Rahn Brosh | Kitebolt This workflow corresponds to n8n.io template #17599 — we link there as the canonical source.
This workflow follows the Gmail → Gmail Trigger 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": "RFQ Intake: AI Extraction, Completeness Check & Quote Draft (template)",
"tags": [],
"nodes": [
{
"id": "d7767db4-ace9-44c0-8a11-e9cf828211b0",
"name": "New RFQ Email",
"type": "n8n-nodes-base.gmailTrigger",
"position": [
16,
32
],
"parameters": {
"simple": false,
"filters": {
"q": "subject:(RFQ OR \"request for quote\" OR quote)",
"readStatus": "unread"
},
"options": {
"downloadAttachments": true,
"dataPropertyAttachmentsPrefixName": "attachment_"
},
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
}
},
"typeVersion": 1.4
},
{
"id": "bce57e34-c2de-4a1b-9b0b-b53c51c29d6d",
"name": "Normalize Email",
"type": "n8n-nodes-base.set",
"position": [
224,
32
],
"parameters": {
"options": {
"stripBinary": false
},
"assignments": {
"assignments": [
{
"id": "a1",
"name": "email_text",
"type": "string",
"value": "={{ $json.text ?? $json.textAsHtml ?? $json.snippet ?? \"\" }}"
},
{
"id": "a2",
"name": "from_email",
"type": "string",
"value": "={{ $json.from?.value?.[0]?.address ?? $json.from?.text ?? \"\" }}"
},
{
"id": "a3",
"name": "subject_line",
"type": "string",
"value": "={{ $json.subject ?? \"\" }}"
},
{
"id": "a4",
"name": "thread_id",
"type": "string",
"value": "={{ $json.threadId ?? $json.id }}"
},
{
"id": "a5",
"name": "received_at",
"type": "string",
"value": "={{ $json.date ?? $now.toISO() }}"
}
]
},
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "8d47dbfc-5b72-40ca-b289-ba13b2282a16",
"name": "Has PDF Attachment?",
"type": "n8n-nodes-base.if",
"position": [
448,
32
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": false,
"typeValidation": "loose"
},
"combinator": "and",
"conditions": [
{
"id": "c1",
"operator": {
"type": "boolean",
"operation": "equals"
},
"leftValue": "={{ !!$binary?.attachment_0 }}",
"rightValue": true
},
{
"id": "c2",
"operator": {
"type": "string",
"operation": "contains"
},
"leftValue": "={{ $binary?.attachment_0?.mimeType ?? \"\" }}",
"rightValue": "pdf"
}
]
}
},
"typeVersion": 2.3
},
{
"id": "e422b607-560e-4f27-b21b-8e9843464c30",
"name": "Extract PDF Text",
"type": "n8n-nodes-base.extractFromFile",
"position": [
672,
32
],
"parameters": {
"options": {
"joinPages": true
},
"operation": "pdf",
"binaryPropertyName": "attachment_0"
},
"typeVersion": 1.1
},
{
"id": "6546d509-68a1-4454-9302-5bde892a7830",
"name": "Combine Email + PDF Text",
"type": "n8n-nodes-base.set",
"position": [
864,
32
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "b1",
"name": "rfq_text",
"type": "string",
"value": "={{ $('Normalize Email').item.json.email_text }}\n\n--- ATTACHED PDF ---\n{{ $json.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "7369ac4c-6180-4f81-800f-296b85a1577c",
"name": "Extract RFQ Fields",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
1104,
32
],
"parameters": {
"text": "={{ $json.rfq_text }}",
"options": {
"systemPromptTemplate": "You extract manufacturing RFQ data. Extract every value that is explicitly present in the text, exactly as written - part numbers, quantities, names, dates, addresses, packaging, prices. Use null ONLY for fields the text does not state. Never estimate, infer, or invent a value - a fabricated date, address, price, or packaging spec is a critical failure. Partial information is normal: extract what is there, null the rest."
