This workflow follows the Agent → Chainsummarization 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 →
{
"id": "Nvn78tMRNnKji7Fg",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Very simple Human in the loop system email with AI e IMAP",
"tags": [],
"nodes": [
{
"id": "271bb16f-9b62-41d9-ab76-114cd7ba915a",
"name": "Email Trigger (IMAP)",
"type": "n8n-nodes-base.emailReadImap",
"position": [
-1300,
1340
],
"parameters": {
"options": {}
},
"credentials": {
"imap": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "42d150d8-d574-49f9-9c0e-71a2cdea3b79",
"name": "Markdown",
"type": "n8n-nodes-base.markdown",
"position": [
-1040,
1340
],
"parameters": {
"html": "={{ $json.textHtml }}",
"options": {}
},
"typeVersion": 1
},
{
"id": "e9498a60-0078-4581-b269-7ff552f4047a",
"name": "Send Email",
"type": "n8n-nodes-base.emailSend",
"position": [
920,
1320
],
"parameters": {
"html": "={{ $('Set Email text').item.json.email }}",
"options": {},
"subject": "=Re: {{ $('Email Trigger (IMAP)').item.json.subject }}",
"toEmail": "={{ $('Email Trigger (IMAP)').item.json.from }}",
"fromEmail": "={{ $('Email Trigger (IMAP)').item.json.to }}"
},
"credentials": {
"smtp": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "ab9f6ac3-2095-44df-aeba-2eab96ecf425",
"name": "Email Summarization Chain",
"type": "@n8n/n8n-nodes-langchain.chainSummarization",
"position": [
-780,
1340
],
"parameters": {
"options": {
"binaryDataKey": "={{ $json.data }}",
"summarizationMethodAndPrompts": {
"values": {
"prompt": "=Write a concise summary of the following in max 100 words:\n\n\"{{ $json.data }}\"\n\nDo not enter the total number of words used.",
"combineMapPrompt": "=Write a concise summary of the following in max 100 words:\n\n\"{{ $json.data }}\"\n\nDo not enter the total number of words used."
}
}
},
"operationMode": "nodeInputBinary"
},
"typeVersion": 2
},
{
"id": "86b7c3d0-e1f2-4e2f-b293-8042700d6816",
"name": "Write email",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-340,
1340
],
"parameters": {
"text": "=Write the text to reply to the following email:\n\n{{ $json.response.text }}",
"options": {
"systemMessage": "You are an expert at answering emails. You need to answer them professionally based on the information you have. This is a business email. Be concise and never exceed 100 words. Only the body of the email, not create the subject"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.7
},
{
"id": "5d5a397f-f9c3-4691-afd0-9a6102679eac",
"name": "OpenAI",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-400,
1560
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "5b36a295-fda6-4174-9078-0a8ec57620d2",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-800,
1260
],
"parameters": {
"width": 320,
"height": 240,
"content": "Chain that summarizes the received email"
},
"typeVersion": 1
},
{
"id": "7110fe1f-0099-49aa-9095-96e733aa468f",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-360,
1260
],
"parameters": {
"width": 340,
"height": 240,
"content": "Agent that retrieves business information from a vector database and processes the response"
},
"typeVersion": 1
},
{
"id": "e2bdbd64-3c37-4867-ae2c-0f6937d82b81",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1100,
1260
],
"parameters": {
"height": 240,
"content": "Convert email to Markdown format for better understanding of LLM models"
},
"typeVersion": 1
},
{
"id": "8ae5d216-5897-4c33-800a-27ff939b174a",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
620,
1300
],
"parameters": {
"height": 180,
"content": "If the feedback is OK send email"
},
"typeVersion": 1
},
{
"id": "4cfce63c-5931-45c5-99ca-eb85dca962b5",
"name": "Approve Email",
"type": "n8n-nodes-base.emailSend",
"position": [
380,
1340
],
"parameters": {
"message": "=<h3>MESSAGE</h3>\n{{ $('Email Trigger (IMAP)').item.json.textHtml }}\n\n<h3>AI RESPONSE</h3>\n{{ $json.email }}",
"options": {},
"subject": "=[Approval Required] {{ $('Email Trigger (IMAP)').item.json.subject }}",
"toEmail": "info@n3witalia.com",
"fromEmail": "info@n3witalia.com",
"operation": "sendAndWait"
},
"credentials": {
"smtp": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "d6c8acd2-ebc1-4aaa-bfcc-cdb18fcc8715",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-820,
1560
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "deepseek-chat",
"cachedResultName": "deepseek-chat"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "33bbedeb-129a-4e99-ab5a-9e0ec4456156",
