This workflow follows the Chainllm → OpenAI Chat recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "154458b0-dde3-4224-9fa8-d38a025aa0d3",
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
-640,
-140
],
"parameters": {
"rule": {
"interval": [
{
"field": "hours"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "0fc88546-50ef-4183-8fb2-dcea939f3bcf",
"name": "Get Recent Messages",
"type": "n8n-nodes-base.microsoftOutlook",
"position": [
-440,
-140
],
"parameters": {
"fields": [
"body",
"categories",
"conversationId",
"from",
"hasAttachments",
"internetMessageId",
"sender",
"subject",
"toRecipients",
"receivedDateTime",
"webLink"
],
"output": "fields",
"options": {},
"filtersUI": {
"values": {
"filters": {
"receivedAfter": "={{ $now.minus({ \"hour\": 1 }).toISO() }}"
}
}
},
"operation": "getAll"
},
"credentials": {
"microsoftOutlookOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "d056be7e-43ed-4fea-8aef-36579c656633",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
280,
40
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "e4b6fd9d-2506-45bf-bd80-a81a2c04306b",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
480,
40
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n \"type\": \"object\",\n \"properties\": {\n \"labels\": {\n \"type\": \"array\",\n \"items\": { \"type\": \"string\" }\n },\n \"priority\": { \"type\": \"number\" },\n \"summary\": { \"type\": \"string\" },\n \"description\": { \"type\": \"string\" }\n }\n}"
},
"typeVersion": 1.2
},
{
"id": "3cef25fc-2581-4556-bf54-7704815d98b3",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
-340
],
"parameters": {
"color": 7,
"width": 700,
"height": 540,
"content": "## 2. Automate Generation and Triaging of Ticket\n[Read more about the Basic LLM node](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainllm)\n\nNew tickets always need to be properly labelled and prioritised but it's not always possible to get to update all incoming tickets if you're light on hands. Using an AI is a great use-case for triaging of tickets as its contextual understanding helps automates this step."
},
"typeVersion": 1
},
{
"id": "d6ba8c9b-3e39-442f-8b79-cafe11c15a18",
"name": "Markdown",
"type": "n8n-nodes-base.markdown",
"position": [
100,
-140
],
"parameters": {
"html": "={{ $json.body.content }}",
"options": {}
},
"typeVersion": 1
},
{
"id": "fb7c6d7c-df30-43de-8f37-9e394a8ad7aa",
"name": "Create Issue",
"type": "n8n-nodes-base.jira",
"position": [
900,
-140
],
"parameters": {
"project": {
"__rl": true,
"mode": "id",
"value": "10000"
},
"summary": "={{ $json.output.summary }}",
"issueType": {
"__rl": true,
"mode": "id",
"value": "10000"
},
"additionalFields": {
"labels": "={{ $json.output.labels }}",
"priority": {
"__rl": true,
"mode": "id",
"value": "={{ $json.output.priority }}"
},
"description": "={{ $json.output.description }}"
}
},
"credentials": {
"jiraSoftwareCloudApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "9e26f402-36da-40e1-a736-db4fe16de54a",
"name": "Mark as Seen",
"type": "n8n-nodes-base.removeDuplicates",
"position": [
-240,
-140
],
"parameters": {
"options": {},
"operation": "removeItemsSeenInPreviousExecutions",
"dedupeValue": "={{ $json.id }}"
},
"typeVersion": 2
},
{
"id": "b5f49877-e494-4712-a937-1f348198700e",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-740,
-340
],
"parameters": {
"color": 7,
"width": 720,
"height": 540,
"content": "## 1. Watch Outlook Inbox for Support Emails\n[Learn more about the Outlook node](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.microsoftoutlook/)\n\n**This template assumes a shared inbox specifically for support tickets!** If you have a general inbox, you may need to classify and filter each message which might become costly. The \"remove duplicates\" node (ie. \"Mark as seen\") ensures we only process each email exactly once."
},
"typeVersion": 1
},
{
"id": "b9d08834-14ad-4cdf-bc20-411033eee5b7",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
720,
-340
],
"parameters": {
"color": 7,
"width": 460,
"height": 440,
"content": "## 3. Create Issue in JIRA\n[Read more about the JIRA node](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.jira/)\n\nThis is only a simple example to create an issue in JIRA but easily extendable to add much more!"