},
"schemaType": "manual",
"inputSchema": "{\n \"type\": \"object\",\n \"properties\": {\n \"company\": { \"type\": [\"string\", \"null\"], \"description\": \"Requesting company name, only if explicitly written in the text. Null otherwise.\" },\n \"contact_name\": { \"type\": [\"string\", \"null\"], \"description\": \"Sender name, only if explicitly written. Null otherwise.\" },\n \"line_items\": {\n \"type\": \"array\",\n \"description\": \"One entry per requested part. Only parts explicitly mentioned in the text.\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"part_number\": { \"type\": [\"string\", \"null\"], \"description\": \"Exact part number as written. Null if none given.\" },\n \"description\": { \"type\": [\"string\", \"null\"], \"description\": \"Part description as written. Null if none given.\" },\n \"quantity\": { \"type\": [\"number\", \"null\"], \"description\": \"Quantity explicitly stated for this part. Null if not stated.\" },\n \"unit\": { \"type\": [\"string\", \"null\"], \"description\": \"Unit as written (pcs, kg, sets). Null if not stated.\" },\n \"target_price\": { \"type\": [\"string\", \"null\"], \"description\": \"Target price ONLY if the text states one for this part. Null if not stated.\" }\n }\n }\n },\n \"need_by_date\": { \"type\": [\"string\", \"null\"], \"description\": \"Required delivery date, only if a date appears in the text. Null otherwise.\" },\n \"ship_to_address\": { \"type\": [\"string\", \"null\"], \"description\": \"Delivery address, only if one appears in the text. Null otherwise.\" },\n \"packaging_spec\": { \"type\": [\"string\", \"null\"], \"description\": \"Packaging requirements, only if stated in the text. Null otherwise.\" },\n \"incoterms\": { \"type\": [\"string\", \"null\"], \"description\": \"Incoterms, only if stated. Null otherwise.\" },\n \"special_requirements\": { \"type\": [\"string\", \"null\"], \"description\": \"Certs, finishes, inspection requirements explicitly stated. Null otherwise.\" }\n }\n}"
},
"typeVersion": 1.2
},
{
"id": "9a26c6d8-b9b4-45bf-861b-6733c9d8b74a",
"name": "OpenAI Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1104,
272
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5.4-mini",
"cachedResultName": "gpt-5.4-mini"
},
"options": {},
"builtInTools": {}
},
"typeVersion": 1.3
},
{
"id": "c3db9863-db61-4c33-a1fc-ff5402bd3c74",
"name": "Use Email Text Only",
"type": "n8n-nodes-base.set",
"position": [
768,
256
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "d1",
"name": "rfq_text",
"type": "string",
"value": "={{ $json.email_text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "c3bad62c-f941-4561-918a-359e2e880511",
"name": "Completeness Gate",
"type": "n8n-nodes-base.code",
"position": [
1472,
32
],
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "// EDIT: fields required before an RFQ is quotable\nconst REQUIRED = [\n { key: \"line_items\", label: \"part numbers and quantities\" },\n { key: \"need_by_date\", label: \"need-by date\" },\n { key: \"ship_to_address\", label: \"ship-to address\" },\n { key: \"packaging_spec\", label: \"packaging requirements\" },\n];\n\nconst extracted = $json.output ?? $json;\nconst meta = $(\"Normalize Email\").item.json;\nconst isEmpty = (v) => v === null || v === undefined || (typeof v === \"string\" && v.trim() === \"\") || (Array.isArray(v) && v.length === 0);\n\nconst missing = [];\nfor (const req of REQUIRED) {\n if (isEmpty(extracted[req.key])) missing.push(req.label);\n}\nconst items = Array.isArray(extracted.line_items) ? extracted.line_items : [];\nif (items.length > 0 && items.some((li) => !li.quantity)) missing.push(\"quantity for every line item\");\n\nconst itemLines = items.map((li) =>\n \"- \" + (li.part_number || li.description || \"item\") + \" | qty: \" + (li.quantity || \"?\") + (li.unit ? \" \" + li.unit : \"\") + (li.target_price ? \" | target: \" + li.target_price : \"\") + \" | unit price: ____ | lead time: ____\"\n).join(\"\\n\");\n\nreturn { json: {\n ...extracted,\n line_items_json: JSON.stringify(items),\n line_items_text: itemLines,\n missing,\n missing_text: missing.map((m) => \"- \" + m).join(\"\\n\"),\n complete: missing.length === 0,\n from_email: meta.from_email,\n subject_line: meta.subject_line,\n thread_id: meta.thread_id,\n received_at: meta.received_at,\n} };"