"name": "Set Email text",
"type": "n8n-nodes-base.set",
"position": [
100,
1340
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "35d7c303-42f4-4dd1-b41e-6eb087c23c3d",
"name": "email",
"type": "string",
"value": "={{ $json.output }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "2293e0e6-4f2a-4622-a610-64b65f34e1e5",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
320,
1300
],
"parameters": {
"height": 180,
"content": "Human in the loop"
},
"typeVersion": 1
},
{
"id": "510196ec-adaf-4e6c-aac0-8ca8b754438a",
"name": "Sticky Note11",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1100,
940
],
"parameters": {
"color": 3,
"width": 540,
"height": 260,
"content": "# How it works\nThis workflow automates the handling of incoming emails, summarizes their content, generates appropriate responses and validate it through send IMAP email with \"Human in the loop\" system. \n\nYou can quickly integrate Gmail and Outlook via the appropriate nodes"
},
"typeVersion": 1
},
{
"id": "c4c9157d-4d05-47a1-a5eb-63865e838d39",
"name": "Approved?",
"type": "n8n-nodes-base.if",
"position": [
680,
1340
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "62e26bc5-1732-4699-a602-99490c7406fd",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.data.approved }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "47e79286-00f4-48e8-a0d1-e0f56d9ba0d5",
"connections": {
"OpenAI": {
"ai_languageModel": [
[
{
"node": "Write email",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Markdown": {
"main": [
[
{
"node": "Email Summarization Chain",
"type": "main",
"index": 0
}
]
]
},
"Approved?": {
"main": [
[
{
"node": "Send Email",
"type": "main",
"index": 0
}
],
[]
]
},
"Write email": {
"main": [
[
{
"node": "Set Email text",
"type": "main",
"index": 0
}
]
]
},
"Approve Email": {
"main": [
[
{
"node": "Approved?",
"type": "main",
"index": 0
}
]
]
},
"Set Email text": {
"main": [
[
{
"node": "Approve Email",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Email Summarization Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Email Trigger (IMAP)": {
"main": [
[
{
"node": "Markdown",
"type": "main",
"index": 0
}
]
]
},
"Email Summarization Chain": {
"main": [
[
{
"node": "Write email",
"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.
imapopenAiApismtp
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow delivers a streamlined human-in-the-loop system that processes incoming emails with AI assistance, enabling you to review and respond efficiently without constant monitoring. It suits busy professionals or teams handling customer support, sales leads, or internal communications who need intelligent summaries and draft replies to prioritise high-value tasks. The core step involves using the emailReadImap integration to fetch new messages, followed by chainSummarization with OpenAI to generate concise markdown overviews, then prompting you via emailSend for approval before finalising responses.
Use this workflow when you receive moderate email volumes requiring thoughtful replies, such as drafting personalised follow-ups based on AI insights, to save time on routine processing. Avoid it for high-volume inboxes needing instant automation or complex multi-step approvals, where more robust tools like dedicated ticketing systems would be better. Common variations include swapping OpenAI for another LLM or adding conditional routing based on email content for targeted handling.
About this workflow
Very simple Human in the loop system email with AI e IMAP. Uses emailReadImap, markdown, emailSend, chainSummarization. Manual trigger; 16 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.
Very simple Human in the loop system email with AI e IMAP. Uses emailReadImap, markdown, emailSend, chainSummarization. Manual trigger; 16 nodes.
This workflow automates the handling of incoming emails by summarizing their content, generating appropriate responses, and validating the responses through a "Human-in-the-Loop" system. It integrates
How it works
K&S-Media Downloadliste SQL. Uses httpRequest, agent, googleSheets, lmChatOpenAi. Event-driven trigger; 97 nodes.
This template is built for solo attorneys, small law firms, and legal billing coordinators who receive timesheet documents by email and need to produce LEDES-compliant e-billing files for client billi