Prompt
Create a prompt template with dynamic variables ({input}, {human_input}, {context}, {chat_history}, {system_message}).
This is the message from user:
{input}
LiveAgent AI Chatbot Support
Automate customer support in LiveAgent with an AI chatbot that answers questions using your internal knowledge base, retrieves relevant documents, and seamlessly hands off to human agents when needed. Improve response speed and customer satisfaction with intelligent inquiry handling.
Flows
How the AI Flow works
- Receive Customer Chat.
- Captures incoming chat messages from website visitors in LiveAgent.
- Prepare AI Prompt.
- Formats user input and chat history to create a clear prompt for the AI agent.
- AI Agent Processes Inquiry.
- The AI agent analyzes the question, searches internal documents and knowledge sources, and determines the best response strategy.
- Retrieve Answers or Escalate.
- Pulls information from the internal knowledge base or, if needed, escalates the chat to a human support agent.
- Respond to Customer.
- Delivers the AI-generated answer or connects the customer with a human agent in the LiveAgent 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
A tool calling agent.
You are an AI language model assistant acting as technical live chat customer support specialist for ***[https://www.YOURWEBSITE.com]*** - ***YOUR_BUSINESS***.
***
<u>**Initial response:**xa0</u>
Conversation may start with automatic pre-chat info (e.g. email, data consent). Start with a greeting, then reply in customer language, offering assistance.
***
<u>**Identify intent and provide answers:**</u>
1. Search for Relevant Content:
- Use Document Retriever tool to find context related to the question.
2. If Relevant Context is Found:
- Use found knowledge sources to provide concise answers with URLs from Document Retriever for more info.
- Provide setup instructions exactly as stated in the referenced URL.
3. If No Relevant Context is Found and Questions are About **YOUR_BUSINESS**:
- Request additional information for unclear queries.
- Focus first on gathering more details, and use Document Retriever again.
- If still unresolved, use the Contact Human Assist tool to transfer the chat to a human support agent. (Ensure the customer speaks ENGLISH for live assistance).
4. For Inquiries NOT related to **YOUR_BUSINESS**:
- Recognize and direct unrelated inquiries to the support team of the mentioned software or business and prevent misuse for inquiries unrelated to **YOUR_BUSINESS**.
***
<u>**Resource Utilization**</u>
* Use "Document Retriever" to search for knowledge relevant to customer question
* Use "Contact Human Assist" tool for transfer valid and relevant communication to Human agent.
* If visitor is asking about pricing of **YOUR_SERVICE**, use URL retriever tool with URL **YOUR-PRICING-PAGE.COM**.
* If customer is asking about recent changes, check **YOUR-PAGE-WITH-RECENT-CHANGES** and **YOUR-PAGE-WITH-NEWS** using URL retriever tool
***
<u>**Formatting:**</u>
* Answer in the conversation's language.
* NEVER USE BULLETPOINTS (not supported yet)
* Use dashes instead of bullet points.
* DO NOT USE MARKDOWN (not supported yet)
* Keep answers in plain text format.
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.
Prompt Component in FlowHunt
Learn how FlowHunt's Prompt component lets you define your AI bot’s role and behavior, ensuring relevant, personalized responses. Customize prompts and templates for effective, context-aware chatbot flows.
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.
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.
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).
URL Retriever
Unlock web content in your workflows with the URL Retriever component. Effortlessly extract and process the text and metadata from any list of URLs—including web articles, documents, and more. Supports advanced options like OCR for images, selective metadata extraction, and customizable caching, making it ideal for building knowledge-rich AI flows and automations.
LiveAgent Integration
Integrate FlowHunt Chatbot with LiveAgent for seamless AI-to-human support transitions. The AI agent intelligently escalates conversations to human agents, ensuring smooth customer interactions and reducing frustration.
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.
Flow description
Purpose and benefits
This workflow enables a chatbot to automatically handle live chat interactions within the LiveAgent platform. The bot leverages an internal knowledge base and can forward customer inquiries to human agents when necessary. The main objective is to automate customer support, provide instant answers, and scale support operations while ensuring smooth handover to human agents for complex or unresolved issues.
Workflow Overview
The flow processes incoming chat messages, retrieves context from the conversation history, searches internal documentation, and outputs responses. If the chatbot cannot resolve a query, it can escalate the chat to a real human agent using LiveAgent integration.
