Welcome Message
A widget that displays the welcome prompt to the user at the beginning of the chat.
AI Customer Service Chatbot with Human Handoff
An AI-powered customer service chatbot that automatically assists users, retrieves information from internal documents and the web, and seamlessly escalates to a human agent when needed. Ideal for automating customer inquiries and support while ensuring human backup for complex issues.
Flows
How the AI Flow works
- Trigger Chatbot Session.
- Initiates a new chat session and displays a welcome message when a user opens the chat.
- Collect User Input.
- Captures user queries and messages for processing.
- AI Agent Processes Requests.
- An AI agent analyzes user input, leveraging chat history and available information sources.
- Retrieve Knowledge & Search Web.
- Fetches relevant information from company documents and performs Google searches or retrieves content from URLs as needed to answer questions.
- Seamless Human Handoff.
- If the AI cannot resolve the issue, the conversation is escalated to a human support agent for personalized assistance.
Prompts used in this flow
Tool Calling Agent System Prompt
System prompt for the agent that guides its behavior in helping and answering all user questions and tasks.
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.
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.
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.
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.
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.
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).
GoogleSearch Component
FlowHunt's GoogleSearch component enhances chatbot accuracy using Retrieval-Augmented Generation (RAG) to access up-to-date knowledge from Google. Control results with options like language, country, and query prefixes for precise and relevant outputs.
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.
Contact Human Assist Tool
Connect the FlowHunt Chatbot to your customer service tools for seamless transitions to human support. The AI agent smartly escalates conversations, reducing errors and improving satisfaction.
Flow description
Purpose and benefits
This workflow implements a scalable, AI-powered customer service chatbot designed to efficiently handle user queries, provide intelligent responses using information retrieval and web search, and seamlessly escalate conversations to human agents when necessary. The system is structured for automation and high adaptability, making it suitable for organizations aiming to enhance customer support while reducing manual workload.
Workflow Overview
The flow is structured around several interconnected components (nodes) that together provide:
- Automated customer support via AI and information retrieval tools.
- Live chat history management for context-aware responses.
- Web search and document retrieval to answer a broad range of queries.
- Human agent handoff when personalized attention is needed.
Step-by-Step Process
1. Welcome and Chat Initiation
Chat Opened Trigger: Detects when a user opens the chat interface.
Message Widget: Displays a warm welcome message:
👋 Welcome to the AI Customer Service Chatbot!
I’m here to assist you with any questions or issues using AI-powered responses 🤖. If you need further help, I’ll seamlessly hand off the conversation to a human agent for more personalized support.
Ask me anything, and let’s get started! ✨💬Chat Output: Presents the welcome message to the user in the chat interface.
2. Handling User Inputs
- Chat Input: Captures messages and file attachments from the user.
- Chat History: Maintains up to 15 previous chat messages (with a 4000 token limit) to provide context for AI responses.
3. Knowledge Retrieval and Tool Integration
To answer user queries intelligently, the AI agent can access multiple sources:
- Document Retriever: Searches internal knowledge bases or document repositories.
- Google Search: Performs live web searches to fetch up-to-date information, returning URLs and summarized content.
- URL Retriever: Extracts full content from URLs found during Google searches.
- Contact Human Assist Tool: Provides options for the user to connect with a human agent via email or website link (e.g., support@flowhunt.io , https://www.flowhunt.io ).
4. AI Agent Response Generation
Tool Calling Agent: The AI agent orchestrates the response process:
- Receives user input and chat history.
- Uses connected tools (document retriever, web search, URL retriever, human assist) to gather the best information.
- Is guided by the system prompt:
Your goal is to answer all questions and help user with all requested tasks.
Chat Output: The response generated by the AI agent is displayed to the user in the chat.
Key Components and Their Roles
| Component | Role/Functionality |
|---|---|
| Chat Opened Trigger | Detects chat session start |
| Message Widget | Displays welcome message |
| Chat Input | Captures user messages and attachments |
| Chat History | Stores recent messages for context-aware AI responses |
| Document Retriever | Searches internal documents for relevant answers |
| Google Search | Fetches and summarizes internet results for broader coverage |
| URL Retriever | Extracts detailed content from URLs returned by Google Search |
| Contact Human Assist Tool | Enables seamless escalation to human support (email, website) |
| Tool Calling Agent (AI Agent) | Integrates all tools, manages conversation flow, generates final responses |
| Chat Output | Presents messages to the user |
Benefits for Scaling and Automation
- Consistent, Fast Support: Automates responses for repetitive or easily-answered queries, freeing human agents for complex cases.
- Contextual Intelligence: Maintains and leverages chat history for more accurate and relevant answers.
- Comprehensive Information Access: Combines internal documentation, live web search, and URL reading to maximize answer coverage.
- Seamless Human Handoff: When automation is insufficient, the workflow offers easy escalation to a human agent—ensuring customer satisfaction.
- Scalability: Handles multiple conversations in parallel, reducing bottlenecks in customer service operations.
Ideal Use Cases
- Customer support for SaaS platforms, e-commerce, or service providers.
- Internal helpdesks for employees (IT, HR, etc.).
- Any application needing 24/7 intelligent chat support with optional human involvement.
This workflow automates much of the customer support process, ensuring that users get fast, accurate, and context-aware assistance while providing a safety net for escalation to human experts when needed. It is ideal for organizations looking to scale their support operations efficiently without compromising quality.
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 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
AI Chatbot with Tawk Human Handoff
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...
3 min read
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