This workflow follows the Emailreadimap → Emailsend 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 →
{
"name": "HR Knowledge Assistant with Sentiment & Fake Jira",
"nodes": [
{
"parameters": {
"protocol": "IMAP",
"action": "read",
"downloadAttachments": false
},
"id": "EmailTrigger",
"name": "Email Trigger",
"type": "n8n-nodes-base.emailReadImap",
"typeVersion": 1,
"position": [
250,
300
],
"credentials": {
"imap": "<your credential>"
}
},
{
"parameters": {
"path": "/data/hr_docs/*.txt",
"options": {}
},
"id": "ReadHRDocs",
"name": "Read HR Docs",
"type": "n8n-nodes-base.readBinaryFiles",
"typeVersion": 1,
"position": [
500,
150
]
},
{
"parameters": {
"options": {
"encoding": "utf8"
}
},
"id": "BinaryToText",
"name": "Binary \u2192 Text",
"type": "n8n-nodes-base.moveBinaryData",
"typeVersion": 1,
"position": [
700,
150
]
},
{
"parameters": {
"mode": "mergeByIndex",
"propertyName": "data"
},
"id": "MergeDocs",
"name": "Merge Docs",
"type": "n8n-nodes-base.merge",
"typeVersion": 2,
"position": [
900,
150
]
},
{
"parameters": {
"model": "claude-3-opus-20240229",
"prompt": "You are an HR assistant. Answer the employee's question strictly using the following HR policy documents:\n\n{{$json[\"data\"]}}\n\nEmployee Question: {{$node[\"Email Trigger\"].json[\"text\"]}}",
"temperature": 0.2
},
"id": "ClaudeAnswer",
"name": "Claude Answer",
"type": "n8n-nodes-base.anthropic",
"typeVersion": 1,
"position": [
1150,
150
],
"credentials": {
"anthropicApi": "<your credential>"
}
},
{
"parameters": {
"model": "claude-3-opus-20240229",
"prompt": "Classify the sentiment of this employee's email as one of: angry, neutral, happy.\n\nEmail: {{$node[\"Email Trigger\"].json[\"text\"]}}",
"temperature": 0
},
"id": "ClaudeSentiment",
"name": "Claude Sentiment",
"type": "n8n-nodes-base.anthropic",
"typeVersion": 1,
"position": [
1150,
400
],
"credentials": {
"anthropicApi": "<your credential>"
}
},
{
"parameters": {
"conditions": {
"string": [
{
"value1": "{{$json[\"completion\"]}}",
"operation": "contains",
"value2": "angry"
}
]
}
},
"id": "IfAngry",
"name": "If Angry",
"type": "n8n-nodes-base.if",
"typeVersion": 1,
"position": [
1400,
400
]
},
{
"parameters": {
"values": {
"string": [
{
"name": "jira_ticket_id",
"value": "JIRA-{{$json[\"id\"] || $json[\"random\"] || Math.floor(Math.random()*10000)}}"
}
]
},
"options": {}
},
"id": "FakeJira",
"name": "Fake Jira Ticket",
"type": "n8n-nodes-base.set",
"typeVersion": 2,
"position": [
1600,
250
]
},
{
"parameters": {
"fromEmail": "hr-assistant@yourcompany.com",
"toEmail": "{{$node[\"Email Trigger\"].json[\"from\"]}}",
"subject": "HR Policy Answer",
"text": "Here is the answer to your HR query:\n\n{{$node[\"Claude Answer\"].json[\"completion\"]}}\n\n{{ $json[\"jira_ticket_id\"] ? \"A Jira ticket was also created: \" + $json[\"jira_ticket_id\"] : \"\" }}"
},
"id": "EmailReply",
"name": "Email Reply",
"type": "n8n-nodes-base.emailSend",
"typeVersion": 1,
"position": [
1850,
250
],
"credentials": {
"smtp": "<your credential>"
}
}
],
"connections": {
"Email Trigger": {
"main": [
[],
[]
]
},
"Read HR Docs": {
"main": [
[
{
"node": "Binary \u2192 Text",
"type": "main",
"index": 0
}
]
]
},
"Binary \u2192 Text": {
"main": [
[
{
"node": "Merge Docs",
"type": "main",
"index": 0
}
]
]
},
"Merge Docs": {
"main": [
[
{
"node": "Claude Answer",
"type": "main",
"index": 0
}
]
]
},
"Claude Answer": {
"main": [
[
{
"node": "Email Reply",
"type": "main",
"index": 0
}
]
]
},
"Claude Sentiment": {
"main": [
[
{
"node": "If Angry",
"type": "main",
"index": 0
}
]
]
},
"If Angry": {
"main": [
[
{
"node": "Fake Jira Ticket",
"type": "main",
"index": 0
}
],
[]
]
},
"Fake Jira Ticket": {
"main": [
[
{
"node": "Email Reply",
"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.
anthropicApiimapsmtp
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
HR Knowledge Assistant with Sentiment & Fake Jira. Uses emailReadImap, readBinaryFiles, moveBinaryData, anthropic. Manual trigger; 9 nodes.
Source: https://gist.github.com/ananya170/6b11083fd76f12b0467b11af0c385ffd — 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.
This workflow template is designed for business owners and HR professionals to automatically detect and structure unstructured job applications received through email. Additionally, other email catego
Personal Assistant with Long-Term Memory (StudioMeyer). Uses stickyNote, telegramTrigger, n8n-nodes-studiomeyer-memory, telegram. Event-driven trigger; 26 nodes.
1978. Uses informationExtractor, lmChatOpenAi, stopAndError, httpRequest. Event-driven trigger; 24 nodes.
This workflow uses AI to analyze customer sentiment from product feedback. If the sentiment is negative, AI will determine whether offering a coupon could improve the customer experience.
Use cases are many: Perfect for freelancers managing client invoices, small businesses handling supplier bills, accounting departments processing high invoice volumes, or anyone who wants to eliminate