Key Components and Their Roles
| Component Name | Role/Function |
|---|---|
| Chat Input | Receives incoming user messages from the chat interface. |
| Chat History | Retrieves recent chat history to provide context for responses. |
| Prompt Template | Formats the incoming message and context into a prompt for the chatbot agent. |
| Document Retriever | Searches internal documentation and knowledge bases for relevant answers. |
| URL Retriever | Fetches and parses external web pages or documentation based on URLs for up-to-date answers. |
| LiveAgent Human Assist Tool | Enables escalation to a human support agent via LiveAgent when required. |
| Tool Calling Agent | The main chatbot “brain” that orchestrates document retrieval, response generation, and escalation logic. |
| Chat Output | Displays the chatbot’s reply in the chat interface. |
| Note Widget | Provides setup instructions for administrators to customize the chatbot for their business. |
How the Workflow Operates
User Message Intake: The workflow begins with the Chat Input node, which captures each new message from the user.
Context Gathering: Simultaneously, the Chat History node retrieves recent conversation history (up to 10 messages) to ensure context-aware responses.
Prompt Construction: The Prompt Template node dynamically composes a prompt by inserting the user’s message and context, preparing it for processing by the chatbot agent.
Knowledge Search:
- The Document Retriever searches through internal knowledge sources for documents relevant to the inquiry.
- The URL Retriever can fetch content from specified URLs (e.g., pricing pages, news, updates) if needed.
Tool Orchestration & Response Generation:
- The Tool Calling Agent acts as the central decision-making unit. It:
- Uses document retrieval tools to answer questions with authoritative information.
- Escalates the chat to a human agent via the LiveAgent Human Assist Tool if the bot cannot solve the issue.
- Follows strict formatting rules (no markdown or bullet points, only dashes for lists, plain text).
- Ensures responses are in the user’s language and provides URLs where appropriate.
- The agent is configurable with business-specific information via the Note Widget.
- The Tool Calling Agent acts as the central decision-making unit. It:
Output: The final response, whether an automated answer or a message indicating escalation to a human, is displayed via the Chat Output node.
Configuration and Customization
Setup Instructions: The Note Widget provides guidance for administrators to personalize the chatbot’s configuration for their organization. This includes updating the system message with the correct business name, website, and other key details.
Escalation Logic: If the chatbot cannot find a relevant answer or the inquiry is ambiguous or complex, it prompts the user for more information. If unresolved, it offers to connect the user with a human agent through LiveAgent.
Advantages for Scaling and Automation
- Automated 24/7 Support: The chatbot can instantly field common questions, reducing response times and the workload on human agents.
- Seamless Escalation: For complex or sensitive inquiries, the bot hands over the conversation to a human agent, maintaining support quality and customer satisfaction.
- Centralized Knowledge Base: By integrating both internal documentation and live URLs, the chatbot provides up-to-date, accurate responses.
- Context Awareness: Recent chat history is always considered, leading to more relevant and helpful answers.
- Consistent Formatting and Compliance: The agent follows strict formatting and language rules suitable for LiveAgent chat systems.
Summary Table: Workflow Logic
| Step | Action |
|---|---|
| Incoming message | Captured by Chat Input |
| Gather chat history | Retrieves up to 10 previous messages |
| Prepare prompt | User message + context formatted by Prompt Template |
| Search knowledge sources | Document Retriever and URL Retriever tools engaged as needed |
| Generate response | Tool Calling Agent crafts a response, using tools and context |
| Escalate if needed | Unresolved/complex queries are forwarded to a human agent via LiveAgent integration |
| Display reply | Final message shown to the user through Chat Output |
Conclusion
This workflow automates and streamlines customer support in LiveAgent by combining AI-powered conversation, internal knowledge search, and seamless human handoff. It is highly configurable, scalable, and designed to boost efficiency, consistency, and customer satisfaction in live chat environments.
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.
Learn more
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 L...
4 min read
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 unresolv...
4 min read
Smartsupp AI Chatbot with Human Handoff
This workflow creates an AI-powered chatbot integrated with Smartsupp, leveraging an internal knowledge base to answer customer support inquiries. If the chatbo...
3 min read