AI Chatbot with LiveChat.com Integration

Deploy an AI-powered chatbot on your website that leverages your internal knowledge base to answer customer queries, and seamlessly forwards complex or unresolved inquiries to a real human agent via LiveChat.com. Enhance customer support efficiency and ensure users always get the help they need.

How the AI Flow works - AI Chatbot with LiveChat.com Integration

Flows

How the AI Flow works

Chat Session Initiation.
Detect when a chat session is opened and greet the user with a welcome message.
User Input Collection.
Collect user queries and inputs through the chat interface.
Knowledge Base Search.
Automatically search the internal knowledge base to find relevant answers to user questions.
AI Response and Assistance.
Use an AI agent to formulate responses based on retrieved knowledge or escalate to a human agent if the answer is not found or user requests.
LiveChat.com Human Escalation.
Seamlessly forward conversations to a real human agent on LiveChat.com when necessary, ensuring complex or sensitive issues are resolved.

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

LLM agent acting as a technical live chat customer support specialist, responding to user queries, searching internal knowledge base, and deciding when to forwa...

                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

Message Widget

Displays a welcome message to the user when they open the chat.

                👋 Welcome to the LiveChat Support Bot!
I’m here to assist you with your inquiries using our internal knowledge base 🤠. If I can’t find the answer you need, I’ll seamlessly forward your request to a real agent on LiveChat.com for further assistance.

Feel free to ask me anything, and let’s get started on resolving your questions! ✨💬

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.

ChatInput

The Chat Input component in FlowHunt initiates user interactions by capturing messages from the Playground. It serves as the starting point for flows, enabling the workflow to process both text and file-based inputs.

See ChatInput

Chat History Component

The Chat History component in FlowHunt enables chatbots to remember previous messages, ensuring coherent conversations and improved customer experience while optimizing memory and token usage.

See Chat History Component

Document Retriever

FlowHunt's Document Retriever enhances AI accuracy by connecting generative models to your own up-to-date documents and URLs, ensuring reliable and relevant answers using Retrieval-Augmented Generation (RAG).

See Document Retriever

Tool Calling Agent

Explore the Tool Calling Agent in FlowHunt—an advanced workflow component that enables AI agents to intelligently select and use external tools to answer complex queries. Perfect for building smart AI solutions that require dynamic tool usage, iterative reasoning, and integration with multiple resources.

See Tool Calling Agent

LiveChat Integration

Seamlessly connect FlowHunt Chatbot to your favorite customer service tools for a smooth transition to human support. The AI agent smartly decides when to escalate, turning the chatbot into a live chat solution with a single click.

See LiveChat Integration

Chat Output

Discover the Chat Output component in FlowHunt—finalize chatbot responses with flexible, multi-part outputs. Essential for seamless flow completion and creating advanced, interactive AI chatbots.

See Chat Output

Message Widget

The Message Widget component displays custom messages within your workflow. Ideal for welcoming users, providing instructions, or showing any important information, it supports Markdown formatting and can be set to appear only once per session.

See Message Widget

Chat Opened Trigger

The Chat Opened Trigger component detects when a chat session starts, enabling workflows to respond instantly as soon as a user opens the chat. It initiates flows with the initial chat message, making it essential for building responsive, interactive chatbots.

See Chat Opened Trigger

Flow description

Purpose and benefits

This workflow sets up a scalable, automated AI chatbot that integrates with LiveChat.com for seamless customer support. It uses an internal knowledge base for instant answers and can smartly escalate to a human agent if needed. Below is a structured explanation of the flow, its logic, and how it benefits support operations.

Main Purpose and Value

  • Goal: Automate customer support by handling common queries with an AI chatbot, using your business’s internal documentation, and escalate to human agents on LiveChat.com when necessary.
  • Benefits:
    • Reduces workload for human agents by handling repetitive questions.
    • Ensures 24/7 coverage and consistent first-line support.
    • Provides smooth handoff for complex or unresolved issues, improving customer satisfaction.

Workflow Steps and Components

ComponentPurposeKey Features
Chat InputReceives user messages from the chat interfaceSupports text and file inputs
Chat HistoryStores and retrieves conversation historyEnsures context is maintained across messages
Document RetrieverSearches internal knowledge base for relevant informationSupplies data for AI responses
Tool Calling Agent (AI)Core logic that generates chatbot responses and decides escalationMultilingual support, integrates with retriever & LiveChat
LiveChat Human Assist ToolConnects user to a real agent via LiveChat.com when escalation is neededSeamless escalation with chat history context
Chat OutputDisplays AI or agent messages to the userTwo instances: for bot responses and system messages
Chat Opened TriggerDetects when a new chat is startedInitiates welcome message
Message WidgetShows a customizable welcome messageSets expectations and invites user questions

Typical Conversation Flow

  1. User Opens Chat:

    • The Chat Opened Trigger activates, leading to the Message Widget displaying a friendly welcome message.
    • This message informs users that they are interacting with a smart bot, supported by an internal knowledge base, and that they can be forwarded to a human agent if needed.

  2. User Sends a Message:

    • The Chat Input node receives the user’s question or request.
    • Conversation context is maintained using the Chat History node.

  3. AI Attempts to Answer:

    • The Tool Calling Agent (AI) analyzes the input.
    • It queries the Document Retriever, searching the internal knowledge base for relevant information.
    • If an answer is found, the AI responds in the same language as the user, and the reply is shown via the Chat Output.

  4. Decision Logic for Escalation:

    • If no relevant information is found and the question is about the software:
      • If the question is in English, the AI prompts the user about connecting to a real agent.
      • If in another language, the AI checks if the user would like to be connected to an English-speaking agent.
    • For unclear questions, the AI asks for clarification.
    • When human assistance is needed, the LiveChat Human Assist Tool connects the user with a real agent on LiveChat.com, including chat history for context.

  5. Human Handoff:

    • The transition is smooth, with the human agent receiving context, ensuring continuity and user satisfaction.

Why This Workflow is Useful for Scaling Support

  • Efficiency: Handles common queries instantly without human intervention, freeing up agents for complex issues.
  • Consistency: Provides uniform answers using your curated knowledge base.
  • Availability: Functions 24/7, capturing leads and assisting users outside business hours.
  • Seamless Escalation: When escalation is necessary, users are smoothly handed over to a human, avoiding frustration.
  • Multilingual Support: Detects and responds in the user’s language, with smart prompts for language switching if escalation is needed.

Example User Journey

  1. User opens the website chat → Receives a welcome message.
  2. User asks a question about your software → AI searches internal docs and replies.
  3. If AI cannot answer, it offers to connect to a human agent (with language logic).
  4. If user agrees, chat is escalated to a LiveChat.com agent with full context.

Conclusion

This flow allows your support system to scale efficiently, ensuring rapid, accurate responses to customers and intelligent escalation to human agents only when needed. It enhances user experience, reduces agent workload, and maximizes the value of your internal knowledge assets.

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