This workflow creates an AI-powered chatbot integrated with Smartsupp, leveraging an internal knowledge base to answer customer support inquiries. If the chatbot cannot answer a question, it offers seamless handoff to a human agent via Smartsupp, ensuring customers always get the help they need.
Flows
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.
Displays a welcome message to the user when the chat starts. Used as the initial greeting for the Smartsupp-integrated chatbot.
Here’s a welcome message for your Smartsupp-integrated chatbot:
👋 Welcome to our customer Support Bot!
I’m here to assist you using our internal knowledge base 🧠. If I can’t find the answer you need, I’ll forward your inquiry to a real agent via Smartsupp for personalized support.
Ask me anything, and I’ll do my best to help! ✨💬
System prompt for the LLM-powered agent acting as the technical live chat customer support specialist. Guides the agent's behavior for greeting, searching the k...
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
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.
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.
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.
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.
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.
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.
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.
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).
Integrate FlowHunt Chatbot with Smartsupp for seamless AI-to-human support transitions. AI agents smartly decide when to escalate to human agents, ensuring efficient, error-reduced customer service.
Flow description
This workflow implements an intelligent chatbot that integrates with Smartsupp live chat. It leverages an internal knowledge base to answer customer queries automatically and can escalate conversations to a real human agent through Smartsupp when necessary. This automation helps scale customer support, provide instant answers, and ensure seamless transitions to human support when required.
| Step | Component | Description |
|---|---|---|
| 1 | Chat Opened Trigger | Detects when a chat session starts. |
| 2 | Welcome Message Widget | Sends a friendly, multilingual welcome message to the user. |
| 3 | Chat Output (Welcome) | Displays the welcome message to the user. |
| 4 | Chat Input | Captures user questions or messages typed into the chat interface. |
| 5 | Chat History | Retrieves the conversation history for context-aware responses. |
| 6 | Document Retriever | Searches the internal knowledge base for answers relevant to the user’s question. |
| 7 | Smartsupp Human Assist Tool | Provides an option to connect the user with a live agent via Smartsupp if needed. |
| 8 | Tool Calling Agent (AI Assistant) | Orchestrates the logic, choosing when to answer, ask clarifying questions, or escalate to a human agent. |
| 9 | Chat Output (Agent Response) | Displays the AI’s or human agent’s response to the user. |
Chat Session Initiation: When a user opens a chat, the workflow triggers a welcome message. This message introduces the chatbot, explains its purpose (to assist using the internal knowledge base), and assures the user that they can connect to a human agent if needed.
User Interaction: As the user sends messages, the Chat Input node captures these, and the conversation history is tracked for context.
Knowledge Base Search: For every user message, the workflow uses a Document Retriever to search the internal knowledge base for documents or content relevant to the user’s query.
Automated Answering: The Tool Calling Agent (AI Assistant) uses the retrieved content to provide answers. If the question is unclear, the bot asks for clarification. If no relevant knowledge base content is found for a software-related question, the bot follows this logic:
Human Escalation via Smartsupp: If the AI cannot answer or the user requests, the Smartsupp Human Assist Tool is activated to facilitate a smooth handover to a live support agent.
Consistent Language Support: The AI always responds in the language used by the user, ensuring a natural and comfortable experience.
By employing this workflow, businesses can significantly enhance their customer support efficiency, responsiveness, and scalability—all while maintaining a human touch when needed.
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.
An AI-powered live chat support chatbot that answers customer questions using an internal knowledge base and intelligently hands off complex queries to human ag...
Deploy a smart customer support chatbot for LiveAgent that automatically answers visitor questions, retrieves knowledge base documents, and escalates to a human...
Automate customer support in LiveAgent with an AI chatbot that answers questions using your internal knowledge base, retrieves relevant documents, and seamlessl...
