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

# Chat Agents

> Build and deploy AI chat agents across multiple messaging platforms

## Overview

Chat agents handle every written channel—Instagram DMs, Facebook Messenger, web-chat widgets, SMS, WhatsApp, and email. This guide walks you through creating, configuring, and testing them so they feel every bit as polished as your voice agents.

***

## Create an Agent

### Step 1: Access Chat Agents

Navigate to the **Agents** tab in your Outbox AI dashboard.

<Frame>
  <img src="https://mintcdn.com/outboxsolutions/jQ0LoSOOg35Qyr-K/images/chat-agents-dashboard.png?fit=max&auto=format&n=jQ0LoSOOg35Qyr-K&q=85&s=4ecefb26c7cd4b1fe4ada937f524d408" alt="Chat Agents Dashboard" width="486" height="594" data-path="images/chat-agents-dashboard.png" />
</Frame>

### Step 2: Create New Agent

Click **New Agent** or open an existing one from the list.

<Frame>
  <img src="https://mintcdn.com/outboxsolutions/jQ0LoSOOg35Qyr-K/images/prompting-create-agent-description.png?fit=max&auto=format&n=jQ0LoSOOg35Qyr-K&q=85&s=fd642d45b5e51aea7d72d86f01455c92" alt="Create New Chat Agent" width="1262" height="1380" data-path="images/prompting-create-agent-description.png" />
</Frame>

<Tip>
  **AI-Powered Prompt Generation:** If you enter a description of the agent in
  the "Create Agent" modal, Outbox AI will automatically generate a professional
  prompt for you!
</Tip>

***

## Write the Prompt

The prompt is the brain of your chat agent. In the large text box, you'll define how your agent behaves.

<Frame>
  <img src="https://mintcdn.com/outboxsolutions/fF9oh0K1x8Orod4R/images/voice-core-prompt-settings.png?fit=max&auto=format&n=fF9oh0K1x8Orod4R&q=85&s=ba80a989b4e351e1e5f6e4e071c460f4" alt="Chat Agent Prompt Editor" width="1206" height="1238" data-path="images/voice-core-prompt-settings.png" />
</Frame>

<Note>
  **Current time:** Chat agents always receive the current time in context—you
  do not need a separate tool to know “what time it is” for scheduling or
  messaging.
</Note>

### What to Include:

1. **Agent's Role** – Who is the agent? (e.g., "You are a friendly customer service representative for XYZ Company")
2. **Tone & Personality** – Formal, casual, enthusiastic, empathetic, etc.
3. **Goals** – What should the agent accomplish? (qualify leads, book appointments, answer FAQs)
4. **Tool Usage Instructions** – Explicitly tell the agent when to use tools:

```
When a customer wants to book an appointment, call the book_appointment tool.
When you need to check inventory, use the check_stock tool.
```

<Note>
  **Don't forget to save!** Click the **Save** button to apply your changes.
  Once saved, the agent updates in real-time.
</Note>

***

## Automatic Follow-Up Prompt

Use the **Follow Up Prompt** field to tell the chat agent how and when to
**automatically follow up with the contact later** if the conversation goes
quiet, without you writing each message by hand.

**Examples:**

* “If the user doesn’t reply, send a friendly check-in after 3 hours, then again after 6 hours if they still haven’t responded.”
* “After sending a quote, remind them once in 24 hours if they haven’t booked.”

The agent uses this instruction together with your main prompt, so keep it
specific about timing, tone, and what to say (or not say) on each nudge.

***

## Attach Tools

Tools give your chat agent superpowers—the ability to book appointments, send data to external systems, fetch real-time information, and more.

<Note>
  **Postrun (voice calls):** On **voice** agents, tools support a **Postrun** flag so a tool can run **after the call ends** with the **transcript** as context instead of during the live call. Chat agents use tools in the conversation thread as usual; see [Voice Agents](/voice-agents#postrun) for Postrun behavior.
</Note>

<AccordionGroup>
  <Accordion title="Custom URL" icon="link">
    Call any webhook to integrate with Zapier, Make, or your own custom API.

