Automate support ticket classification & routing from HubSpot to Jira with GPT
Who is this for?
This n8n workflow template is designed for customer support, CX, and ops teams that manage customer messages through HubSpot and use Jira for internal task management. It is especially useful for SaaS companies aiming to automate ticket triage, sentiment detection, and team assignment using AI agents.
🧩 What problem is this workflow solving?
Customer service teams often struggle with manual message classification, delayed reactions to churn signals, and inefficiencies in routing support issues to the right internal teams. This workflow uses LLMs and automated profiling to:
-
Detect churn risk or intent in customer messages
-
Summarize issues
-
Classify tickets into categories (e.g. fulfillment, technical, invoicing)
-
Automatically create Jira tickets based on enriched insights
🤖 What this workflow does
This AI-powered workflow processes HubSpot support tickets and routes them to Jira based on sentiment and topic. Here’s the full breakdown:
-
Triggers: Either manually or on a schedule (via cron).
-
Fetch HubSpot tickets: Retrieves new messages and their metadata.
-
Run Orchestration Agent:
-
Uses Sentinel Agent to detect emotional tone, churn risk, and purchase intent.
-
Calls Profiler Agent to enrich customer profiles from HubSpot.
-
Summarizes the message using OpenAI.
-
Classifies the ticket using a custom classifier (technical, fulfillment, etc.).
-
-
Generate a Jira ticket:
-
Title and description are generated using GPT.
-
The assignee and project are predefined.
-
-
AI agents can be expanded (e.g. add Guide or Facilitator agents).
⚙️ Setup
To use this template, you’ll need:
-
HubSpot account with OAuth2 credentials in n8n
-
Jira Software Cloud account and project ID
-
OpenAI credentials for GPT-based nodes
-
Optional: Create sub-workflows for additional AI agents
Steps:
-
Clone the workflow in your n8n instance.
-
Replace placeholder credentials for HubSpot, OpenAI, and Jira.
-
Adjust Jira project/issue type IDs to match your setup.
-
Test the workflow using the manual trigger or scheduled trigger node.
🛠️ How to customize this workflow to your needs
1. Edit category logic
In the “Category Classifier” node, modify categories and prompt structure to match your internal team structures (e.g., billing, account management, tech support).
2. Refine AI prompts
Customize the agent prompt definitions in:
-
Sentinel_agent
-
Profiler_agent
-
Orchestrator
to better align with your brand tone or service goals.
3. Update Jira integration
You can route tickets to different projects or team leads by adjusting the “Create an issue in Jira” node based on classification output.
4. Add escalation paths
Insert Slack, email, or webhook notifications for specific risk levels or customer segments.
This workflow empowers your team with real-time message triage, automated decision-making, and AI-enhanced customer insight, turning every inbound ticket into a data-driven action item.
Automate Support Ticket Classification & Routing from HubSpot to Jira with GPT
This n8n workflow automates the process of classifying and routing support tickets created in HubSpot to the appropriate Jira project using the power of AI (GPT). It helps streamline your support operations by intelligently analyzing ticket details and directing them to the correct team for resolution.
What it does
This workflow is designed to be a sub-workflow, meaning it's intended to be called by another n8n workflow. When triggered, it performs the following key steps:
- Receives Trigger Data: It waits to be executed by another workflow, expecting input related to a support ticket.
- AI-Powered Text Classification: It uses an AI Text Classifier (likely powered by a Large Language Model like GPT) to analyze the incoming ticket data and determine its category or type.
- Conditional Routing: Based on the classification result, it uses a Switch node to route the ticket down different paths.
- Jira Ticket Creation: For each classified category, it creates a new issue in the corresponding Jira Software project.
- HubSpot Update (Optional/Placeholder): Includes a HubSpot node, which could be used to update the original HubSpot ticket with the Jira issue link or status.
- Summarization (Optional/Placeholder): Features a Summarization Chain, suggesting the capability to summarize ticket details, potentially before creating the Jira issue or for internal notes.
- AI Agent (Optional/Placeholder): Incorporates an AI Agent, indicating potential for more complex, multi-step AI reasoning or interaction within the workflow.
- Structured Output Parsing (Optional/Placeholder): Includes a Structured Output Parser, which can be used to extract specific data fields from unstructured text, likely from the AI classification or summarization steps.
- Call n8n Workflow Tool (Optional/Placeholder): Contains a "Call n8n Workflow Tool" node, which could allow the AI Agent to trigger other n8n workflows as part of its reasoning process.
Prerequisites/Requirements
To use this workflow, you will need:
- n8n Instance: A running instance of n8n.
