate to **Build → Agents** and click **Create Agent**.
  </Step>

  <Step title="Name Your Agent">
    Give it a descriptive name like "Support Agent" or "Help Desk Bot".
  </Step>

  <Step title="Choose Autonomous Mode">
    Select **Autonomous** so the agent can decide which knowledge, runbooks, workflows, and tools to use.
  </Step>

  <Step title="Write Instructions">
    Describe what the agent should handle, when it should research, and when it should escalate.
  </Step>

  <Step title="Configure Knowledge">
    Leave **Knowledge Tags** empty to let the agent access all connected knowledge, or select tags to narrow its scope.
  </Step>

  <Step title="Save">
    Click **Create** to save your agent.
  </Step>
</Steps>

{/* Screenshot: Create agent dialog/drawer with autonomous mode, instructions, and knowledge tags */}

## Step 4: Test in the Playground

Before deploying to real customers, test your agent in the playground.

<Steps>
  <Step title="Open Playground">
    Navigate to **Test → Playground**.
  </Step>

  <Step title="Select Your Agent">
    Choose the agent you just created from the dropdown.
  </Step>

  <Step title="Send Test Messages">
    Ask questions your customers would ask. Try:

    * "How do I reset my password?"
    * "What's your refund policy?"
    * "I'm having trouble logging in"
  </Step>

  <Step title="Review Responses">
    Check that responses are accurate and helpful. Click on any response to see the execution details.
  </Step>
</Steps>

{/* Screenshot: Playground showing a conversation with execution steps panel expanded */}

<Tip>
  **Iterate here:** If responses aren't quite right, adjust your agent's knowledge or guidelines before deploying. The playground is your safe space to experiment.
</Tip>

## Step 5: Deploy to Your Channel

Once you're happy with playground results, deploy your agent to handle real conversations.

<Steps>
  <Step title="Go to Deploy">
    Navigate to **Deploy** and click **Create Deployment**.
  </Step>

  <Step title="Select Your Agent">
    Choose the agent you created and tested.
  </Step>

  <Step title="Configure Trigger">
    Select your connected channel and the events that should trigger the agent (e.g., "New ticket created", "Message received").
  </Step>

  <Step title="Start in Testing Mode">
    Select **Testing** mode to review behavior before switching to live customer responses.
  </Step>

  <Step title="Activate">
    Click **Create** and set the deployment to **Active**.
  </Step>
</Steps>

{/* Screenshot: Create deployment dialog showing agent selection, trigger configuration, and mode selection */}

<Warning>
  **We recommend starting in Testing mode.** Testing mode lets you review behavior and reduce risk before switching to live customer responses.
</Warning>

## Step 6: Go Live

After reviewing test runs and confirming quality:

1. Go to **Deploy**
2. Click on your deployment
3. Change mode from **Testing** to **Live**
4. Save

Your agent is now responding to customers!

## What's Next?

<CardGroup cols={2}>
  <Card title="Add Guidelines" icon="list-check" href="/guidelines/overview">
    Shape your agent's tone and communication style
  </Card>

  <Card title="Set Up Guardrails" icon="shield" href="/guardrails/overview">
    Define escalation rules and restrictions
  </Card>

  <Card title="Monitor Performance" icon="chart-line" href="/analytics/overview">
    Track metrics and view run history
  </Card>

  <Card title="Explore Integrations" icon="plug" href="/integrations/supported-integrations">
    Connect more tools and channels
  </Card>
</CardGroup>

## Need Help?

* **Documentation** — You're in the right place! Use the sidebar to explore.
* **Community** — Join our [Discord](https://discord.gg/duckie) to ask questions and share tips.
* **Support** — Email [founders@duckie.ai](mailto:founders@duckie.ai) for direct assistance.