Prompt
Prompt template for constructing API URL with dynamic human input.
https://YOURLINK/api/conversations/{human_input}/messages
AI-Powered Email Spam Detection and Support Routing
This AI workflow automatically classifies incoming emails as spam or not, and intelligently routes legitimate messages to an AI assistant that leverages company knowledge sources to provide professional support responses. It integrates document retrieval, advanced LLMs, and API interactions for seamless customer support automation.
Flows
How the AI Flow works
- Receive Incoming Email.
- The workflow starts by receiving a user email or message input.
- Classify Email as Spam or Not.
- Uses an AI model to determine whether the incoming message is spam or a legitimate customer inquiry.
- Route Based on Classification.
- Spam messages trigger a simple notification, while legitimate inquiries are routed to the AI support assistant.
- Retrieve Knowledge & Compose Response.
- The AI assistant retrieves relevant documents and knowledge, then generates a professional, context-aware support response.
- Deliver Output to User.
- The final response or notification is output back to the user or support agent.
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.
Prompt
Prompt template for constructing API URL with dynamic input.
https://YOURLINK/api/conversations/{input}
Prompt
Prompt template for constructing API URL with dynamic human input.
https://YOURLINK/api/conversations/{human_input}/messages
Generator
System prompt for LLM to classify emails as spam or not.
You are a business email classifier.
Decide whether the email is business-relevant or an unwanted solicitation.
Spam (“yes”) if it contains:
- Promotions, discounts, sales, campaigns, reward points, affiliate links  
- Invitations to webinars, seminars, events, or partnerships  
- Investment, crypto, job or side-business offers  
- Unsolicited advertisements or commercial outreach  
Not spam (“no”) if it includes:
- Customer complaints, support requests, usage questions  
- Invoices, quotes, purchase orders, contracts, or payment discussions  
- Internal or partner coordination, scheduling, or reports  
- Legitimate responses or confirmation requests  
Output only "yes" or "no".
Generator
System prompt for LLM to extract Preview sections from input.
extract the "Preview" section of your input and output only the section exactly as it is and if there are multiple preview sections output all of them by classifying them based on their date.
Tool Calling Agent
System prompt for LLM agent to act as a professional customer support assistant.
You are an AI language model assistant functioning as a friendly and professional customer support and consulting assistant for [YOUR COMPANY].
Always respond in English, regardless of whether the input is in English or another language.
All messages should be written in a polite and business-appropriate tone to instill confidence and trust in customers.
[Role]
You assist with questions, consultations, and technical issue resolution related to [YOUR COMPANY]'s services and related products (e.g., customer support tools, flow management tools, website building and management, etc.).
Provide guidance in a tone that is easy to understand and leaves a positive impression on customers.
[Purpose]
Based on the conversation history and the latest inquiry, refer to accurate information from available knowledge sources or tools to provide optimal responses in English.
[Information Reference Priority]
Primary Source: Use the knowledge source search tool to verify relevant information before responding.
Secondary Source: When investigating related context, always use the document retriever tool.
Speculation or fabrication based on self-judgment is prohibited.
[Response Guidelines]
1. When relevant context or information is found, provide accurate and concise responses in English based on that information.
2. List the URLs of referenced sources directly below the response (modifying URLs is prohibited).
3. Use only service names and plan names that exist in the actual knowledge base.
4. If no relevant information is found, clearly state that "the relevant information could not be found" and politely request additional details from the customer.
[Handling Questions Unrelated to [YOUR COMPANY]]
For inquiries unrelated to [YOUR COMPANY], clearly state, "This question is not related to [YOUR COMPANY]."
[When a Customer Shows Interest in a Specific Plan or Service]
• Provide details about the plan, pricing, and consultation/demo options.
• If necessary, guide the customer on how to inquire through the official website.
• For questions about implementation schedules or initial costs, present available options.
[Style and Expression Rules]
• Use a professional email tone (formal but approachable).
• Structure responses in short paragraphs for readability.
• Bullet points are allowed.
• Use plain text format only (Markdown symbols such as #, ##, ### for headings are strictly prohibited).
• Do not use emojis or emoticons.
• Maintain respectful language while avoiding overly formal tones.
