💬 Score and send LinkedIn DMs with GPT-4.1-mini, Google Sheets and Phantombuster

⚡ 20 views · 💬 Lead Nurturing & AI Sales Agents

💡 Pro Tip — If you’re pulling LinkedIn data through HTTP requests or dealing with API restrictions, there’s a community node called ScraperNode that handles this natively. It has dedicated scrapers for profiles, companies, jobs, and people search — you just pass a URL and get structured data back.

Description

How it works

This workflow creates an AI-powered LinkedIn DM outreach sequence that automatically scores, messages, and follows up with prospects using Google Sheets as a lightweight CRM. When the workflow runs on a schedule, it reads prospect data from Google Sheets and filters only leads that are new or due for action. Each lead is scored by GPT-4.1-mini, which assigns a lead score, priority, and recommended message angle. Based on the prospect’s outreach step, the workflow either sends a personalized first DM or a follow-up DM via Phantombuster, then updates the sheet with the latest status and next action date. Leads with no reply after the full sequence are automatically closed.

Step-by-step

• Trigger and fetch prospects
  • Schedule Trigger – Runs the workflow every hour automatically.
  • Get Prospects from Sheet – Reads all prospect rows from Google Sheets.
  • Filter Active Prospects – Filters leads that are new or have a NextActionDate due today. Skips Closed and Replied leads.
  • Batch Prospects – Processes leads in batches of 3 to respect API rate limits.
• AI lead scoring
  • Score Lead with AI – Sends each prospect to GPT-4.1-mini for evaluation. Returns lead score (Hot / Warm / Cold), priority, and recommended message angle.
  • Parse Lead Score – Extracts and maps the AI JSON response into structured fields.
• Route by outreach step
  • Route by Step – Checks the Step value for each lead and routes to the correct flow: Step 0 → first DM, Step 1 → follow-up DM, Step 2+ → auto-close.
• DM generation, send and CRM update
  • Generate First DM – GPT-4.1-mini writes a short, personalized cold DM based on role, company, and AI message angle.
  • Parse First DM – Extracts the generated message text.
  • Send First DM via Phantombuster – Sends the DM to the prospect’s LinkedIn profile via Phantombuster HTTP API.
  • Update Sheet — First DM Sent – Updates the sheet: Status → Contacted, Step → 1, NextActionDate → +3 days.
  • Generate Follow-up DM – GPT-4.1-mini writes a soft follow-up referencing the first message.
  • Parse Follow-up DM – Extracts the follow-up message text.
  • Send Follow-up DM via Phantombuster – Sends the follow-up to the same LinkedIn profile.
  • Update Sheet — Follow-up Sent – Updates the sheet: Status → Follow-up Sent, Step → 2, NextActionDate → +2 days.
  • Close Lead in Sheet – Marks unresponsive leads as Closed with an auto-closure note.

Why use this?

• Automates the full LinkedIn outreach sequence without manual effort
• Uses AI to personalize every DM based on prospect role, company, and scoring
• Manages the entire pipeline from a single Google Sheet — no extra CRM needed
• Timing between steps is controlled automatically via NextActionDate
• Easily customizable for different industries, message tones, or outreach sequences

🔗 Nodes Used

Google Sheets, HTTP Request, Schedule Trigger, OpenAI

📥 Import

Download workflow.json and import into n8n: Workflow menu → Import from File

📖 Importing guide · 🔑 Credential setup