    **Configuration:**

    1. Enter the webhook URL
    2. Define the request method (GET, POST, PUT, DELETE)
    3. Add any required headers or parameters
    4. Map the response data to variables

    <Frame>
      <img src="https://mintcdn.com/outboxsolutions/jQ0LoSOOg35Qyr-K/images/chat-tool-custom-url.png?fit=max&auto=format&n=jQ0LoSOOg35Qyr-K&q=85&s=19243737cee5904c8f0f06c234ae2acd" alt="Custom URL Tool" width="1862" height="1600" data-path="images/chat-tool-custom-url.png" />
    </Frame>

    **Use Cases:**

    * Send lead data to your CRM
    * Trigger automations in Zapier or Make
    * Connect to third-party APIs
    * Update external databases
  </Accordion>

  <Accordion title="Tool Library" icon="books">
    Pick from ready-made tools that handle common tasks.

    **Available Tools:**

    **Cal.com Integration:**

    * **Cancel or Reschedule Booking** – Cancel or reschedule a booking made in Cal.com
    * **Fetch Free Slots** – Fetch free slots between two dates for a specific event type
    * **Get User Bookings** – Get a list of bookings for a specific user so you can reschedule or cancel it

    **GoHighLevel Integration:**

    * **Cancel or Reschedule Appointment** – Cancel or reschedule a specific appointment to a later date
    * **Fetch Free Slots** – Fetch a list of free slots for a calendar within a specific time range
    * **Find Or Create Contact** – Find or create a contact to use for appointment booking and other functions
    * **Get Booked Appointments** – Retrieve a list of booked appointments for a contact

    **Popular Tools:**

    * **Book AI Callback** – Allow agents to call users back at a later time
    * **Create Opportunity** – Create a pipeline opportunity from the conversation
    * **Update Opportunity** – Move or update an existing opportunity (e.g. stage)
    * **Send SendGrid Email** – Integrate SendGrid to send emails directly from your agent
    * **Send Twilio SMS** – Integrate Twilio to send text messages directly from your agent
    * **Solar Savings (US Only)** – Calculate estimated savings of switching to solar based on monthly bill and address

    <Frame>
      <img src="https://mintcdn.com/outboxsolutions/jQ0LoSOOg35Qyr-K/images/chat-tool-library.png?fit=max&auto=format&n=jQ0LoSOOg35Qyr-K&q=85&s=6be0535505fcd675e9b56ec042739814" alt="Tool Library" width="1880" height="1198" data-path="images/chat-tool-library.png" />
    </Frame>

    <Tip>
      The tool library is constantly growing. Check back regularly for new additions!
    </Tip>
  </Accordion>

  <Accordion title="MCP Server" icon="server">
    Connect to Model Context Protocol (MCP) servers for advanced integrations with thousands of apps and services.

    **Two Setup Options:**

    When you choose the MCP Server tool type, you'll be prompted with two options:

    **Option 1: Custom MCP Server**
    Connect to your own custom MCP server (like Zapier MCP). Perfect for advanced users who want full control over their integrations.

    **Option 2: Preset MCP Applications**
    Choose from our curated list of preset MCP application servers. Quick setup with popular applications like Gmail, Google Sheets, Slack, and more.

    **Using Preset MCP Applications:**

    <Steps>
      <Step title="1. Select an Application">
        Choose an application from the preset MCP Application list (e.g., Gmail, Google Sheets, Slack, HubSpot, Salesforce, Airtable).
      </Step>

      <Step title="2. Authenticate Your Account">
        Connect and authenticate your account with the selected application. Outbox AI will guide you through the OAuth flow.
      </Step>

      <Step title="3. Choose Specific Tools">
        Select which specific tools from the application you want your agent to have access to. You have granular control over permissions.

        **Example:** For Gmail, you can give your agent access to:

        * ✅ Create draft emails
        * ❌ Send emails
        * ❌ Read emails

        This allows you to control exactly what actions your agent can perform.
      </Step>

      <Step title="4. Agent Can Use Tools">
        Once configured, your agent can perform the selected tasks through the MCP server during conversations.
      </Step>
    </Steps>

    **Using Custom MCP Server (Zapier):**

    <Steps>
      <Step title="1. Visit Zapier MCP">
        Go to [mcp.zapier.com](https://mcp.zapier.com) and sign in with your Zapier account.
      </Step>

      <Step title="2. Create New MCP Server">
        Click **"Create New MCP Server"** and select **"Other"** as the MCP Client type.

