Research Business Leads with Perplexity AI and Save to Google Sheets

This n8n workflow automates the process of researching business leads using Perplexity AI and then saving the extracted information into a Google Sheet. It's designed to streamline lead generation by leveraging AI for information gathering and structured output.

What it does

1. Manual Trigger: The workflow is initiated manually, allowing you to control when the lead research process begins.
2. Edit Fields (Set): Defines the initial input for the AI agent, specifically the lead_topic you want to research (e.g., "AI startups in San Francisco").
3. AI Agent:
   • Utilizes an OpenAI Chat Model to generate a structured research plan based on the lead_topic.
   • Employs a Perplexity tool to perform web searches and gather information relevant to the lead_topic.
   • The agent is configured to output a JSON array of leads, where each lead contains business_name, website, and description.
4. Structured Output Parser: Parses the AI agent's output to ensure it conforms to the expected JSON structure, extracting the leads array.
5. Split Out: Takes the array of leads and splits them into individual items, so each lead can be processed separately.
6. Aggregate: Combines the individual lead items back into a single array, preparing them for the next step. (Note: This step might be redundant if the goal is to process each lead individually for Google Sheets. It could be useful for specific post-processing before saving.)
7. Google Sheets: Appends the extracted business lead data (business name, website, description) as new rows to a specified Google Sheet.

Prerequisites/Requirements

• n8n Instance: A running n8n instance.
• OpenAI API Key: For the OpenAI Chat Model.
• Perplexity API Key: For the Perplexity AI node.
• Google Account: With access to Google Sheets. You'll need to authenticate your Google Sheets node with n8n.
• Google Sheet: An existing Google Sheet where the leads will be saved. You'll need to specify the Spreadsheet ID and Sheet Name in the Google Sheets node. Ensure the sheet has columns for "Business Name", "Website", and "Description" (or adjust the workflow to match your column names).

Setup/Usage

1. Import the Workflow:
   • Copy the provided JSON code.
   • In your n8n instance, go to "Workflows" and click "New".
   • Click the three dots in the top right corner and select "Import from JSON".
   • Paste the JSON code and click "Import".
2. Configure Credentials:
   • OpenAI Chat Model: Click on the "OpenAI Chat Model" node, then click "Create New Credential" for the "OpenAI API" field. Enter your OpenAI API Key.
   • Perplexity: Click on the "Perplexity" node, then click "Create New Credential" for the "Perplexity API" field. Enter your Perplexity API Key.
   • Google Sheets: Click on the "Google Sheets" node, then click "Create New Credential" for the "Google Sheets API" field. Follow the authentication steps to connect your Google account.
3. Configure Nodes:
   • Edit Fields (Set): Update the lead_topic value to your desired research topic. For example, change "AI startups in San Francisco" to "Sustainable energy companies in Germany".
   • Google Sheets:
     • Enter the Spreadsheet ID of your target Google Sheet.
     • Enter the Sheet Name (e.g., "Sheet1") where the data should be appended.
     • Ensure the "Operation" is set to Append Row.
     • Map the values from the previous nodes to your Google Sheet columns. By default, it expects columns like Business Name, Website, and Description. Adjust the expressions if your column names differ (e.g., ={{ $json.business_name }}).
4. Execute the Workflow:
   • Click "Execute Workflow" in the "When clicking ‘Execute workflow’" (Manual Trigger) node or click the "Execute Workflow" button in the n8n editor toolbar.
   • The workflow will run, research leads based on your topic, and add them to your Google Sheet.

Note: The AI Agent's performance depends on the clarity of the prompt and the capabilities of the underlying language model and tools. You might need to refine the lead_topic and the AI Agent's instructions for optimal results.