Davide Boizza This workflow corresponds to n8n.io template #2861 — we link there as the canonical source.
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": "OuHrYOR3uWGmrhWQ",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "AI Email processing autoresponder with approval (Yes/No)",
"tags": [],
"nodes": [
{
"id": "06a098db-160b-45f7-aeac-a73ef868148e",
"name": "Email Trigger (IMAP)",
"type": "n8n-nodes-base.emailReadImap",
"position": [
-180,
-100
],
"parameters": {
"options": {}
},
"credentials": {
"imap": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "9589443b-efb7-4e0d-bafc-0be9858a4755",
"name": "Markdown",
"type": "n8n-nodes-base.markdown",
"position": [
40,
-100
],
"parameters": {
"html": "={{ $json.textHtml }}",
"options": {}
},
"typeVersion": 1
},
{
"id": "8de7b2f3-bf75-4f3c-a1ee-eec047a7b82e",
"name": "DeepSeek R1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
240,
80
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "deepseek/deepseek-r1:free",
"cachedResultName": "deepseek/deepseek-r1:free"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "babf37dc-99ca-439a-b094-91c52799b8df",
"name": "Send Email",
"type": "n8n-nodes-base.emailSend",
"position": [
1840,
-120
],
"parameters": {
"html": "={{ $('Write email').item.json.output }}",
"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": "ebeb986d-053a-420d-8482-ee00e75f2f10",
"name": "Qdrant Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
1180,
200
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"toolName": "company_knowladge_base",
"toolDescription": "Extracts information regarding the request made.",
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "=COLLECTION"
},
"includeDocumentMetadata": false
},
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "ccc3d026-bfa3-4fda-be0a-ef70bf831aa7",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
1180,
380
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "1726aac9-a77d-4f19-8c07-70b032c3abeb",
"name": "Email Summarization Chain",
"type": "@n8n/n8n-nodes-langchain.chainSummarization",
"position": [
260,
-100
],
"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": "81b889d0-e724-4c1f-9ce3-7593c796aaaf",
"name": "Write email",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
980,
-100
],
"parameters": {
"text": "=Write the text to reply to the following email:\n\n{{ $('Email Summarization Chain').item.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.\n\nIt must be in HTML format and you can insert (if you think it is appropriate) only HTML characters such as <br>, <b>, <i>, <p> where necessary."
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.7
},
{
"id": "cf38e319-59b3-490e-b841-579afc9fbc02",
"name": "OpenAI",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
980,
200
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "19842e5f-c372-4dfd-b860-87dc5f00b1af",
"name": "Set Email",
"type": "n8n-nodes-base.set",
"position": [
760,
-100
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "759dc0f9-f582-492c-896c-6426f8410127",
"name": "email",
"type": "string",
"value": "={{ $json.response.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "2cf7a9af-c5e8-45dd-bda5-01c562a0defb",
"name": "Approve?",
"type": "n8n-nodes-base.if",
"position": [
1560,
-100
],
"parameters": {
"options": {
"ignoreCase": false
},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "5c377c1c-43c6-45e7-904e-dbbe6b682686",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.data.approved }}",
"rightValue": "true"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "08cabec6-9840-4214-8315-b877c86794bf",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-220,
-680
],
"parameters": {
"color": 3,
"width": 580,
"height": 420,
"content": "# Main Flow\n\n## Preliminary step:\nCreate a vector database on Qdrant and tokenize the documents useful for generating a response\n\n\n## How it works\nThis workflow is designed to automate the process of handling incoming emails, summarizing their content, generating appropriate responses with RAG, and obtaining approval (YES/NO button) before sending replies.\n\nThis workflow is designed to handle general inquiries that come in via corporate email via IMAP and generate responses using RAG. You can quickly integrate Gmail and Outlook via the appropriate trigger nodes"