        <Frame>
          <img src="https://mintcdn.com/outboxsolutions/rDFm6_ZozUWohQ56/images/mcp-create-server.png?fit=max&auto=format&n=rDFm6_ZozUWohQ56&q=85&s=d0e5a6432d799173a4a868eb52b013f5" alt="Create MCP Server" width="1270" height="868" data-path="images/mcp-create-server.png" />
        </Frame>
      </Step>

      <Step title="3. Add Tools from 8,000+ Apps">
        Browse and select tools from Zapier's extensive app library. Popular options include:

        * **Google Sheets** – Search, create, and update spreadsheets
        * **Gmail** – Send emails and manage inbox
        * **Slack** – Send messages and create channels
        * **HubSpot** – Manage contacts and deals
        * **Salesforce** – Update records and create tasks
        * **Airtable** – Query and update databases
      </Step>

      <Step title="4. Connect Your Apps">
        Authenticate with the apps you want to use. Zapier will guide you through OAuth flows for each service.

        <Frame>
          <img src="https://mintcdn.com/outboxsolutions/rDFm6_ZozUWohQ56/images/mcp-select-tools.png?fit=max&auto=format&n=rDFm6_ZozUWohQ56&q=85&s=8d64d71a3885438fd981857eb770a75a" alt="Select MCP Tools" width="1790" height="1526" data-path="images/mcp-select-tools.png" />
        </Frame>
      </Step>

      <Step title="5. Get Server URL">
        Once configured, click **"Connect"** and copy the MCP server URL.

        <Frame>
          <img src="https://mintcdn.com/outboxsolutions/rDFm6_ZozUWohQ56/images/mcp-server-url.png?fit=max&auto=format&n=rDFm6_ZozUWohQ56&q=85&s=f4231f00f075b109bdba013c3911fb06" alt="Copy MCP Server URL" width="1606" height="1126" data-path="images/mcp-server-url.png" />
        </Frame>
      </Step>

      <Step title="6. Add to Outbox AI">
        Select **"Custom MCP Server"** and paste the server URL into the MCP Server field in your chat agent settings.

        <Frame>
          <img src="https://mintcdn.com/outboxsolutions/jQ0LoSOOg35Qyr-K/images/chat-tool-mcp-server.png?fit=max&auto=format&n=jQ0LoSOOg35Qyr-K&q=85&s=e3e528e72f23549a3bb060b6b7b255c7" alt="MCP Server in Outbox" width="1768" height="1270" data-path="images/chat-tool-mcp-server.png" />
        </Frame>
      </Step>

      <Step title="7. Select Specific Tools">
        Choose which tools from your MCP server to make available to your chat agent.

        <Frame>
          <img src="https://mintcdn.com/outboxsolutions/rDFm6_ZozUWohQ56/images/mcp-select-agent-tools.png?fit=max&auto=format&n=rDFm6_ZozUWohQ56&q=85&s=e0286d1f72906950ec3ba19878edc713" alt="Select Tools for Agent" width="1880" height="686" data-path="images/mcp-select-agent-tools.png" />
        </Frame>
      </Step>
    </Steps>

    **Example Use Cases:**

    <AccordionGroup>
      <Accordion title="Google Sheets Integration" icon="table">
        **Search customer data during conversations:**

        * Look up customer information from spreadsheets
        * Update appointment bookings in real-time
        * Track conversation outcomes and lead quality
      </Accordion>

      <Accordion title="CRM Integration" icon="address-book">
        **Update customer records:**

        * Create new contacts during conversations
        * Update deal stages based on chat interactions
        * Add conversation notes and follow-up tasks
      </Accordion>

      <Accordion title="Communication Tools" icon="envelope">
        **Send follow-up messages:**

        * Email appointment confirmations
        * Send Slack notifications to team
        * Create tasks in project management tools
      </Accordion>
    </AccordionGroup>

