Chatbot with Flow Call Processor Node

The Chatbot with Flow Call Processor node creates an interactive chatbot interface that can invoke sub-flows for complex processing tasks. This powerful node combines conversational AI with the ability to call external sub-flows, enabling sophisticated multi-turn conversations with modular processing capabilities. It's ideal for building intelligent assistants that need to perform specialized tasks through reusable sub-flows.

Chatbot with Flow Call Processor node

Basic Usage

Use the Chatbot with Flow Call Processor node to create interactive chatbots that can call sub-flows for data processing, analysis, or specialized operations during conversations.

Inputs

The Chatbot with Flow Call Processor node accepts the following inputs:

The Bot Name: The display name for your chatbot.
Icon Image: Optional custom icon/avatar for the chatbot.
Bot Introduction - First Message: The initial greeting message when users start a conversation.
Placeholder: Placeholder text shown in the user input field.
System Prompt: Core instructions that define the chatbot's behavior and personality.
Reference: Additional context or reference information for the chatbot (optional).
Additional Slots: Dynamic slots that can be configured to pass data to called sub-flows.

Outputs

Full Chat Log: Complete conversation history including all user inputs and bot responses.
Additional Output Slots: Custom output slots for receiving data back from called sub-flows.

Configuration

Bot Control Section

The Bot Name: Enter the name that will be displayed for your chatbot (e.g., "Employee Report Assistant", "Data Analyzer Bot").

Icon Image: Upload or select an icon/avatar image to represent your chatbot in the interface.

Bot Introduction - First Message: Write the greeting message users will see when they start interacting with the chatbot.

User Interaction Section

Placeholder: Set the placeholder text for the user input field (e.g., "Type your message here...", "Ask me anything...").

Processing Flow Section

System Prompt: Define the chatbot's core behavior, personality, and capabilities. This is crucial for instructing the bot on how to interact and when to call sub-flows.

Reference: Provide additional context, knowledge base content, or reference information that the chatbot can use during conversations.

+ Add More Slots: Click to add custom input/output slots for:

Passing data to called sub-flows
Receiving results from sub-flows
Mapping conversation data to specific parameters

Sub-Flow Integration

Json Builder: Configure the sub-flow(s) that the chatbot can call:

Select the target sub-flow (e.g., JSON Builder for data processing)
Map conversation data to sub-flow parameters
Define when and how to invoke the sub-flow
Mark as "Done" when configuration is complete

Additional Options

Full Chat Log: Output handle for accessing the complete conversation history.

Math Input: Enable mathematical expression input if needed.

Handwriting Input: Enable handwriting recognition for user input.

Write To Journal: Save conversation data to a journal/log.

Set Character Limit: Limit the length of user messages.

Example Workflows

Employee Report Processing Chatbot

Scenario: Create an intelligent chatbot that can extract and structure employee information from text reports using a sub-flow.

Chatbot Flow Processor Example

Steps to Create the Flow:

Set up the Chatbot with Flow Call Processor node:

i. Configure Bot Control:
- The Bot Name: "Employee Report Assistant"
- Icon Image: Upload a professional bot avatar
- Bot Introduction:
```
Hello! I'm your Employee Report Assistant. I can help you extract and structure employee 
information from company reports. Just paste your report text, and I'll process it for you.
```
ii. Configure User Interaction:
- Placeholder: "Paste your employee report here..."
iii. Configure Processing Flow:
- System Prompt:
```
You are a helpful employee data extraction assistant. When users provide an employee report, 
acknowledge it and call the JSON Builder sub-flow to extract structured employee information. 
Present the results in a clear, organized format. Be professional and helpful.
```
- Reference: Add any company-specific formatting guidelines or data structures
iv. Configure Sub-Flow Integration:
- Click + Add More Slots to add custom slots
- Configure the Json Builder sub-flow:
  - Map user input to the sub-flow's input parameter
  - Connect to the Flow Call Receiver's slot-1
  - Mark as Done when configuration is complete
Create the Sub-Flow (as shown in the image):

i. Add Flow Call Receiver Node:
- Configure slot-1 to receive report text from the chatbot
ii. Add Text Node with the employee report data (or pass through from receiver)

iii. Add JSON Block Node with the schema:
```
{
  "type": "object",
  "properties": {
    "employees": [
      {
        "name": "string",
        "id": "string",
        "email": "string",
        "age": "number",
        "status": "string"
      }
    ]
  }
}
```
iv. Add Text Node with extraction instructions:
```
Extract information for all employees mentioned in the report. Create an array of employee 
objects and provide summary statistics.
```
v. Add JSON Builder Node:
- Connect all inputs (report text, schema, instructions)
- Process the data
vi. Add Flow Call Return Node:
- Connect JSON Builder's output to Returning Slot Json
- This returns structured data back to the chatbot
Test the conversation flow:
- User pastes employee report
- Chatbot acknowledges and processes via sub-flow
- Sub-flow extracts structured JSON data
- Chatbot presents formatted results to user

Preview:

User Input:

Company Employee Report 2026
Employee #1: John Smith (ID: EMP001, john@company.com, age 32, active) works as Senior 
Developer in Engineering department.

Chatbot Response:

Thank you! I've processed your employee report. Here's the structured information:

**Employee Data Extracted:**

📋 Employee #1:
- Name: John Smith
- ID: EMP001
- Email: john@company.com
- Age: 32
- Status: Active
- Position: Senior Developer
- Department: Engineering

**Summary:**
- Total Employees: 1
- Average Age: 32

Would you like to process another report or need any modifications to this data?

Result: An intelligent chatbot that can have natural conversations while leveraging sub-flows for complex data processing tasks.

Basic Usage​

Inputs​

Outputs​

Configuration​

Bot Control Section​

User Interaction Section​

Processing Flow Section​

Sub-Flow Integration​

Additional Options​

Example Workflows​

Employee Report Processing Chatbot​