Reply to LinkedIn messages with OpenAI GPT and escalate complex cases to Discord

Workflow preview

100%

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

1. Workflow Overview

Who it's for This workflow is for sales teams, growth agencies, and solo operators running LinkedIn outreach campaigns who want to automate prospect reply handling without losing the human touch on...

Best for

Lead Nurturing automation workflows
AI Chatbot automation workflows
advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.stickynote, n8n-nodes-base.webhook, n8n-nodes-base.filter, n8n-nodes-base.httprequest, @n8n/n8n-nodes-langchain.agent, n8n-nodes-base.wait, n8n-nodes-base.if, n8n-nodes-base.discord

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Allan Vaccarizi.

Original n8n.io source

1.1 Workflow description

Title: Reply to LinkedIn messages with OpenAI GPT and escalate complex cases to Discord
Workflow name: Reply to LinkedIn messages with OpenAI GPT and escalate complex cases to Discord

Who it's for

This workflow is for sales teams, growth agencies, and solo operators running LinkedIn outreach campaigns who want to automate prospect reply handling without losing the human touch on complex cases.

How it works

A webhook receives incoming LinkedIn message events and filters out invalid entries — ensuring a LinkedIn URL is present and the message is not sent by the agent itself.
The Unipile API resolves the contact's public LinkedIn identifier, then fetches the full conversation history for that chat thread.
An AI agent powered by OpenAI GPT analyzes the conversation and classifies the prospect (Meeting Request, Info Request, Not Interested, or Escalation), then drafts a contextual reply.
A conditional branch evaluates the classification: if escalation is required, a formatted alert is posted to a Discord channel; otherwise, the workflow waits a randomized business-hours delay before posting the AI-generated reply back to LinkedIn via the Unipile API.

How to set up

Configure the Webhook node with the correct path to receive LinkedIn reply events
Add your Unipile API credentials (base URL + API key) to the three HTTP Request nodes
Set your OpenAI API credentials in the OpenAI Chat Model node
Configure the Discord bot token and target channel ID for escalation alerts
Update the AI agent system prompt with your identity, company details, and booking link
Adjust the Wait node logic to match your preferred reply delay window

Requirements

Unipile account with a connected LinkedIn account
OpenAI API account
Discord bot with access to a notification channel

How to customize

Swap the OpenAI model for another provider (Anthropic Claude, Mistral) by replacing the language model sub-node.
Extend the classification logic in the IF node to add more routing branches (e.g. route "Not Interested" prospects to a CRM update step).
Replace the Discord alert with a Slack message or an email notification via Gmail for escalation handling.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - Sticky Note13

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 2 - Sticky Note16

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 3 - Sticky Note

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 4 - Sticky Note1

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 5 - Sticky Note2

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 6 - Sticky Note3

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 7 - Sticky Note4

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 8 - Sticky Note5

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 9 - When LinkedIn Reply Received

Type / Role: n8n-nodes-base.webhook - webhook
Config choices: Version 2.1

Block 10 - Filter Valid LinkedIn URLs

Type / Role: n8n-nodes-base.filter - filter
Config choices: Version 2.3

Block 11 - Fetch LinkedIn Public Identifier

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.4

Block 12 - Fetch LinkedIn Chat Messages

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.4

Block 13 - LinkedIn Reply Agent

Type / Role: @n8n/n8n-nodes-langchain.agent - agent
Config choices: Version 3.1

Block 14 - Wait Business Hours Delay

Type / Role: n8n-nodes-base.wait - wait
Config choices: Version 1.1

Block 15 - If Escalation Needed

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.3

Block 16 - Send Escalation to Discord

Type / Role: n8n-nodes-base.discord - discord
Config choices: Version 2

Block 17 - Post AI Reply to LinkedIn Chat

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.4

Block 18 - OpenAI GPT-5-mini Model

Type / Role: @n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices: Version 1.3

Block 19 - Parse Linkedin output

Type / Role: @n8n/n8n-nodes-langchain.outputParserStructured - outputParserStructured
Config choices: Version 1.3