    **Advanced Features:**

    * **Real-time Data Access** – Query live data during conversations
    * **Multi-app Workflows** – Chain actions across different services
    * **Custom Authentication** – Secure access to your business tools
    * **Error Handling** – Graceful fallbacks when tools fail

    <Tip>
      **Pro Tip:** Start with 2-3 essential tools and gradually add more as you become comfortable with MCP integration. Too many tools can slow down response times.
    </Tip>

    <Note>
      MCP servers provide a standardized way for AI agents to interact with external tools and data sources. With preset MCP applications, you can quickly connect popular services with granular tool selection. For advanced integrations, custom MCP servers like Zapier give you access to 8,000+ apps without custom development.
    </Note>
  </Accordion>
</AccordionGroup>

***

## Platform Integrations

Toggle the channels your chat agent should answer on. These can come from your connected GoHighLevel subaccount and/or the new Meta integration (Facebook + Instagram).

### Meta Integration (Instagram + Facebook Pages)

To respond directly on your Instagram or Facebook Pages:

<Steps>
  <Step title="Open Company Settings">
    Go to **Settings → Company → Integrations**
  </Step>

  <Step title="Connect Meta">
    Click **Meta**, log in, and choose the Facebook Page + Instagram account to connect
  </Step>

  <Step title="Enable Channels">
    Return to **Platform Integrations** and toggle **Instagram DMs** and/or **Facebook Messenger**
  </Step>
</Steps>

<Frame>
  <img src="https://mintcdn.com/outboxsolutions/jQ0LoSOOg35Qyr-K/images/chat-platform-integrations.png?fit=max&auto=format&n=jQ0LoSOOg35Qyr-K&q=85&s=ca353f2652b0594ae692e9e117c82048" alt="Platform Integrations" width="900" height="830" data-path="images/chat-platform-integrations.png" />
</Frame>

### Available Channels:

<CardGroup cols={2}>
  <Card title="Instagram DMs" icon="instagram">
    Automatically respond to Instagram direct messages
  </Card>

  {" "}

  <Card title="Facebook Messenger" icon="facebook-messenger">
    Handle Facebook Messenger conversations
  </Card>

  {" "}

  <Card title="Email" icon="envelope">
    Respond to emails automatically
  </Card>

  {" "}

  <Card title="SMS" icon="message">
    Answer text messages instantly
  </Card>

  {" "}

  <Card title="WhatsApp" icon="whatsapp">
    Manage WhatsApp business conversations
  </Card>

  <Card title="Web Chat" icon="comment-dots">
    Embed a chat widget on any website
  </Card>
</CardGroup>

<Warning>
  **Important:** Switching a platform on means this agent will answer **all**
  new messages for that channel (unless a trigger blocks it—see next section).
</Warning>

### Automated do-not-contact (DND)

If a contact **asks not to be contacted again** in chat or on a call, Outbox AI can **automatically mark them as DND (do not disturb)**. Once set, they will not be contacted again by your automated agents, helping you stay aligned with opt-out requests without manual tagging.

***

## Triggers for Campaigns & Keyword Flows

Triggers give you precise control over when your agent should respond. Perfect for Instagram reels, keyword campaigns, or keeping the AI silent while you chat with clients manually.

### How Triggers Work:

1. **Add a trigger word or phrase** (e.g., "start", "book", "info")
2. The agent **only wakes up** when the incoming message matches the trigger
3. Messages that don't match the trigger are ignored by the AI

### Example Use Cases:

<AccordionGroup>
  <Accordion title="Instagram Reel Campaigns" icon="video">
    "DM me **START** to claim your free voucher!"

    The agent only responds to messages containing "start", ignoring casual comments and other DMs.
  </Accordion>

  {" "}

  <Accordion title="Keyword-Based Routing" icon="route">
    * **"book"** → Activate booking agent - **"support"** → Activate support agent
    * **"refund"** → Activate refund agent
  </Accordion>

  <Accordion title="Manual Control" icon="hand">
    Set a trigger so the AI doesn't interfere when you're personally chatting with VIP clients.
  </Accordion>
</AccordionGroup>

<Tip>
  Leave triggers **empty** if you want the agent to respond to every message on
  the enabled platforms.
</Tip>

***

## Delay Settings

Make your agent feel more human by adding natural response delays.

