Lead generation and qualification with GPT-4o, Google Workspace, and automated follow-up
π AI Lead Generation and Follow-Up Template π Overview This n8n workflow template automates your lead generation and follow-up process using AI. It captures leads through a form, enriches them with company data, classifies them into different categories, and sends appropriate follow-up sequences automatically. Key Features: π€ AI-powered lead classification (Demo-ready, Nurture, Drop) π Automatic lead enrichment with company data π§ Intelligent email responses and follow-up sequences π Automated demo scheduling for qualified leads π Complete lead logging in Google Sheets π¬ AI assistant for immediate query responses π οΈ Prerequisites Before setting up this workflow, ensure you have: n8n Instance: Self-hosted or cloud version OpenAI API Key: For AI-powered features Google Workspace Account with: Gmail access Google Sheets Google Calendar Basic understanding of your Ideal Customer Profile (ICP) β‘ Quick Start Guide Step 1: Import the Workflow Copy the workflow JSON Import into your n8n instance The workflow will appear with all nodes connected Step 2: Configure Credentials You'll need to set up the following credentials: OpenAI API: For AI agents and classification Gmail OAuth2: For sending emails Google Sheets OAuth2: For lead logging Google Calendar OAuth2: For demo scheduling Step 3: Create Your Lead Log Sheet Create a Google Sheet with these columns: Date Name Email Company Job Title Message Number of Employees Industry Geography Annual Revenue Technology Pain Points Lead Classification Step 4: Update Configuration Nodes Replace Sheet ID: Update all Google Sheets nodes with your sheet ID Update Email Templates: Customize all email content Set Escalation Email: Replace "your-email@company.com" with your team's email Configure ICP Criteria: Edit the "Define ICP and Lead Criteria" node π― Lead Classification Setup Define Your ICP (Ideal Customer Profile) Edit the "Define ICP and Lead Criteria" node to set your criteria: π ICP Criteria Example: Company Size: 50+ employees Industry: SaaS, Finance, Healthcare, Manufacturing Geography: North America, Europe Pain Points: Manual processes, compliance needs, scaling challenges Annual Revenue: $5M+ β Demo-Ready Criteria: High-intent prospects who meet multiple qualifying factors: Large company size (your threshold) Clear pain points mentioned Urgent timeline Budget authority indicated Specific solution requests π± Nurture Criteria: Prospects with future potential: Meet basic size requirements In target industry General interest expressed Planning future implementation Exploring options β Drop Criteria: Only drop leads that clearly don't fit: Outside target geography Wrong industry (B2C if you're B2B) Too small with no growth Already with competitor Spam or test messages π§ Email Customization Customize Follow-Up Sequences: Demo-Ready Sequence: Immediate calendar invitation Personalized demo confirmation Meeting reminder (optional) Nurture Sequence: Welcome email with resources Educational content (Day 2) Webinar/event invitation (Day 3) Demo offer (Day 4) Drop Message: Polite acknowledgment Clear explanation Keep door open for future π§ Advanced Configuration AI Answer Agent Setup: Update the system prompt with your company information Add common Q&A patterns Set escalation rules Configure language preferences Lead Enrichment Options: Add API keys for additional data sources Configure enrichment fields Set data quality thresholds Enable duplicate detection Calendar Integration: Set available meeting times Configure meeting duration Add buffer times Set timezone handling π Monitoring and Optimization Track Key Metrics: Lead volume by classification Response rates Demo conversion rates Time to first response Enrichment success rate Optimization Tips: Regular Review: Check classification accuracy weekly A/B Testing: Test different email sequences Feedback Loop: Use outcomes to refine ICP criteria AI Training: Update prompts based on results π Best Practices Start Simple: Begin with basic criteria and refine over time Test Thoroughly: Use test leads before going live Monitor Daily: Check logs for the first week Iterate Quickly: Adjust based on results Document Changes: Keep track of criteria updates π Scaling Your Workflow As your lead volume grows: Add Sub-workflows: Separate complex processes Implement Queuing: Handle high volumes Add CRM Integration: Sync with your sales tools Enable Analytics: Track detailed metrics Set Up Alerts: Monitor for issues
By FranzDomain-specific web content crawler with depth control & text extraction
This template implements a recursive web crawler inside n8n. Starting from a given URL, it crawls linked pages up to a maximum depth (default: 3), extracts text and links, and returns the collected content via webhook. --- π How It Works 1) Webhook Trigger Accepts a JSON body with a url field. Example payload: { "url": "https://example.com" } 2) Initialization Sets crawl parameters: url, domain, maxDepth = 3, and depth = 0. Initializes global static data (pending, visited, queued, pages). 3) Recursive Crawling Fetches each page (HTTP Request). Extracts body text and links (HTML node). Cleans and deduplicates links. Filters out: External domains (only same-site is followed) Anchors (), mailto/tel/javascript links Non-HTML files (.pdf, .docx, .xlsx, .pptx) 4) Depth Control & Queue Tracks visited URLs Stops at maxDepth to prevent infinite loops Uses SplitInBatches to loop the queue 5) Data Collection Saves each crawled page (url, depth, content) into pages[] When pending = 0, combines results 6) Output Responds via the Webhook node with: combinedContent (all pages concatenated) pages[] (array of individual results) Large results are chunked when exceeding ~12,000 characters --- π οΈ Setup Instructions 1) Import Template Load from n8n Community Templates. 2) Configure Webhook Open the Webhook node Copy the Test URL (development) or Production URL (after deploy) Youβll POST crawl requests to this endpoint 3) Run a Test Send a POST with JSON: curl -X POST https://<your-n8n>/webhook/<id> \ -H "Content-Type: application/json" \ -d '{"url": "https://example.com"}' 4) View Response The crawler returns a JSON object containing combinedContent and pages[]. --- βοΈ Configuration maxDepth Default: 3. Adjust in the Init Crawl Params (Set) node. Timeouts HTTP Request node timeout is 5 seconds per request; increase if needed. Filtering Rules Only same-domain links are followed (apex and www treated as same-site) Skips anchors, mailto:, tel:, javascript: Skips document links (.pdf, .docx, .xlsx, .pptx) You can tweak the regex and logic in Queue & Dedup Links (Code) node --- π Limitations No JavaScript rendering (static HTML only) No authentication/cookies/session handling Large sites can be slow or hit timeouts; chunking mitigates response size --- β Example Use Cases Extract text across your site for AI ingestion / embeddings SEO/content audit and internal link checks Build a lightweight page corpus for downstream processing in n8n --- β±οΈ Estimated Setup Time ~10 minutes (import β set webhook β test request)
By Le Nguyen