Documentation
Introduction Dashboard
Widget Public Pages

Flow editor

The custom workflows editor allows you to build sophisticated chatbot automation by connecting different action nodes. Each node type serves a specific purpose in your conversation flow.

Understanding Action Nodes

Action nodes are the building blocks of your chatbot workflows. Each node type performs a specific function and can be connected to create conversational pathways. Actions are now categorized into two types:

Regular Actions are processed sequentially within a node - each action completes (either instantly or waiting for user input) before moving to the next action in the same node. You can include multiple regular actions in a single node.

Final Actions can only be selected one per node and will complete the node once executed. These actions typically branch the conversation or end the automated flow.

Regular Actions

These actions are processed one after another within a single node, allowing you to build sequential automation steps.

Message Node

Send text messages to guide users through your conversation flow. Perfect for providing information, asking questions, or delivering instructions.

Collect Data Node

Gather information from users with flexible input types. Collect emails, custom data, or survey responses to build customer profiles and improve targeting.

Ask Question Node

Ask open-ended questions to visitors and collect their natural responses. Perfect for gathering feedback, conducting surveys, or having free-form conversations.

Form Node

Launch interactive forms to collect structured data. Create comprehensive data collection experiences with validation, conditional logic, and custom styling.

API Action Node

Connect your chatbot to external services. Make HTTP requests, trigger webhooks, or integrate with third-party systems with automatic error handling.

Request Agent Node

Transfer conversations to human agents when automation reaches its limits. Ensure seamless handoff for complex situations.

Reply Time Node

Show visitors expected response times to set proper expectations for when they'll receive a reply.

Final Actions

These actions complete the node when executed and can only be used one per node. They typically create branching paths or end the automated conversation.

Buttons Node

Create interactive choices with clickable buttons. Each button can lead to different conversation paths, making it ideal for menus, surveys, or decision trees.

Conditions Node

Add intelligent routing based on visitor data or previous responses. Use conditions to personalize experiences and create dynamic conversation flows.

AI Bot Node

Leverage AI intelligence for complex queries. Ask questions and receive smart, context-aware responses from your AI chatbot.

Custom Bot Node

Reuse existing workflows as components. Build modular automation by nesting one chatbot workflow inside another.

Link Node

Share clickable links with users. Direct them to resources, documentation, or external websites with customizable display options.

Deep Dive: Action Node Capabilities

Regular Actions

Message Node Details

The Message node is your basic communication tool. It sends text content to users at specific points in your conversation flow.

Common scenarios:

  • Welcome messages when workflows start
  • Instructions before data collection
  • Confirmation messages after actions complete
  • Help text and guidance throughout the process

Configuration options:

  • Custom message text with full formatting support
  • Outbound toggle to control message presentation
  • Support for both public and private messages
Pro tip: Use clear, concise language in your messages. Consider your audience and keep instructions simple and actionable.

Collect Data Node: Information Gathering

Transform your chatbot into a data collection tool with flexible input options and validation.

Data collection types:

Automatically collect and validate email addresses. Skips collection if the visitor already has an email on file.

Configuration details:

  • Custom question prompts for each data point
  • Attribute names for data storage and reference
  • Input validation and formatting options
  • Integration with visitor profiles and CRM systems
dataType
select required
Choose between collecting customer email addresses or custom data fields
inputType
select required
For custom data, select text, number, or dropdown input types
question
string required
The prompt or question shown to users when collecting this data
attributeName
string
Name used to store and reference this data in other workflow actions

Ask Question Node: Open-Ended Conversations

Enable natural, free-form conversations by asking open-ended questions that visitors can answer in their own words. Unlike structured data collection, this node allows for organic dialogue and qualitative feedback.

Perfect for:

  • Gathering detailed feedback and reviews
  • Conducting open-ended surveys and research
  • Allowing users to express complex needs or issues
  • Building rapport through conversational interactions
  • Collecting qualitative data for analysis

Key features:

  • Custom question prompts that appear in the chat
  • Natural language responses from visitors
  • Flexible conversation flow without predefined options
  • Response storage for later analysis or follow-up
  • Seamless integration with subsequent workflow actions

How it works:

  1. Configure your question text in the node settings
  2. The question appears naturally in the chat conversation
  3. Visitors respond in their own words without restrictions
  4. Their response is captured and stored for workflow processing
  5. Conversation continues based on your connected workflow paths
question
string required
The question text that will be displayed to visitors in the chat
Best Practice: Use Ask Question nodes when you want genuine, unscripted responses from users. Perfect for understanding customer sentiment, gathering detailed feedback, or exploring complex topics that don't fit predefined choices.
Response Handling: Visitor responses are stored and can be referenced in subsequent workflow actions, conditions, or passed to human agents for context.