- HubSpot Account: With appropriate API access configured.
- Jira Software Account: With appropriate API access configured.
- OpenAI API Key (or compatible LLM): For the AI Agent, Text Classifier, and OpenAI Chat Model nodes. This will require credentials for your chosen Large Language Model provider.
- Configured Credentials: You'll need to set up credentials within n8n for HubSpot, Jira Software, and your AI provider (e.g., OpenAI).
Setup/Usage
- Import the workflow: Download the JSON provided and import it into your n8n instance.
- Configure Credentials:
- Set up your HubSpot API credentials.
- Set up your Jira Software API credentials.
- Set up your OpenAI (or other LLM) API credentials for the AI-related nodes.
- Customize AI Nodes:
- Text Classifier: Configure the
Text Classifiernode with the categories you want to classify your support tickets into (e.g., "Bug", "Feature Request", "Technical Support", "Billing Inquiry"). - OpenAI Chat Model: Ensure this node is correctly configured with your OpenAI credentials and desired model.
- Structured Output Parser: If used, define the schema for the structured output you expect from the AI.
- Text Classifier: Configure the
- Configure Switch Node: Adjust the
Switchnode to match the output categories from yourText Classifierand define the routing logic to different Jira projects or issue types. - Configure Jira Software Nodes: For each branch of the
Switchnode, configure theJira Softwarenode to create issues in the correct project with appropriate issue types and fields, mapping data from the incoming HubSpot ticket. - Integrate with a Parent Workflow: This workflow is designed to be triggered by another workflow using the
Execute Workflow Triggernode. You will need a parent workflow (e.g., a HubSpot Webhook trigger) that captures new HubSpot tickets and passes their data to this sub-workflow. - Activate the workflow: Once configured, activate the workflow to start automating your ticket classification and routing.
Related Templates
Send WooCommerce cross-sell offers to customers via WhatsApp using Rapiwa API
Who Is This For? This n8n workflow enables automated cross-selling by identifying each WooCommerce customer's most frequently purchased product, finding a related product to recommend, and sending a personalized WhatsApp message using the Rapiwa API. It also verifies whether the user's number is WhatsApp-enabled before sending, and logs both successful and unsuccessful attempts to Google Sheets for tracking. What This Workflow Does Retrieves all paying customers from your WooCommerce store Identifies each customer's most purchased product Finds the latest product in the same category as their most purchased item Cleans and verifies customer phone numbers for WhatsApp compatibility Sends personalized WhatsApp messages with product recommendations Logs all activities to Google Sheets for tracking and analysis Handles both verified and unverified numbers appropriately Key Features Customer Segmentation: Automatically identifies paying customers from your WooCommerce store Product Analysis: Determines each customer's most purchased product Smart Recommendations: Finds the latest products in the same category as customer favorites WhatsApp Integration: Uses Rapiwa API for message delivery Phone Number Validation: Verifies WhatsApp numbers before sending messages Dual Logging System: Tracks both successful and failed message attempts in Google Sheets Rate Limiting: Uses batching and wait nodes to prevent API overload Personalized Messaging: Includes customer name and product details in messages Requirements WooCommerce store with API access Rapiwa account with API access for WhatsApp verification and messaging Google account with Sheets access Customer phone numbers in WooCommerce (stored in billing.phone field) How to Use — Step-by-Step Setup Credentials Setup WooCommerce API: Configure WooCommerce API credentials in n8n (e.g., "WooCommerce (get customer)" and "WooCommerce (get customer data)") Rapiwa Bearer Auth: Create an HTTP Bearer credential with your Rapiwa API token Google Sheets OAuth2: Set up OAuth2 credentials for Google Sheets access Configure Google Sheets Ensure your sheet has the required columns as specified in the Google Sheet Column Structure section Verify Code Nodes Code (get paying_customer): Filters customers to include only those who have made purchases Get most buy product id & Clear Number: Identifies the most purchased product and cleans phone numbers Configure HTTP Request Nodes Get customer data: Verify the WooCommerce API endpoint for retrieving customer orders Get specific product data: Verify the WooCommerce API endpoint for product details Get specific product recommend latest product: Verify the WooCommerce API endpoint for finding latest products by category Check valid WhatsApp number Using Rapiwa: Verify the Rapiwa endpoint for WhatsApp number validation Rapiwa Sender: Verify the Rapiwa endpoint for sending messages Google Sheet Required Columns You’ll need two Google Sheets (or two tabs in one spreadsheet): A Google Sheet formatted like