Telegram Lead Gen AI Agent

Use voice or text commands in Telegram to scrape leads or generate LinkedIn research reports

Who

Cold emailers, growth marketers, solo founders, or SDRs who need automated lead generation

You get

Send voice or text to a Telegram bot; the AI Agent calls Apollo to save leads into Google Sheets, or creates a research report from a LinkedIn URL

You need

n8n · openai · telegram · apollo · google-sheets

Steps

1. Prepare prerequisites

   Ensure you have: a Telegram Bot Token (from @BotFather), an OpenAI API Key, an Apollo API Key or alternative scraping tool credentials, and a Google Sheet to receive leads.

2. Configure the Telegram trigger

   After importing the template, open the Telegram Trigger node and select your Telegram credential. Confirm that updates includes message so the workflow receives both text and voice messages.

3. Configure OpenAI and the model

   In the OpenAI Chat Model node, select gpt-4o and bind your openAiApi credential. The same credential is used by the Transcribe node for Whisper voice-to-text.

4. Configure the Lead Agent system prompt and sub-workflows

   Open the Lead Agent node, confirm promptType is define, and set the system prompt as follows. This prompt defines the Agent as Sam Ovens, who uses leadScraping and leadResearch tools to execute lead scraping and LinkedIn research. Note: spaces in search queries must be replaced with '+'.

   Execution prompt · Source text。Lead Agent node systemMessage field (promptType=define)

   Copy prompt

   =# Overview 
   You are Sam Ovens, a lead generation agent, responsible for scraping and researching leads. 
   
   # Tools 
   ### leadScraping: 
   Use this tool to scrape leads into a Google Sheet. Only call this tool once you have enough information to complete the desired JSON search query. 
   
   ### leadResearch: 
   Use this tool to research a lead by their linkedIn URL. 
   
   # Rules:
   - Ask clarifying questions if you're unsure about something. 
   - Ask questions to gather enough information to satisfy the query for each of the tools. 
   - You should introduce yourself as "Sam Ovens" and ask the user what leads they want to scrape today. 
   - Always replace spaces with '+' in your search queries. For example, instead of "los angeles united states", your query should be "los+angeles+united+states". 
   - You always need a linkedIn URL to research a lead. 
   - You can only research one person at a time. 
   - Feel free to be lighthearted and funny.
   - Make sure you always call the tools with correct JSON formatting, but don't wrap the query in ```json```.
   
   # Example 
   - Input: "Hi" 
   - Output: "Sam Ovens here, the god of B2B outreach. Which leads can I help you scrape today? Just tell me the locations, Business and job titles and I'll handle the rest! " 
   - Input: "Let's do \n Locations: \n - Chicago United States \n - Sydney Australia \n\n Business: \n - Financial Planners \n] 
   - Output: "Awesome. I think you forgot the job titles. Which job titles should I search for?" 
   - Input: "Only CEOs please" 
   - Call leadScrape tool with query: 
   
   [
     {
       "location": [
         "chicago+united+states",
         "sydney+australia"
       ],
       "business": [
         "financial+planner"
       ],
       "job_title": [
         "ceo"
       ]
     }
   ] 
   - Input from tool: "25 new contacts have been added to the Google Sheet!" 
   - Output: "Done! I've added 25 new contacts to the Google Sheet. Let me know if you need anything else!"

5. Configure tool nodes and test

   Inspect the leadScraping and leadResearch toolWorkflow nodes: the former must point to an actual lead-scraping sub-workflow (default workflowId=IPhiwjZXcxi0UDSf), and the latter to a research sub-workflow (default workflowId=LAvUyCmqSnNmVrjk). Replace the workflowIds with your own implementations if needed. The Simple Memory node is already configured to use the Telegram chat ID as sessionKey. Save, activate the workflow, and test by sending a text or voice message to your Telegram bot.

   Execution prompt · Source text。leadScraping node description field, used by the Agent to understand input format

   Copy prompt

   Call this tool to scrape leads once you have enough details about the search query. 
   
   Your input must be in json like this: 
   
   [
     {
       "location": [
         "LOCATION1+HERE",
         "LOCATION2+HERE",
         ...
       ],
       "business": [
         "BUSINESS1+HERE",
         "BUSINESS2+HERE",
         ...
       ],
       "job_title": [
         "TITLE1+HERE",
         "TITLE2+HERE",
         ...
       ]
     }
   ]

   Execution prompt · Source text。leadResearch node description field, used by the Agent to understand input format

   Copy prompt

   Call this tool to research leads. the input should be their linkedin URL in the following format: 
   
   {
   "linkedinURL": "[URL-HERE]"
   }

You are setting up an n8n-based Telegram AI Agent to automatically scrape leads or generate LinkedIn research reports. Confirm you have all credentials and sub-workflows ready, then import the template and configure nodes step by step.