### Configuration:

* **Minimum delay** – The shortest time before the agent responds
* **Maximum delay** – The longest time before the agent responds
* The actual delay is **randomized** between these values

### Recommended Settings:

<CardGroup cols={2}>
  <Card title="Instant Response" icon="bolt">
    Min: 0 seconds Max: 5 seconds For time-sensitive inquiries or customer
    support
  </Card>

  {" "}

  <Card title="Human-like Response" icon="user">
    Min: 30 seconds Max: 120 seconds For conversations that should feel natural
    and unhurried
  </Card>

  {" "}

  <Card title="Casual Response" icon="coffee">
    Min: 2 minutes Max: 10 minutes For lower-priority channels or when mimicking a
    busy human
  </Card>

  <Card title="Business Hours Simulation" icon="clock">
    Min: 15 minutes Max: 60 minutes For email responses or non-urgent inquiries
  </Card>
</CardGroup>

<Note>
  **Why randomize?** A fixed delay (e.g., always 60 seconds) feels robotic.
  Random delays make the agent feel more human and authentic.
</Note>

***

## Automatic chat score and summary

Every chat conversation is automatically analyzed for **quality and outcome**:

* **Score** – A percentage from **0% to 100%** reflecting how well the exchange went (engagement, resolution, tone, and similar signals).
* **Summary** – A short **plain-language summary** of what was discussed or decided.

Use scores and summaries in logs and reporting to spot coaching opportunities, compare agents, and prioritize follow-up without reading full threads.

***

## Knowledge Base

Give your agent access to company information, product details, policies, and more. Choose from three methods:

<AccordionGroup>
  <Accordion title="File Upload" icon="file-arrow-up">
    Drop files directly into the knowledge base—the agent will read and understand them.

    **Supported Formats:**

    * 📄 PDFs
    * 📝 Word documents (.docx, .doc)
    * 📊 CSV files
    * 📋 Plain-text files (.txt)
    * 🔤 Markdown files (.md)

    <Frame>
      <img src="https://mintcdn.com/outboxsolutions/jQ0LoSOOg35Qyr-K/images/chat-knowledge-file-upload.png?fit=max&auto=format&n=jQ0LoSOOg35Qyr-K&q=85&s=5dc513de858149ad7e14b87c68117471" alt="File Upload" width="1074" height="776" data-path="images/chat-knowledge-file-upload.png" />
    </Frame>

    **Best for:**

    * Product manuals
    * Company policies
    * FAQs
    * Pricing sheets
    * Training materials
  </Accordion>

  <Accordion title="Website Scrape" icon="globe">
    Paste any URL and Outbox AI will scrape the entire site into clean, AI-readable Markdown.

    **Powered by Firescraper** – Advanced scraping technology that handles:

    * JavaScript-rendered content
    * Multi-page sites
    * Dynamic content
    * Complex site structures

    <Frame>
      <img src="https://mintcdn.com/outboxsolutions/jQ0LoSOOg35Qyr-K/images/chat-knowledge-website-scrape.png?fit=max&auto=format&n=jQ0LoSOOg35Qyr-K&q=85&s=94757c75a6b3d41f094f722eebffff68" alt="Website Scrape" width="1068" height="632" data-path="images/chat-knowledge-website-scrape.png" />
    </Frame>

    **Best for:**

    * Company websites
    * Product documentation
    * Help centers
    * Blog content
    * Knowledge base articles

    <Tip>
      The scraper will follow links and capture the entire site structure, not just a single page!
    </Tip>
  </Accordion>

  <Accordion title="Plain Text" icon="text">
    Paste raw text directly into the knowledge base.