this ➤ sample The workflow uses a Google Sheet with the following columns to track coupon distribution: Both must have the following headers (match exactly): | name | number | email | address1 | price | suk | title | product link | validity | staus | | ---------- | ------------- | ----------------------------------------------- | ----------- | ----- | --- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------- | -------- | | Abdul Mannan | 8801322827799 | contact@spagreen.net | mirpur dohs | 850 | | Sharp Most Demanding Hoodie x Nike | https://yourshopdomain/p-img-nike | verified | sent | | Abdul Mannan | 8801322827799 | contact@spagreen.net | mirpur dohs | 850 | | Sharp Most Demanding Hoodie x Nike | https://yourshopdomain/p-img-nike | unverified | not sent | | Abdul Mannan | 8801322827799 | contact@spagreen.net | mirpur dohs | 850 | | Sharp Most Demanding Hoodie x Nike | https://yourshopdomain/p-img-nike | verified | sent | Important Notes Phone Number Format: The workflow cleans phone numbers by removing all non-digit characters. Ensure your WooCommerce phone numbers are in a compatible format. API Rate Limits: Rapiwa and WooCommerce APIs have rate limits. Adjust batch sizes and wait times accordingly. Data Privacy: Ensure compliance with data protection regulations when sending marketing messages. Error Handling: The workflow logs unverified numbers but doesn't have extensive error handling. Consider adding error notifications for failed API calls. Product Availability: The workflow recommends the latest product in a category, but doesn't check if it's in stock. Consider adding stock status verification. Testing: Always test with a small batch before running the workflow on your entire customer list. Useful Links Dashboard: https://app.rapiwa.com Official Website: https://rapiwa.com Documentation: https://docs.rapiwa.com Support & Help WhatsApp: Chat on WhatsApp Discord: SpaGreen Community Facebook Group: SpaGreen Support Website: https://spagreen.net Developer Portfolio: Codecanyon SpaGreen
Track SDK documentation drift with GitHub, Notion, Google Sheets, and Slack
📊 Description Automatically track SDK releases from GitHub, compare documentation freshness in Notion, and send Slack alerts when docs lag behind. This workflow ensures documentation stays in sync with releases, improves visibility, and reduces version drift across teams. 🚀📚💬 What This Template Does Step 1: Listens to GitHub repository events to detect new SDK releases. 🧩 Step 2: Fetches release metadata including version, tag, and publish date. 📦 Step 3: Logs release data into Google Sheets for record-keeping and analysis. 📊 Step 4: Retrieves FAQ or documentation data from Notion. 📚 Step 5: Merges GitHub and Notion data to calculate documentation drift. 🔍 Step 6: Flags SDKs whose documentation is over 30 days out of date. ⚠️ Step 7: Sends detailed Slack alerts to notify responsible teams. 🔔 Key Benefits ✅ Keeps SDK documentation aligned with product releases ✅ Prevents outdated information from reaching users ✅ Provides centralized release tracking in Google Sheets ✅ Sends real-time Slack alerts for overdue updates ✅ Strengthens DevRel and developer experience operations Features GitHub release trigger for real-time monitoring Google Sheets logging for tracking and auditing Notion database integration for documentation comparison Automated drift calculation (days since last update) Slack notifications for overdue documentation Requirements GitHub OAuth2 credentials Notion API credentials Google Sheets OAuth2 credentials Slack Bot token with chat:write permissions Target Audience Developer Relations (DevRel) and SDK engineering teams Product documentation and technical writing teams Project managers tracking SDK and doc release parity Step-by-Step Setup Instructions Connect your GitHub account and select your SDK repository. Replace YOURGOOGLESHEETID and YOURSHEET_GID with your tracking spreadsheet. Add your Notion FAQ database ID. Configure your Slack channel ID for alerts. Run once manually to validate setup, then enable automation.
Automate Gmail responses with GPT and human-in-the-loop verification
Try It Out! This n8n template uses AI to automatically respond to your Gmail inbox by drafting response for your approval via email. How it works Gmail Trigger monitors your inbox for new emails AI Analysis determines if a response is needed based on your criteria Draft Generation creates contextually appropriate replies using your business information Human Approval sends you the draft for review before sending Auto-Send replies automatically once approved Setup Connect your Gmail account to the Gmail Trigger node Update the "Your Information" node with: Entity name and description Approval email address Resource guide (FAQs, policies, key info) Response guidelines (tone, style, formatting preferences) Configure your LLM provider (OpenAI, Claude, Gemini, etc.) with API credentials Test with a sample email Requirements n8n instance (self-hosted or cloud) Gmail account with API access LLM provider API key Need Help? Email Nick @ nick@tropicflare.com