AI Support Chatbot with LiveAgent Integration

Automate your customer support with an AI chatbot that answers questions using your internal knowledge base and seamlessly connects users to a human agent via LiveAgent if needed. Enhance user experience, reduce response times, and streamline support operations.

How the AI Flow works - AI Support Chatbot with LiveAgent Integration

How the AI Flow works

User Opens Chat

Detects when a user opens the chat and initiates a welcome message.

Display Welcome Message

Shows a personalized welcome message to the user in the chat interface.

AI Handles User Questions

Accepts user questions, retrieves relevant information from the internal knowledge base, and generates AI-powered answers.

Seamless Human Handoff

If the AI cannot answer or if the query requires human assistance, the system offers to connect the user with a live agent via LiveAgent.

Chat Output

Displays responses and updates from both the AI and human agents to the user in the chat.

Prompts used in this flow

Below is a complete list of all prompts used in this flow to achieve its functionality. Prompts are the instructions given to the AI model to generate responses or perform actions. They guide the AI in understanding user intent and generating relevant outputs.

Tool Calling Agent

Agent that acts as technical live chat customer support specialist for a business, utilizing an internal knowledge base and forwarding to human agents if necess...

                You are an AI language model assistant acting as technical live chat customer support specialist for [YOUR BUSINESS] -[DESCRIPTION OF YOUR BUSINESS] 
If conversation starts with a greeting, respond with a greeting in same language and ask how you can assist and if they have any question about our our software or it's features.
Search content relevant to question of user by connecting to DocumentRetriever. 
If you don't find any relevant evidence in context found with DocumentRetriever and ONLY IF QUESTIONS ARE RELATED TO OUR software:
- In case question was in English language, always prompt the user to connect him/her to a real agent.
- In case question in different language, first ask if visitor speaks English and be interested t be connected with English speaking support agent, and only in case of confirmation, prompt the user to connect him/her to a real agent. 
FOR UNCLEAR QUESTIONS ask for more information.

ANSWER IN THE SAME LANGUAGE as defined in Current session chat data

Components used in this flow

Below is a complete list of all components used in this flow to achieve its functionality. Components are the building blocks of every AI Flow. They allow you to create complex interactions and automate tasks by connecting various functionalities. Each component serves a specific purpose, such as handling user input, processing data, or integrating with external services.

Flow description

Purpose and benefits

Workflow Description: Legacy - Chatbot With Old LiveAgent Integration

This workflow automates customer support by combining an AI-powered chatbot with integration to the LiveAgent platform. The chatbot leverages an internal knowledge base to answer customer inquiries. If the AI cannot resolve the customer’s issue, the conversation is seamlessly escalated to a human agent via LiveAgent. Below is a structured description of the workflow, its components, and its potential benefits for scaling and automation.

Overview of Workflow Steps

  1. Chat Initialization & Welcome Message

    • When a user opens the chat, a trigger node activates.
    • The system displays a welcome message, explaining that the bot can answer questions using the internal knowledge base and, if needed, connect the customer to a live agent.

  2. User Input & Message Handling

    • The chat captures user input and tracks the conversation history.
    • All messages and files sent by the user are processed and stored for context-aware responses.

  3. Retrieving Knowledge Base Information

    • The bot queries internal knowledge sources (via a Document Retriever) to find answers relevant to the user’s query.
    • If relevant information is found, the bot provides an answer directly from the knowledge base.

  4. AI as Support Specialist

    • An AI agent acts as a technical support specialist, following a detailed system prompt:
      • Greets users in their language.
      • Seeks to answer questions using the knowledge base.
      • Asks for clarification if a question is unclear.
      • If the AI cannot find a relevant answer and the question is about the software:
        • For English queries: Offers to connect to a live human agent.
        • For other languages: Asks if the user wants to speak to an English-speaking agent, and offers connection upon confirmation.
      • Always responds in the user’s language.

  5. Escalation to Human Agent

    • If the AI cannot resolve the issue, or the user requests it, the workflow can escalate the conversation to a real support agent using LiveAgent.
    • The transition includes context from the current chat, ensuring a smooth handover.

  6. Output to User

    • All responses, whether from the chatbot or a live agent, are displayed to the user in the chat interface.

Key Components and Their Functions

Component NameFunctionality
Chat Opened TriggerDetects when a user initiates a chat session.
Message WidgetSends a friendly, informative welcome message to the user.
Chat OutputDisplays messages to the user in the chat window.
Chat InputCollects messages and files from the user.
Chat HistoryMaintains a running history of the conversation for context-aware responses.
Document RetrieverSearches the internal knowledge base for relevant answers to user queries.
LiveAgent Human Assist ToolProvides a button or process to escalate the chat to a real human agent via LiveAgent.
Tool Calling Agent (AI)Orchestrates responses, utilizing both the Document Retriever and LiveAgent handoff tool.

Workflow Diagram

Here’s a simplified flow of the described process:

  1. User opens chat
    ⬇️
  2. Welcome message is displayed
    ⬇️
  3. User sends a question
    ⬇️
  4. AI agent uses chat history and knowledge base to answer
    ⬇️
  5. If answer not found
    ⬇️
  6. AI offers to connect user to human agent (LiveAgent)
    ⬇️
  7. Human agent takes over, if needed

Benefits for Automation and Scaling

  • 24/7 Instant Support: The AI chatbot provides immediate answers to common questions, reducing wait times and improving customer satisfaction.
  • Efficient Human Escalation: Only complex or unresolved queries are forwarded to human agents, optimizing agent workload and improving efficiency.
  • Context-Aware Responses: The use of chat history and knowledge retrieval ensures that responses are tailored and relevant.
  • Multi-language Support: The AI handles greetings and answers in the user’s language and manages language transitions for human escalation.
  • Reduced Training Costs: The AI acts as a first-line support specialist, allowing human agents to focus on more challenging issues.
  • Seamless Handover: Integration with LiveAgent ensures that when escalation is needed, the transition is smooth and includes all relevant context.

Use Cases

  • SaaS Customer Support: For software companies looking to provide scalable, automated support with a human backup.
  • E-commerce Helpdesks: To answer product, order, or return queries instantly, escalating only complex or sensitive cases.
  • Technical Support: For organizations that need to provide technical guidance from both a knowledge base and live experts.

This workflow is especially useful for organizations seeking to automate routine support tasks, scale their support operations efficiently, and maintain high-quality customer service with minimal delays.

Let us build your own AI Team

We help companies like yours to develop smart chatbots, MCP Servers, AI tools or other types of AI automation to replace human in repetitive tasks in your organization.

Schedule a demo Try it now

Learn more