    <Frame>
      <img src="https://mintcdn.com/outboxsolutions/jQ0LoSOOg35Qyr-K/images/chat-knowledge-plain-text.png?fit=max&auto=format&n=jQ0LoSOOg35Qyr-K&q=85&s=9fba6e8fb627a8e3e687f28c053a8988" alt="Plain Text" width="1058" height="1028" data-path="images/chat-knowledge-plain-text.png" />
    </Frame>

    **Best for:**

    * Custom instructions
    * Quick reference information
    * Company values and mission
    * Temporary information
    * Testing and prototyping

    <Note>
      You can combine all three methods! Add files, scrape websites, **and** paste text for maximum coverage.
    </Note>
  </Accordion>
</AccordionGroup>

***

## Agent Settings

Fine-tune your agent's behavior with advanced configuration options.

### Time Zone

Set the agent's time zone to ensure accurate date and appointment logic.

<Note>
  The time zone affects how the agent interprets phrases like "tomorrow at 3pm"
  or "next Monday."
</Note>

***

### Model Selection

Choose the AI model that powers your agent. Each model has different capabilities, speeds, and costs.

<Frame>
  <img src="https://mintcdn.com/outboxsolutions/jQ0LoSOOg35Qyr-K/images/chat-settings-model.png?fit=max&auto=format&n=jQ0LoSOOg35Qyr-K&q=85&s=ac75f47c921f7150630b4fba63b3a72c" alt="Model Selection" width="828" height="628" data-path="images/chat-settings-model.png" />
</Frame>

<AccordionGroup>
  <Accordion title="GPT-4.1 (Recommended)" icon="star">
    **Best balance of speed, cost, and intelligence.**

    * ⚡ Fast response times
    * 💰 Cost-effective for high-volume conversations
    * 🧠 Excellent understanding of context and nuance
    * ✅ Recommended for most use cases

    **Pricing:** \~\$0.01 per conversation
  </Accordion>

  <Accordion title="GPT-4o" icon="brain">
    **OpenAI's flagship model with superior performance.**

    * 🎯 Superior reasoning ability
    * 📚 Better handling of complex knowledge bases
    * 💡 More creative responses
    * 💸 Higher cost per conversation

    **Pricing:** \~\$0.015 per conversation

    **Best for:** High-value conversations, complex product lines, technical support
  </Accordion>

  <Accordion title="GPT-4.1 Mini / Nano" icon="gauge-simple-min">
    **Ultra-cheap, only for very basic auto-responses.**

    * 🏃 Extremely fast
    * 💵 Very low cost
    * ⚠️ Limited reasoning ability
    * 📝 Best for simple, scripted responses

    **Pricing:** \~\$0.001 per conversation

    **Best for:** Simple FAQs, basic greetings, keyword-based responses
  </Accordion>

  <Accordion title="GPT o3 / o4-mini (Premium)" icon="gem">
    **Premium accuracy with advanced reasoning capabilities.**

    * 🔍 Can search the web in real-time
    * 🎓 Exceptional reasoning and problem-solving
    * ⏱️ Slower response times (5-15 seconds)
    * 💎 Premium pricing

    **Pricing:** \~\$0.05 per conversation

    **Best for:** Research-heavy conversations, fact-checking, complex technical queries
  </Accordion>
</AccordionGroup>

<Warning>
  **Cost Management:** Higher-tier models can significantly increase your costs.
  Start with GPT-4.1 and only upgrade if you need the extra capabilities.
</Warning>

***

## Embed Code

Get HTML code to embed your chat widget on any website—yours or your clients'.

<Frame>
  <img src="https://mintcdn.com/outboxsolutions/jQ0LoSOOg35Qyr-K/images/chat-embed-code.png?fit=max&auto=format&n=jQ0LoSOOg35Qyr-K&q=85&s=ac54ab137d0acecca57ed337b427e064" alt="Embed Code" width="796" height="1062" data-path="images/chat-embed-code.png" />
</Frame>

### How to Use:

1. Copy the HTML snippet from the **Embed Code** section
2. Paste it into your website's HTML, just before the closing `</body>` tag
3. The chat widget will appear on your site automatically

### Example Code:

```html theme={null}
<script
  src="https://app.getoutbox.ai/widget/chat.js"
  data-agent-id="6531f2d6-7067-458b-a782-2cae809a7dc6"
  data-open="false"
  async
></script>
```

<Note>
  Replace the `data-agent-id` value with your actual agent ID from the Embed
  Code section.
</Note>

***

### Branding Your Chat Widget

Customize your chat widget's accent color to match your brand identity directly from the Embed Code settings.

**Branding Option:**

* **Accent Color** – Set the accent color for buttons, links, and interactive elements in the chat widget

**How to Configure:**

1. Navigate to your chat agent's settings
2. Open the **Embed Code** section
3. Use the accent color picker to select your brand color
4. Your embed code automatically updates with your branding preference
5. Copy the updated code and paste it into your website

<Tip>
  **Brand Consistency:** Match your chat widget accent color to your website's
  primary color scheme for a seamless, professional appearance.
</Tip>

<Note>
  Branding changes are applied instantly to the embed code. You can update the
  accent color at any time without needing to regenerate the embed code.
</Note>

***

## Demo Your Agent

Share your chat agent with clients, team members, or test it yourself using the **Share** button.

### Share Options

When you click the **Share** button, you can choose from two demo options:

**1. Chat Window Demo**\
Share a standalone chat window that opens in a new tab. Perfect for quick testing or sharing with team members.

**2. Chat Widget Demo**\
Share an embeddable chat widget that can be displayed on any website. This option includes an optional **Website Embed** feature.

### Website Embed Feature

The chat widget demo includes an optional **Website Embed** field that allows you to demo your chat agent directly on top of your client's website.

**How it works:**

1. Enter the client's website URL in the **Website Embed** field
2. Share the demo link
3. When opened, the chat widget appears overlaid on the client's website
4. This gives clients a preview of how the chat agent will look and function on their actual site

<Note>
  **Website Compatibility:** The Website Embed feature may not work on all
  websites due to website security settings, Content Security Policy (CSP)
  restrictions, or iframe blocking. If the embed doesn't load, try the Chat
  Window Demo instead or contact support for assistance.
</Note>

<Tip>
  **Best Practice:** Use the Website Embed demo to show clients exactly how the
  chat agent will appear on their site before they commit to implementation.
  This helps with client buy-in and reduces setup questions.
</Tip>

***

## Initial Message

Set the first message contacts see when they open the chat widget.

### Example Initial Messages:

<AccordionGroup>
  <Accordion title="Friendly Greeting" icon="hand-wave">
    "👋 Hi there! How can I help you today?"
  </Accordion>

  {" "}

  <Accordion title="Specific Offer" icon="gift">
    "🎉 Welcome! Ask me about our special promotion—20% off all services this
    week!"
  </Accordion>

  {" "}

  <Accordion title="Lead Qualification" icon="clipboard-question">
    "Hi! I'm here to help you find the perfect solution. What brings you here
    today?"
  </Accordion>

  <Accordion title="Booking Focus" icon="calendar-check">
    "Ready to book your appointment? I can check availability and get you scheduled in seconds!"
  </Accordion>
</AccordionGroup>

<Note>
  The initial message only appears in the **web chat embed**. Other platforms
  (Instagram, SMS, etc.) don't support initial messages.
</Note>

***

## Interrupt Mode

Allow the agent to be interrupted when a message is manually sent to the contact.

### How It Works:

When **Interrupt Mode** is enabled:

1. ✅ The AI agent handles all conversations automatically
2. 👤 A human team member sends a manual message in GoHighLevel
3. 🛑 The AI agent is **immediately interrupted** for that contact
4. 🙋 The human takes over the conversation
5. 🤖 The AI stays silent unless manually reactivated

### When to Enable:

<CardGroup cols={2}>
  <Card title="Enable Interrupt Mode" icon="toggle-on">
    **Best for most use cases:** - You want the flexibility to jump into
    conversations - VIP clients get personal attention - Complex situations need
    human expertise - Team members can take over seamlessly
  </Card>

  <Card title="Disable Interrupt Mode" icon="toggle-off">
    **When you want full automation:** - Fully automated support channels -
    After-hours emergency contacts - High-volume, low-touch scenarios - Testing
    agent performance
  </Card>
</CardGroup>

<Tip>
  **Pro Tip:** Keep Interrupt Mode **enabled** during business hours so your
  team can step in when needed, but consider disabling it after hours for 24/7
  automation.
</Tip>