[Recommended Response Format]
1. Polite greeting (e.g., "Thank you for your inquiry.")
2. Briefly restate the question or issue.
3. Clearly present the solution or guidance.
4. If necessary, provide next steps (e.g., URLs, contact information, or support options).
5. Closing statement (e.g., "We look forward to assisting you further.")
[Prohibited Actions]
• Use of Markdown symbols (e.g., #, ##, ###) is prohibited.
• Use of bold, italic, or link Markdown syntax is prohibited.
• Speculation based on uncertain information is prohibited.
• Use of inappropriate expressions, slang, or emojis is prohibited.
[Response Tone Examples]
"Thank you for your inquiry.
The details are as follows: …"
"We apologize for any inconvenience, but regarding this matter…"
"Thank you for your attention, and please let us know if you need further assistance."
[Special Notes]
• For questions about [YOUR COMPANY] and its related services, always respond based on the latest knowledge available.
• If relevant information cannot be obtained, request additional details and avoid speculative responses.
• Always use courteous and empathetic expressions to ensure customers feel supported.
This prompt serves as the standard for delivering consistent, high-quality customer support as a member of the [YOUR COMPANY] support team.
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.
API Request
Integrate external data and services into your workflow with the API Request component. Effortlessly send HTTP requests, set custom headers, body, and query parameters, and handle multiple methods like GET and POST. Essential for connecting your automations to any web API or service.
Parse Data
The Parse Data component transforms structured data into plain text using customizable templates. It enables flexible formatting and conversion of data inputs for further use in your workflow, helping to standardize or prepare information for downstream components.
Generator
Explore the Generator component in FlowHunt—powerful AI-driven text generation using your chosen LLM model. Effortlessly create dynamic chatbot responses by combining prompts, optional system instructions, and even images as input, making it a core tool for building intelligent, conversational workflows.
Conditional Router
The Conditional Router component enables dynamic decision-making within your workflow. It compares input text against a specified value using various operators—such as equals, contains, or is empty—and routes the message to different outputs based on the comparison result. This allows you to branch your flow logic, creating personalized and intelligent workflows that adapt to user input.
Create Data
The Create Data component enables you to dynamically generate structured data records with a customizable number of fields. Ideal for workflows that require the creation of new data objects on the fly, it supports flexible field configuration and seamless integration with other automation steps.
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.
LLM OpenAI
FlowHunt supports dozens of text generation models, including models by OpenAI. Here's how to use ChatGPT in your AI tools and chatbots.
LLM Anthropic AI
FlowHunt supports dozens of AI models, including Claude models by Anthropic. Learn how to use Claude in your AI tools and chatbots with customizable settings for tailored responses.
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.
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.
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).
Note
The Note component in FlowHunt lets you add comments and documentation directly into your workflow. Use it to clarify, annotate, or provide instructions within your flow, making complex automations easier to understand and maintain.
Flow description
Purpose and benefits
Workflow Description: Scalable and Automated Business Email & Chat Handling
This workflow is designed to automate and scale the processing, classification, and routing of business emails and chat messages, with a particular focus on customer support scenarios. It uses a combination of AI-powered classification, conditional logic, API integrations, and context-aware agent responses, making it highly useful for organizations looking to streamline customer support, detect spam, and integrate AI agents with external systems like LiveAgent.
High-Level Overview
The flow consists of two main branches:
- Email/Message Spam Detection and Routing: Automatically classifies incoming messages as spam or not and routes them accordingly to ensure efficient handling and reduce manual filtering.
- Contextual AI Agent for Customer Support: Leverages external document retrieval and a sophisticated tool-calling agent to provide accurate, context-rich, and policy-compliant customer support responses.
Detailed Flow Structure
1. Spam Detection and Routing
- Input: Messages are received through a chat input node.
- Prompt Construction: A prompt template is filled with the incoming message and sent to an API request node (configured for LiveAgent or similar systems).
- Text Extraction: The API response is parsed to extract the relevant content using a parsing node.
- Spam Classification LLM: The extracted message is sent to an OpenAI GPT-4.1 model with a system prompt that instructs it to output “yes” if the message is spam (e.g., promotions, unsolicited offers) or “no” if it is business-relevant.