},
"typeVersion": 2
},
{
"id": "45153586-78ad-4bea-a3fc-d769ce197944",
"name": "All Info Present?",
"type": "n8n-nodes-base.if",
"position": [
1680,
32
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "e1",
"operator": {
"type": "boolean",
"operation": "equals"
},
"leftValue": "={{ $json.complete }}",
"rightValue": true
}
]
}
},
"typeVersion": 2.3
},
{
"id": "0548361d-b5f6-4af0-8493-97b8bd0145dd",
"name": "Draft Quote Skeleton",
"type": "n8n-nodes-base.gmail",
"position": [
1968,
32
],
"parameters": {
"message": "=Hi,\n\nThanks for the RFQ - we have everything needed to quote. Working it up now.\n\nLine items:\n{{ $json.line_items_text }}\n\nNeed-by: {{ $json.need_by_date }}\nShip-to: {{ $json.ship_to_address }}\nPackaging: {{ $json.packaging_spec }}\n\n[INTERNAL: fill unit prices and lead times, delete this line, then send.]\n\nRegards,",
"options": {
"sendTo": "={{ $json.from_email }}",
"threadId": "={{ $json.thread_id }}"
},
"subject": "=Re: {{ $json.subject_line }}",
"resource": "draft"
},
"typeVersion": 2.2
},
{
"id": "837ebb25-4a46-450a-8914-8906e2f7e672",
"name": "Draft Missing-Info Request",
"type": "n8n-nodes-base.gmail",
"position": [
1968,
224
],
"parameters": {
"message": "=Hi,\n\nThanks for the RFQ. To quote accurately we still need:\n\n{{ $json.missing_text }}\n\nReply with the above and we will turn the quote around quickly.\n\nRegards,",
"options": {
"sendTo": "={{ $json.from_email }}",
"threadId": "={{ $json.thread_id }}"
},
"subject": "=Re: {{ $json.subject_line }}",
"resource": "draft"
},
"typeVersion": 2.2
},
{
"id": "6af4fedb-b74b-4fdd-9900-4a28c9078ece",
"name": "Main Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-496,
-176
],
"parameters": {
"width": 440,
"height": 960,
"content": "# RFQ Intake \u2192 Quote Prep\n\nReads incoming RFQ emails, extracts the fields a quote needs, and checks completeness. Complete RFQs get a quote reply draft; incomplete ones get a draft asking only for what is missing.\n\n## How it works\n1. Gmail polls for unread emails matching your RFQ search query.\n2. PDF attachments are extracted and appended to the email body.\n3. AI extracts line items, quantities, need-by date, ship-to, packaging and incoterms. Fields not stated stay null.\n4. A Code node compares the result against an editable REQUIRED list.\n5. Complete: the quote reply is drafted with all line items; you just add prices and lead times.\n6. Incomplete: a reply draft asks only for the missing fields.\n\nReplies are Gmail drafts only. Nothing sends without human review.\n\n## Setup\n1. Connect Gmail and OpenAI credentials.\n2. Adjust the trigger search query to match your RFQ emails.\n3. Edit the REQUIRED list in \"Completeness Gate\" to match your quoting needs.\n\n## Customize\n- Add or remove fields in the extraction schema and the gate.\n- Reword the two reply drafts.\n- Log each RFQ to a Data Table, sheet or CRM after the drafts."
},
"typeVersion": 1
},
{
"id": "047a3036-54af-4909-b6f5-8288b5f620a9",
"name": "Section Ingest",
"type": "n8n-nodes-base.stickyNote",
"position": [
-32,
-128
],
"parameters": {
"color": 7,
"width": 400,
"height": 320,
"content": "### 1. Ingest\nPolls Gmail for unread RFQs."
},
"typeVersion": 1
},
{
"id": "86f58d65-ac9a-4c1f-8052-a079471e9212",
"name": "Section Build Text",
"type": "n8n-nodes-base.stickyNote",
"position": [
400,
-128
],
"parameters": {
"color": 7,
"width": 608,
"height": 544,
"content": "### 2. Build the RFQ text\nPDF text is appended to the email body."