},
"typeVersion": 1
},
{
"id": "80692c8f-e236-43ac-aad2-91bd90f40065",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-40,
-180
],
"parameters": {
"height": 240,
"content": "Convert email to Markdown format for better understanding of LLM models"
},
"typeVersion": 1
},
{
"id": "e6957fde-bf05-4b67-aa0e-44c575fca04d",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
240,
-180
],
"parameters": {
"width": 320,
"height": 240,
"content": "Chain that summarizes the received email"
},
"typeVersion": 1
},
{
"id": "7cfba59f-83ce-4f0b-b54a-b2c11d58fd82",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
940,
-180
],
"parameters": {
"width": 340,
"height": 240,
"content": "Agent that retrieves business information from a vector database and processes the response"
},
"typeVersion": 1
},
{
"id": "28c4bd00-6a47-422f-a50a-935f3724ba01",
"name": "Send Draft",
"type": "n8n-nodes-base.gmail",
"position": [
1340,
-100
],
"parameters": {
"sendTo": "YOUR GMAIL ADDRESS",
"message": "=<h3>MESSAGE</h3>\n{{ $('Email Trigger (IMAP)').item.json.textHtml }}\n\n<h3>AI RESPONSE</h3>\n{{ $json.output }}",
"options": {},
"subject": "=[Approval Required] {{ $('Email Trigger (IMAP)').item.json.subject }}",
"operation": "sendAndWait",
"approvalOptions": {
"values": {
"approvalType": "double"
}
}
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "0aae1689-cee7-403a-8640-396db32eceed",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1300,
-300
],
"parameters": {
"color": 4,
"height": 360,
"content": "## IMPORTANT\n\nFor the \"Send Draft\" node, you need to send the draft email to a Gmail address because it is the only one that allows the \"Send and wait for response\" function."
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "6f7b864e-1589-418c-960e-b832cf032d1b",
"connections": {
"OpenAI": {
"ai_languageModel": [
[
{
"node": "Write email",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Approve?": {
"main": [
[
{
"node": "Send Email",
"type": "main",
"index": 0
}
],
[
{
"node": "Set Email",
"type": "main",
"index": 0
}
]
]
},
"Markdown": {
"main": [
[
{
"node": "Email Summarization Chain",
"type": "main",
"index": 0
}
]
]
},
"Set Email": {
"main": [
[
{
"node": "Write email",
"type": "main",
"index": 0
}
]
]
},
"Send Draft": {
"main": [
[
{
"node": "Approve?",
"type": "main",
"index": 0
}
]
]
},
"DeepSeek R1": {
"ai_languageModel": [
[
{
"node": "Email Summarization Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Write email": {
"main": [
[
{
"node": "Send Draft",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Qdrant Vector Store": {
"ai_tool": [
[
{
"node": "Write email",
"type": "ai_tool",
"index": 0
}
]
]
},
"Email Trigger (IMAP)": {
"main": [
[
{
"node": "Markdown",
"type": "main",
"index": 0
}
]
]
},
"Email Summarization Chain": {
"main": [
[
{
"node": "Set 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.
gmailOAuth2imapopenAiApiqdrantApismtp
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow is designed to automate the process of handling incoming emails, summarizing their content, generating appropriate responses, and obtaining approval before sending replies. Below are the key operational steps: Email Reception and Summarization: The workflow starts…
Source: https://n8n.io/workflows/2861/ — 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.
AI Email processing autoresponder with approval (Yes/No). Uses emailReadImap, markdown, lmChatOpenAi, emailSend. Manual trigger; 17 nodes.
Email Read Imap, OpenAI Chat, Email Send +5
AI Email processing autoresponder with approval (Yes/No). Uses emailReadImap, markdown, lmChatOpenAi, emailSend. Manual trigger; 17 nodes.
Email Read Imap, OpenAI Chat, Email Send +5
Effortless Email Management with AI. Uses emailReadImap, markdown, emailSend, vectorStoreQdrant. Event-driven trigger; 31 nodes.
Email Read Imap, Email Send, Qdrant Vector Store +11
Effortless Email Management with AI. Uses emailReadImap, markdown, emailSend, vectorStoreQdrant. Event-driven trigger; 31 nodes.
Email Read Imap, Email Send, Qdrant Vector Store +11
This workflow automates the handling of incoming emails, summarizes their content, generates appropriate responses using a retrieval-augmented generation (RAG) approach, and obtains approval or sugges
Email Read Imap, Email Send, Qdrant Vector Store +11