},
"typeVersion": 1
},
{
"id": "e6942a39-1893-44cf-a846-c6b4d9c37e92",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1160,
-720
],
"parameters": {
"width": 380,
"height": 940,
"content": "## Try It Out!\n### This n8n template watches an outlook shared inbox for support messages and creates an equivalent issue item in JIRA.\n\n### How it works\n* A scheduled trigger fetches recent Outlook messages from an shared inbox which collects support requests.\n* These support requests are filtered to ensure they are only processed once and their HTML body is converted to markdown for easier parsing.\n* Each support request is then triaged via an AI Agent which adds appropriate labels, assesses priority and summarises a title and description of the original request.\n* Finally, the AI generated values are used to create an issue in JIRA to be actioned.\n\n### How to use\n* Ensure the messages fetched are solely support requests otherwise you'll need to classify messages before processing them.\n* Specify the labels and priorities to use in the system prompt of the AI agent.\n\n### Requirements\n* Outlook for incoming support\n* OpenAI for LLM\n* JIRA for issue management\n\n### Customising this workflow\n* Consider automating more steps after the issue is created such as attempting issue resolution or capacity planning.\n\n\n### Need Help?\nJoin the [Discord](https://discord.com/invite/XPKeKXeB7d) or ask in the [Forum](https://community.n8n.io/)!\n\nHappy Hacking!"
},
"typeVersion": 1
},
{
"id": "71a906b2-7b01-43a8-aa82-7d9810d95e23",
"name": "Generate Issue From Support Request",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
300,
-140
],
"parameters": {
"text": "=Reported by {{ $json.from.emailAddress.name }} <{{ $json.from.emailAddress.address }}>\nReported at: {{ $now.toISO() }}\nSummary: {{ $json.subject }}\nDescription:\n{{ $json.data.replaceAll('\\n', ' ') }}",
"messages": {
"messageValues": [
{
"message": "=Your are JIRA triage assistant who's task is to\n1) classify and label the given issue.\n2) Prioritise the given issue.\n3) Rewrite the issue summary and description.\n\n## Labels\nUse one or more. Use words wrapped in \"[]\" (square brackets):\n* Technical\n* Account\n* Access\n* Billing\n* Product\n* Training\n* Feedback\n* Complaints\n* Security\n* Privacy\n\n## Priority\n* 1 - highest\n* 2 - high\n* 3 - medium\n* 4 - low\n* 5 - lowest\n\n## Write Summary and Description\n* Remove emotional and anedotal phrases or information\n* Keep to the facts of the matter\n* Highlight what was attempted and is/was failing"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.6
}
],
"connections": {
"Markdown": {
"main": [
[
{
"node": "Generate Issue From Support Request",
"type": "main",
"index": 0
}
]
]
},
"Mark as Seen": {
"main": [
[
{
"node": "Markdown",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "Get Recent Messages",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Generate Issue From Support Request",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Get Recent Messages": {
"main": [
[
{
"node": "Mark as Seen",
"type": "main",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Generate Issue From Support Request",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Generate Issue From Support Request": {
"main": [
[
{
"node": "Create Issue",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
jiraSoftwareCloudApimicrosoftOutlookOAuth2ApiopenAiApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow automatically scans your Microsoft Outlook inbox for recent duplicate emails, uses OpenAI to intelligently identify and categorise them, then creates Jira issues to track resolutions while marking duplicates as seen to prevent reprocessing. It's ideal for teams overwhelmed by repetitive correspondence, such as support or sales groups, saving hours of manual deduplication and ensuring nothing slips through. The key step involves the AI-powered analysis that parses email content to flag true duplicates beyond simple subject matching.
Use this workflow when you receive high volumes of similar emails daily and need automated triage integrated with project management tools like Jira. Avoid it for low-volume inboxes or when emails require human nuance that AI might miss, such as subtle contextual differences. Common variations include adjusting the cron schedule for hourly runs or adding filters for specific senders to focus on priority threads.
About this workflow
Schedule Removeduplicates. Uses scheduleTrigger, microsoftOutlook, lmChatOpenAi, outputParserStructured. Scheduled trigger; 12 nodes.
Source: https://github.com/Zie619/n8n-workflows — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Schedule Removeduplicates. Uses scheduleTrigger, jira, lmChatOpenAi, outputParserStructured. Scheduled trigger; 27 nodes.
Video Automation (images only). Uses chainLlm, lmChatOpenAi, outputParserStructured, splitOut. Scheduled trigger; 28 nodes.
This workflow is designed for animal advocacy organizations, activists, and campaigners who want to automatically receive a weekly email update summarizing the latest news and developments related to
Blog Automation TEMPLATE. Uses scheduleTrigger, manualTrigger, googleSheets, lmChatOpenAi. Scheduled trigger; 35 nodes.
Blog Automation TEMPLATE. Uses scheduleTrigger, manualTrigger, googleSheets, lmChatOpenAi. Scheduled trigger; 35 nodes.