},
"typeVersion": 1
},
{
"id": "c1c76aa5-c48f-4ecb-abf9-d7fc39a520c4",
"name": "Section Extract Gate",
"type": "n8n-nodes-base.stickyNote",
"position": [
1040,
-128
],
"parameters": {
"color": 7,
"width": 784,
"height": 544,
"content": "### 3. Extract and gate\nAI pulls the quote fields, stated values only. The Code node lists anything missing."
},
"typeVersion": 1
},
{
"id": "0f4cbad5-c422-4e21-8ac9-1b865000de85",
"name": "Section Draft",
"type": "n8n-nodes-base.stickyNote",
"position": [
1856,
-128
],
"parameters": {
"color": 7,
"width": 352,
"height": 544,
"content": "### 4. Draft the reply\nQuote or missing-info request, created as a Gmail draft on the thread."
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"binaryMode": "separate",
"availableInMCP": true,
"executionOrder": "v1"
},
"nodeGroups": [],
"connections": {
"OpenAI Model": {
"ai_languageModel": [
[
{
"node": "Extract RFQ Fields",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"New RFQ Email": {
"main": [
[
{
"node": "Normalize Email",
"type": "main",
"index": 0
}
]
]
},
"Normalize Email": {
"main": [
[
{
"node": "Has PDF Attachment?",
"type": "main",
"index": 0
}
]
]
},
"Extract PDF Text": {
"main": [
[
{
"node": "Combine Email + PDF Text",
"type": "main",
"index": 0
}
]
]
},
"All Info Present?": {
"main": [
[
{
"node": "Draft Quote Skeleton",
"type": "main",
"index": 0
}
],
[
{
"node": "Draft Missing-Info Request",
"type": "main",
"index": 0
}
]
]
},
"Completeness Gate": {
"main": [
[
{
"node": "All Info Present?",
"type": "main",
"index": 0
}
]
]
},
"Extract RFQ Fields": {
"main": [
[
{
"node": "Completeness Gate",
"type": "main",
"index": 0
}
]
]
},
"Has PDF Attachment?": {
"main": [
[
{
"node": "Extract PDF Text",
"type": "main",
"index": 0
}
],
[
{
"node": "Use Email Text Only",
"type": "main",
"index": 0
}
]
]
},
"Use Email Text Only": {
"main": [
[
{
"node": "Extract RFQ Fields",
"type": "main",
"index": 0
}
]
]
},
"Combine Email + PDF Text": {
"main": [
[
{
"node": "Extract RFQ Fields",
"type": "main",
"index": 0
}
]
]
}
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow monitors Gmail for unread RFQ emails, optionally extracts text from attached PDFs, and uses OpenAI to pull structured quote details and check completeness before creating a Gmail draft reply with either a quote skeleton or a targeted missing-information request.…
Source: https://n8n.io/workflows/17599/ — 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.
Detects new unread Gmail messages Extracts sender name for personalized replies Classifies the email into one of four categories Applies the correct Gmail label and either sends an auto-reply, creates
Gmail Trigger, OpenAI Chat, Gmail +4
This workflow monitors a Gmail inbox for new support-style emails, uses OpenAI to extract a reusable FAQ question and safe draft answer, logs results to Google Sheets, and then creates a Google Docs d
Gmail Trigger, Information Extractor, OpenAI Chat +3
This workflow automatically processes Fireflies.ai meeting recap emails, extracts the meeting transcript, generates a structured summary email, and sends it to a designated recipient.
@Firefliesai/N8N Nodes Fireflies, Gmail Trigger, Gmail +3
Email Automation. Uses gmailTrigger, textClassifier, lmChatOpenAi, openAi. Event-driven trigger; 13 nodes.
Gmail Trigger, Text Classifier, OpenAI Chat +5
Eliminate 90% of manual work in procurement by automating quote requests, response tracking, price extraction, and supplier follow-ups. This complete automation handles everything from sending persona
Gmail, Google Sheets, Information Extractor +2