Chatbots

Chatbots are the execution strategy for your chatbot conversations. Build complex conversation flows using a visual drag-and-drop interface.

What is a Chatbot?

A chatbot defines how your chatbot processes and responds to user messages. It consists of multiple steps connected together, where each step performs a specific action in the conversation flow.

Every chatbot must have a Start (entry point) and an End(exit point). Between these, you can add any combination of processing steps to create sophisticated conversation experiences.

Creating a Chatbot

  1. Navigate to Chatbots
  2. Click Create Chatbot
  3. Enter a descriptive name for your chatbot
  4. You'll see a canvas with Start and End steps already connected
  5. Click the + button on connections to add new steps
  6. Drag steps to rearrange the visual layout
  7. Click on any step to configure its settings

Step Types

Each step type serves a specific purpose in your conversation flow:

Start
The entry point for every conversation. Configure auto-reply messages and initial instructions that greet users when they start chatting.
AI Agent
The AI-powered brain of your chatbot. Configure LLM providers, attach tools and knowledge bases, define response models, and customize prompt behavior.
Branch
Control conversation flow with conditional logic. Define rules using AND/OR operators based on previous step responses and route to different paths.
Form step
Render custom forms to collect structured data from users. Link forms you've created in the Forms section and capture user submissions.
Message
Send fixed, pre-defined messages. Include dynamic variables from previous step responses to personalize the content.
Action
Perform external actions: send emails, post Slack messages, make API calls, or create Zendesk tickets. Supports retry and error handling.
End
The exit point of your chatbot. Attach widgets here to deploy your chatbot and configure sharing options.

Best Practices

Start Simple

Begin with a basic Start → Agent → End flow. Add complexity gradually as you understand how steps interact.

Use Descriptive Names

Name your chatbots and steps clearly (e.g., "Lead Qualification Bot", "Check Intent") to make them easy to understand and maintain.

Test Incrementally

Use the live preview to test your chatbot after adding each new node. This helps identify issues early.

Handle Edge Cases

Use Condition steps to handle different user intents and unexpected inputs gracefully.

Next Steps

AI Agent Deep Dive

Learn about LLM configuration, tools, and knowledge bases

Tools

Explore the IT Services Intent Classifier and other tools