- Conditional Routing:
- If the message is classified as spam (“yes”), a prompt template generates a standard spam notification, which is output to chat.
- If the message is not spam (“no”), it proceeds to a context-aware AI support agent for further handling.
Spam Routing Logic Table:
| Step | Tool/Node | Purpose |
|---|---|---|
| Message Input | ChatInput | Receives user/customer message |
| Prompt for API | PromptTemplate | Formats message for LiveAgent API |
| API Call | APIRequest | Sends/gets message data |
| Parse Data | ParseData | Extracts message preview |
| Spam LLM Classifier | Generator (OpenAI) | Classifies as spam or not |
| Conditional Router | ConditionalRouter | Routes based on LLM output |
| Spam Notification | PromptTemplate & ChatOutput | Standard response for spam |
| Not Spam | Passes to Support Agent | For further human-like handling |
2. Contextual AI Customer Support Agent
- Document Retrieval: When a message is not spam, the flow retrieves relevant documents from a knowledge base, filtered by categories and schedules, to ensure up-to-date and contextually appropriate information is available.
- Chat History Integration: Recent chat history is retrieved to give the agent context for its responses, ensuring continuity and relevance.
- LLM Agent Orchestration: An Anthropic Claude Sonnet 4 model powers a Tool Calling Agent, which is given a detailed system message outlining strict response policies (e.g., always respond in English, use a polite business tone, reference URLs exactly, avoid speculation, and follow a specific output format).
- Tool Integration: The agent can call the document retriever tool and other APIs as needed to supplement its responses, ensuring fact-based answers.
- Output: The agent’s response is output to chat and also passed along for further API integration if required (e.g., forwarding to LiveAgent).
Agent Response Logic Table:
| Step | Tool/Node | Purpose |
|---|---|---|
| Document Retriever | DocumentRetriever | Fetches relevant context from knowledge base |
| Chat History | ChatHistory | Supplies recent conversation context |
| LLM Model | Anthropic Claude | Provides advanced language understanding |
| Tool Calling Agent | ToolCallingAgent | Combines tools, context, and policies to respond |
| Output | ChatOutput | Sends response to chat/playground |
| API Forwarding | APIRequest/ParseData | Optionally forwards for logging/LiveAgent |
System Message Guidelines for Agent
- Always respond in English regardless of the input language.
- Use a formal but friendly business tone; no markdown, no emojis, and no speculation.
- Responses must cite URLs directly below the answer and follow a clear, bullet-friendly structure.
- If no relevant info is found, politely ask the customer for more details.
3. API Integration and Data Handling
- Dynamic Data Creation: Several nodes generate the required data dictionaries for API requests, including API keys, message bodies, and query parameters.
- Multiple API Interactions: The workflow accommodates multiple API requests (e.g., to LiveAgent, other backend systems) with flexible methods (GET, POST, etc.).
- Data Parsing: After each API response, parsing nodes extract relevant text for downstream processing or output.
4. Workflow Automation and Scaling Benefits
- Automated Spam Filtering: Eliminates manual review of unsolicited messages, saving time and focusing agent attention on real support requests.
- Consistent, Policy-Compliant Support: The agent always follows company guidelines, ensuring reliable, brand-safe communication.
- Knowledge-Driven Responses: By integrating document retrieval, the agent bases its answers on the latest and most relevant information.
- Flexible API Integration: Easily extendable to new tools, ticketing systems, or knowledge sources as business needs evolve.
- Scalable: The modular design enables parallel processing of multiple conversations and easy adaptation to higher message volumes.
Example Use Cases
- Customer Support Teams: Automatically triage messages, handle spam, and provide accurate, context-rich responses.
- Sales/Lead Qualification: Filter out non-relevant inquiries before passing genuine leads to sales reps.
- Omnichannel Integration: Connects with platforms like LiveAgent or custom APIs to unify support across channels.
Setup Notes
- Customizations Required: Replace placeholder API keys and URLs (e.g., “YOURLINK”) with actual deployment values.
- Knowledge Base Management: Keep document retriever sources updated for optimal agent performance.
This workflow provides a robust, scalable architecture for automating customer communication, ensuring both efficiency and high-quality, policy-compliant responses. Its modularity allows for easy expansion as your business grows or as new automation needs arise.
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.