Block 20 - Create webhook Unipile

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.4

Block 21 - When clicking ‘Execute workflow’

Type / Role: n8n-nodes-base.manualTrigger - manualTrigger
Config choices: Version 1

Block 22 - Edit Fields

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 23 - Sticky Note6

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

3. Summary Table

Workflow	Reply to LinkedIn messages with OpenAI GPT and escalate complex cases to Discord
Complexity	advanced
Nodes	23
Categories	Lead Nurturing, AI Chatbot
Author	Allan Vaccarizi
Published	12 May 2026

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/15658/15658.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source Lead Nurturing workflows AI Chatbot workflows

Frequently asked questions

What does Reply to LinkedIn messages with OpenAI GPT and escalate complex cases to Discord do?

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Lead Nurturing, AI Chatbot use case.

Allan Vaccarizi

39 workflows

Nodes

n8n-nodes-base.stickynote n8n-nodes-base.webhook n8n-nodes-base.filter n8n-nodes-base.httprequest @n8n/n8n-nodes-langchain.agent n8n-nodes-base.wait n8n-nodes-base.if n8n-nodes-base.discord

Complexity

advanced

Published 12 May 2026

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/15658/15658.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Re-engage missed property viewings with Google Calendar, Gemini, Gmail, and WhatsApp

## Quick overview When a buyer misses a scheduled viewing, this workflow automatically sends an AI-personalized follow-up by email and WhatsApp using Google Gemini, then logs the outcome to Google Sheets, recovering leads that would otherwise go cold. ## How it works 1. Triggers every 15 minutes when a Google Calendar event is updated in the selected viewings calendar. 2. Checks the event title/summary and continues only if it contains the tag “no-show”. 3. Extracts the lead’s name, email, phone, property address, and scheduled viewing time from the calendar event details. 4. Sends the lead and viewing context to Google Gemini to generate an email message and a WhatsApp message in JSON format. 5. Parses and cleans the AI output into safe HTML for email and a trimmed plain-text WhatsApp message. 6. Sends the re-engagement email via Gmail and appends the follow-up outcome to a Google Sheets log. 7. If a phone number is available, sends the WhatsApp message and updates a Google Sheets status field to record that WhatsApp was sent. ## Setup 1. Connect credentials for Google Calendar, Gmail, Google Sheets, and a Google Gemini (PaLM) API key. 2. Select the correct Google Calendar (viewings calendar) and ensure missed appointments are consistently tagged with “no-show” in the event summary. 3. Create or choose a Google Sheets document and sheet, then fill in the document ID/URL, sheet name, and the columns expected by the append/update logging steps. 4. Configure WhatsApp credentials in n8n (or disable the WhatsApp branch) and ensure lead phone numbers are stored in the calendar event description in the expected format (e.g., Name: ... | Email: ... | Phone: ... |). ## Requirements - Before running this workflow, create a Google Sheet with these exact column headers: Record ID | Lead Name | Email | Phone | Property Address | Original Viewing Time | Email Sent | WhatsApp Sent | Email Message Text | WhatsApp Message Text | Timestamp ## Customization - Edit the AI prompt in "Draft Re-Engagement Messages" to change tone or language - Add SMS or other channels by duplicating the WhatsApp branch pattern - Adjust the "no-show" tag keyword if your calendar uses different terminology ## Additional info WhatsApp is optional. If you don't have WhatsApp Business Cloud API credentials, disable that branch — the email follow-up will still send normally. This template assumes calendar events are tagged with "no-show" in the title and include lead contact info in the event description (Name: ... | Email: ... | Phone: ... |).