Form Node: Interactive Data Collection

Launch comprehensive forms within your chatbot workflows to collect structured information from users. Forms provide a more sophisticated data collection experience compared to simple text inputs.

When to use Form nodes:

  • Multi-step data collection processes
  • Complex surveys requiring validation
  • Lead generation with multiple fields
  • Customer onboarding and registration flows
  • Feedback collection with conditional questions

Key features:

  • Full form builder with drag-and-drop field creation
  • Multiple input types (text, email, phone, dropdown, checkboxes, etc.)
  • Conditional logic to show/hide fields based on responses
  • Built-in validation and error handling
  • Custom styling and branding options
  • Progress indicators for multi-step forms
  • Data storage and CRM integration

How it works:

  1. Select a pre-configured form from your dashboard
  2. The form launches seamlessly within the chat interface
  3. Users complete the form with guided validation
  4. Form responses are automatically stored and can trigger subsequent workflow actions
  5. Conversation continues after form completion
Form Configuration: Forms must be created in your dashboard before they can be used in workflows. Learn how to create and configure forms in our comprehensive Forms Documentation.
Best Practice: Use Form nodes for complex data collection scenarios where you need validation, conditional logic, or multiple related fields. For simple single-field collection, consider using the Collect Data node instead.

API Action Node: External Integrations

Connect your chatbot to the outside world with HTTP requests and web service integrations.

Integration possibilities:

  • CRM system updates and customer record creation
  • E-commerce platform interactions and order processing
  • Database queries and information retrieval
  • Webhook triggers and external workflow activation

Built-in reliability:

  • Automatic error detection and handling
  • Seamless fallback to human agents when APIs fail
  • Request/response logging and monitoring
  • Authentication header support for secure connections
API Configuration: Always test your API endpoints before deploying workflows. The system will automatically transfer to an agent if the API request fails, ensuring conversations never get stuck.

Request Agent Node: Human Handoff

Ensure your automation has a safety net by providing seamless transfer to human agents when needed.

When to use agent transfer:

  • Complex technical issues requiring human expertise
  • Emotional situations needing empathy and personal touch
  • High-value customer interactions
  • Fallback when automation cannot resolve queries

Transfer process:

  • Automatic agent assignment based on availability
  • Context preservation from the automated conversation
  • Optional custom transfer messages
  • Seamless transition without conversation interruption

Configuration options:

  • Pre-transfer message: Customize the message sent by the AI before requesting an agent. Leave empty to use the default message.
Best Practice: Use a custom pre-transfer message to set expectations or provide context to the visitor before the handoff occurs, creating a smoother transition experience.

Reply Time Node: Expected Response Times

Set clear expectations by showing visitors how long they can expect to wait for a response. This node helps manage visitor expectations during peak times or when agents are busy.

When to use Reply Time nodes:

  • During business hours when agents are available
  • Before complex tasks that require agent review
  • When transitioning from automated responses to human support
  • To manage expectations during high-volume periods

Display options:

  • Automatic calculation based on current agent availability
  • Custom time estimates for specific scenarios
  • Integration with business hours and timezone settings
  • Clear messaging about when responses can be expected
Best Practice: Use Reply Time nodes before Request Agent actions to set proper expectations. This reduces visitor frustration and improves satisfaction with your support process.

Final Actions

Buttons Node: Interactive Choices

Buttons create decision points in your conversation. Each button represents a choice that leads to a different workflow branch.

Perfect for:

  • Product or service selection
  • Yes/no confirmation dialogs
  • Multi-option surveys and polls
  • Navigation menus and help options

How it works:

  1. User sees your message with clickable buttons
  2. Clicking a button advances them to the connected workflow branch
  3. Each button can lead to completely different conversation paths

Step 1: Configure Button Labels

Enter clear, descriptive text for each button option

Step 2: Connect Output Paths

Drag connections from each button to different nodes in your workflow

Step 3: Handle User Selection

The workflow automatically routes based on the user's choice

Step 4: Continue Conversation

Each path can have its own sequence of actions and responses

Conditions Node: Smart Routing Logic

Conditions add intelligence to your workflows by evaluating visitor data and making decisions automatically.

What you can check:

  • Visitor information (email, country, session history)
  • Widget status (online/offline agents available)
  • Previous user responses and collected data
  • Time-based conditions and patterns

Advanced features:

  • Visual query builder for complex logic
  • Support for AND/OR combinations
  • Multiple conditional branches (if/else if/else)
  • Fallback paths for unmatched conditions

Evaluate whether agents are online, widget availability, or system status. Useful for routing to live agents during business hours.

AI Bot Node: Intelligent Responses

Harness the power of AI to handle complex queries and provide smart, contextual responses.

AI capabilities:

  • Natural language understanding and processing
  • Context-aware conversation handling
  • Knowledge base integration and information retrieval
  • Personalized response generation based on user history

Setup process:

  1. Select your configured AI chatbot
  2. Define the specific question or prompt
  3. Connect the response to continue your workflow
  4. AI handles the conversation seamlessly
AI Integration: The AI bot node works with your existing AI chatbot configurations. Make sure you have an AI chatbot set up in your dashboard before using this node type.

Custom Bot Node: Workflow Composition

Build complex automation by combining multiple workflows into modular components.

Modular design benefits:

  • Reusable workflow components across different chatbots
  • Simplified maintenance and updates
  • Consistent behavior across multiple touchpoints
  • Easier testing and debugging of complex flows

How it works:

  1. Select an existing custom chatbot workflow
  2. Execute it as a step within your current workflow
  3. Pass data between workflows seamlessly
  4. Return control to the main workflow when complete
Best Practice: Use custom bot nodes for common processes like user onboarding, support ticket creation, or product recommendations that you want to reuse across multiple chatbot scenarios.

Link Node: Resource Sharing

Share external resources and direct users to additional information or actions.

Link usage scenarios:

  • Product documentation and user guides
  • Support article references and help centers
  • Download links for files and resources
  • External booking systems or appointment schedulers

Display options:

  • Open links in new browser tabs
  • Maintain conversation context while users browse
  • Seamless return to chatbot after link interaction

Workflow Architecture Principles

Starting Your Workflow

Every custom workflow begins with a Start node - this is your entry point that gets triggered by events like visitor messages, button clicks, or scheduled activations.

Start Node

This node is automatically created and serves as the foundation for your entire workflow. You cannot remove or modify the start node directly.

Building Conversation Flows

Connect your action nodes by dragging from the output handles (right side of nodes) to input handles (left side of nodes). The system validates connections to ensure logical flow.

Connection rules:

  • Output handles create branching paths for decisions
  • Input handles accept connections from previous actions
  • Some nodes (like buttons and conditions) create multiple output paths
  • Workflows can branch extensively and merge back together

Completing Conversations

Workflows naturally end when they reach nodes without output connections. These terminal nodes represent conversation completion points.

End state considerations:

  • Clear user guidance about next steps
  • Data collection completion confirmation
  • Transfer to human agents when appropriate
  • Seamless conversation closure

Advanced Workflow Strategies

Error Handling and Fallbacks

Design robust workflows that handle edge cases gracefully:

Always plan for API failures: API Action nodes automatically transfer to agents when external services fail, but consider additional fallback messaging.
Validate data collection: Use conditions to check if required information was successfully gathered before proceeding.
Handle unexpected user responses: Include catch-all conditions and agent transfer options for scenarios your automation doesn't cover.

Performance Optimization

Keep your workflows efficient and user-friendly:

Minimize decision complexity: Too many conditional branches can confuse both users and workflow maintenance.
Reuse common components: Use Custom Bot nodes for frequently repeated processes rather than rebuilding them.
Test all paths: Thoroughly test every possible conversation path to ensure smooth user experiences.

Monitoring and Analytics

Track your workflow performance:

  • Monitor conversion rates at decision points
  • Analyze common agent transfer reasons
  • Track data collection completion rates
  • Identify popular conversation paths for optimization

Getting Started with Workflows

Ready to build your first custom workflow? Start simple and expand gradually:

Step 1: Define Your Goal

Decide what you want your workflow to accomplish - collect leads, provide support, or guide users through a process.

Step 2: Map the Conversation Flow

Sketch out the logical steps and decision points on paper before building in the editor.

Step 3: Start with Core Actions

Begin with Message and Button nodes to establish the basic conversation structure.

Step 4: Add Intelligence Gradually

Introduce Conditions and Data Collection nodes as your workflow becomes more sophisticated.

Step 5: Test and Iterate

Use the workflow preview to test different paths and refine based on real user interactions.

The custom workflows editor gives you powerful tools to create personalized, intelligent chatbot experiences. Start with the basics and gradually incorporate more advanced features as you become comfortable with the system. Remember - great automation is built on understanding your users and designing conversations that feel natural and helpful.

Previous Custom WorkflowsNextSettings