***

## Best Practices

<AccordionGroup>
  <Accordion title="Start Simple, Then Expand" icon="seedling">
    1. Create a basic agent with one or two tools
    2. Test thoroughly on a single platform
    3. Add more platforms and tools gradually
    4. Monitor conversations and refine the prompt
  </Accordion>

  {" "}

  <Accordion title="Be Specific in Your Prompt" icon="bullseye">
    Vague prompts create unpredictable agents. Instead of: ❌ "Be helpful and
    friendly" Try: ✅ "You are a customer service agent for ABC Company. Your goal
    is to help customers book appointments. Always be polite, confirm details
    before booking, and thank customers at the end of each conversation."
  </Accordion>

  {" "}

  <Accordion title="Test Extensively Before Going Live" icon="flask">
    * Send test messages from different platforms - Try edge cases ("What if I say
      no?" "What if I'm confused?") - Have team members role-play difficult
      customers - Check that tools are working correctly
  </Accordion>

  {" "}

  <Accordion title="Monitor and Iterate" icon="chart-line">
    * Review conversation logs regularly - Look for patterns where the agent
      struggles - Update the prompt based on real conversations - Add knowledge base
      articles for common questions
  </Accordion>

  <Accordion title="Use Delay Settings Wisely" icon="clock">
    **Different situations need different delays:**

    * ⚡ Instant (0-5s): Customer support, urgent inquiries
    * 👤 Human-like (30-120s): Sales conversations, lead nurturing
    * 📧 Relaxed (5-15m): Email responses, non-urgent channels
  </Accordion>
</AccordionGroup>

***

## Troubleshooting

<AccordionGroup>
  <Accordion title="Agent Not Responding" icon="circle-exclamation">
    **Possible causes:**

    1. ✅ Check that the platform is toggled **on** in Platform Integrations
    2. 🔑 Verify your GoHighLevel connection is active
    3. 🎯 Ensure triggers aren't blocking the agent (if triggers are set)
    4. ⚡ Confirm the agent is not paused or disabled
  </Accordion>

  {" "}

  <Accordion title="Agent Giving Wrong Answers" icon="message-xmark">
    **How to fix:** 1. 📝 Update the prompt with more specific instructions 2. 📚
    Add relevant information to the knowledge base 3. 🧪 Test with the exact
    phrasing customers use 4. 🤖 Consider upgrading to a smarter model (4.0 or o3)
  </Accordion>

  {" "}

  <Accordion title="Tools Not Working" icon="wrench">
    **Troubleshooting steps:** 1. 🔗 Check that webhook URLs are correct 2. 🔐
    Verify API keys and authentication 3. 📋 Ensure the prompt explicitly tells
    the agent when to use the tool 4. 🧪 Test the tool manually outside of the
    agent
  </Accordion>

  {" "}

  <Accordion title="Agent Responding Too Fast/Slow" icon="gauge">
    **Adjust delay settings:** - Too fast? Increase minimum delay - Too slow?
    Decrease maximum delay - Inconsistent? Widen the range for more variation
  </Accordion>

  <Accordion title="Interrupt Mode Not Working" icon="hand">
    **Checklist:**

    1. ✅ Confirm Interrupt Mode is enabled in settings
    2. 💬 Ensure you're sending messages from GoHighLevel (not another platform)
    3. 👤 Verify you're sending as a team member, not as the AI
    4. 🔄 Try refreshing the conversation view
  </Accordion>
</AccordionGroup>

***

## Next Steps

Now that you've set up your chat agent, here's what to do next:

<CardGroup cols={2}>
  <Card title="Test Thoroughly" icon="vial" href="#best-practices">
    Run through all scenarios before going live with real customers
  </Card>

  {" "}

  <Card title="Set Up Voice Agents" icon="phone" href="/voice-agents">
    Complement your chat agents with AI voice calling
  </Card>

  {" "}

  <Card title="Connect GoHighLevel" icon="layer-group" href="/gohighlevel">
    Integrate with your CRM for maximum automation
  </Card>

  <Card title="Monitor Performance" icon="chart-mixed" href="/analytics">
    Track conversations and optimize your agents
  </Card>
</CardGroup>