View

Quote freight shipments via WhatsApp with Google Gemini, HighLevel, and Warp

## Quick overview Youtube Video: https://youtu.be/kO4LgKT6oME?si=VpUEz2LKuxMujrUp This workflow receives WhatsApp messages, checks the sender in HighLevel, and uses Google Gemini with Redis chat memory to collect shipment details, then requests an LTL quote from the Warp API, applies a commission, and replies with either a conversational prompt or a final freight quote. ## How it works 1. Receives an incoming WhatsApp message and only continues when the text body is not empty. 2. Looks up the sender’s phone number in HighLevel and stops contacts marked as Do Not Disturb from being processed further. 3. Uses a Google Gemini-powered agent with Redis chat memory to ask for missing contact and freight details in a fixed order, optionally creating the HighLevel contact or marking the lead as DND when the user opts out. 4. Parses the agent’s structured JSON output and checks whether the required shipment data collection is complete. 5. If data is incomplete, sends the agent’s conversational reply back to the user via WhatsApp. 6. If data is complete, posts the shipment details to the Warp LTL quote API, adds a configured commission percentage to the returned price, and sends the finalized quote back to the user via WhatsApp. ## Setup 1. Connect WhatsApp credentials for both the WhatsApp Trigger and WhatsApp “send message” actions, and configure the webhook in Meta/WhatsApp so inbound messages reach this workflow. 2. Add a HighLevel OAuth2 credential and confirm your HighLevel account has permission to search contacts, create contacts, and update the DND field. 3. Add a Google Gemini (PaLM) API credential and a Redis credential for chat memory, and ensure Redis is reachable from your n8n instance. 4. Add an HTTP Header Auth credential for the Warp API and verify the quote endpoint URL, headers, and request body fields match your Warp account requirements. 5. Adjust the commission percentage value (and any quoting assumptions like weight per pallet) to match your pricing policy.

View

Qualify web leads and send replies with Groq, Gmail, Sheets and Slack

## Quick Overview This workflow receives new lead form submissions via webhook, uses Groq (OpenAI-compatible Chat Completions) to score and draft a reply, then sends the email via Gmail, logs the lead to Google Sheets as a lightweight CRM, and posts a lead alert to Slack. ## How it works 1. Receives a POST request from your lead/contact form via a webhook. 2. Extracts and normalizes common form fields (name, email, message, service interest, phone, company) and stops if no email is provided. 3. Sends the lead details to Groq’s Chat Completions API to generate a lead score/tier, intent summary, urgency, a drafted reply email, and a Slack note. 4. Parses the Groq JSON response and flags leads as “hot” when the score is 8 or higher. 5. Sends the drafted reply to the lead using Gmail. 6. Appends the lead details and AI outputs to a Google Sheets “Leads-CRM” sheet and posts a formatted alert to a Slack channel. 7. Returns a JSON confirmation response to the original webhook request. ## Setup 1. Configure your form provider to POST submissions to the workflow’s webhook URL (path: `/new-lead`). 2. Add an HTTP Header Auth credential containing your Groq API key for the Groq Chat Completions request. 3. Connect Gmail OAuth2 credentials and set the desired Reply-To address (default is `[email protected]`). 4. Connect Google Sheets OAuth2 credentials and update the target spreadsheet and sheet to match your CRM columns. 5. Connect Slack credentials and choose the destination channel (default: `#leads`).

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

Reply to LinkedIn messages with OpenAI GPT and escalate complex cases to Discord

Workflow preview

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

Who it's for

How it works

How to set up

Requirements

How to customize

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - Sticky Note13

Block 2 - Sticky Note16

Block 3 - Sticky Note

Block 4 - Sticky Note1

Block 5 - Sticky Note2

Block 6 - Sticky Note3

Block 7 - Sticky Note4

Block 8 - Sticky Note5

Block 9 - When LinkedIn Reply Received

Block 10 - Filter Valid LinkedIn URLs

Block 11 - Fetch LinkedIn Public Identifier

Block 12 - Fetch LinkedIn Chat Messages

Block 13 - LinkedIn Reply Agent

Block 14 - Wait Business Hours Delay

Block 15 - If Escalation Needed

Block 16 - Send Escalation to Discord

Block 17 - Post AI Reply to LinkedIn Chat

Block 18 - OpenAI GPT-5-mini Model

Block 19 - Parse Linkedin output

Block 20 - Create webhook Unipile

Block 21 - When clicking ‘Execute workflow’

Block 22 - Edit Fields

Block 23 - Sticky Note6

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions