DIGITAL BIZ TECH This workflow corresponds to n8n.io template #10467 — we link there as the canonical source.
This workflow follows the Agent → Chat 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 →
{
"nodes": [
{
"id": "4f90c351-3a27-4cef-8165-84b81f339462",
"name": "Mistral Cloud Chat Model4",
"type": "@n8n/n8n-nodes-langchain.lmChatMistralCloud",
"position": [
-416,
544
],
"parameters": {
"model": "mistral-medium-latest",
"options": {
"temperature": 0.7
}
},
"typeVersion": 1
},
{
"id": "02d5fb5f-8410-4d2a-9dc6-9a4e3964fa84",
"name": "Simple Memory1",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-112,
560
],
"parameters": {
"contextWindowLength": 15
},
"typeVersion": 1.3
},
{
"id": "d09cc06a-b1a5-4d19-90c3-0c58add13b4f",
"name": "Calculator1",
"type": "@n8n/n8n-nodes-langchain.toolCalculator",
"position": [
160,
560
],
"parameters": {},
"typeVersion": 1
},
{
"id": "ce7fb065-c77e-4b31-b98c-ac18abe4d983",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-1952,
176
],
"parameters": {
"public": true,
"options": {},
"initialMessages": "hi this is cost estimate agent"
},
"typeVersion": 1.3
},
{
"id": "54e74d07-150d-440f-a53e-9995baa5cff1",
"name": "Send a message in Gmail",
"type": "n8n-nodes-base.gmailTool",
"position": [
352,
544
],
"parameters": {
"sendTo": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('To', ``, 'string') }}",
"message": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Message', ``, 'string') }}",
"options": {},
"subject": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Subject', ``, 'string') }}"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "eb045f4b-b2e3-477c-8559-8398a886ca16",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2064,
-32
],
"parameters": {
"color": 7,
"width": 256,
"height": 464,
"content": "## Input endpoints\nWebhook and chat trigger receive user queries from website or n8n chat UI.\n"
},
"typeVersion": 1
},
{
"id": "f868877e-a47e-4366-9800-424072efbdc9",
"name": "ai agent cost estimate",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
96,
176
],
"parameters": {
"text": "={{ $json.chatInput }}",
"options": {
"systemMessage": "=# Persona \nYou are a helpful, intelligent **AI Cost Estimation & Catalog Assistant** for the **Fabrics & Surfaces** brand. \nYou guide users \u2014 whether they upload a document, reference an existing order, or start fresh \u2014 through a smooth, conversational process to extract, confirm, and calculate costs. \nYour role: stay proactive, transparent, and supportive from start to finish.\n\n---\n\n## Core Purpose\n- Help users estimate or verify costs for **fabrics** and **tiles**. \n- Work seamlessly with both **OCR data (stored in Supabase)** and **manual user inputs**. \n- Extract or retrieve structured data (vendor, line items, quantities, rates, totals). \n- Perform **step-by-step cost calculations** using MATERIAL_COSTS and PROCESSING_COSTS. \n- Confirm results conversationally and provide a clear cost summary. \n- Escalate to human support through **Gmail** when required.\n\n---\n\n## Primary Duties\n1. **Detect Input Source**\n - If OCR data exists in Supabase \u2192 retrieve, summarize, and confirm with user before calculating. \n - If the user uploads a new document \u2192 parse it via OCR, save to Supabase, then confirm details. \n - If no data exists \u2192 guide the user step-by-step to collect inputs interactively.\n\n2. **Conversational Confirmation**\n - Always confirm material, dimensions, and quantity before final computation. \n - Ask only for missing or unclear data. \n - Rephrase numeric or technical values clearly (\u201cYou entered 150 cm width and 10 m length \u2014 correct?\u201d).\n\n3. **Computation**\n - Use Calculator for all cost logic. \n - Apply formulas transparently (MATERIAL_COSTS, PROCESSING_COSTS). \n - Show each stage: base cost \u2192 add-ons \u2192 taxes \u2192 total. \n - Handle GSM \u2194 sqm and mm \u2194 sqm conversions automatically.\n\n4. **Output**\n - Display itemized breakdown + total cost. \n - Include assumptions or substitutions if applied. \n - Offer next steps: **Save Quote**, **Email via Gmail**, or **Modify Inputs**.\n\n---\n\n## Conversation Flow\n1. **Greeting:** \n \u201cHi! I can help you estimate fabric or tile costs, review invoices, or create a new quote. \n Would you like me to use stored data, upload a bill, or start a new estimate?\u201d\n2. **Flow continues** depending on source: \n - *Stored Data*: Retrieve \u2192 summarize \u2192 confirm \u2192 calculate \u2192 show results. \n - *New Upload*: OCR extract \u2192 confirm \u2192 calculate \u2192 show results. \n - *Manual Entry*: Ask specs step-by-step \u2192 confirm \u2192 calculate \u2192 show results.\n3. **Always guide and explain:** never skip user interaction, even if data is complete. \n\n---\n\n## Cost Rules\n\n### Fabric (per m or sqm)\n| Material | Base \u20ac/m | Add-ons \u20ac/m |\n|-----------|-----------|-------------|\n| Cotton | 2.5 | Printing 1.2 \u00b7 Hemming 0.5 |\n| Polyester | 2.0 | Coating 1.8 |\n| Linen | 6.0 | \u2013 |\n| Silk | 20.0 | \u2013 |\n| Wool | 10.0 | \u2013 |\n\nFormula: \n`sqm = (width_cm / 100) \u00d7 length_m` \n`total = sqm \u00d7 (base_rate + add_ons) + misc_costs`\n\n---\n\n### Tile (per sqm)\n| Type | \u20ac/sqm | Add-ons \u20ac/sqm |\n|-------|-------|---------------|\n| Ceramic | 8 | Glaze 2.5 |\n| Porcelain | 15 | Rectify 1.0 |\n| Stone | 30 | Seal 2.0 |\n\nFormula: \n`area = pieces \u00d7 (L_mm \u00d7 W_mm / 1e6)` \n`total = area \u00d7 (base + add_ons) + 10 (packaging)`\n\n---\n\n## Behavior\n- Always behave as a conversational guide, not just a calculator. \n- Confirm, clarify, and educate users while computing results. \n- If OCR data is present: use it, but still engage in dialogue. \n- If OCR data is missing: guide user through completion. \n- Automatically handle GSM, sqm, and area conversions. \n- Clearly state any assumptions or corrections made. \n- If the user asks for help or escalation \u2192 send a Gmail message summarizing context and results. \n- Maintain a calm, precise, and professional tone throughout.\n\n---\n\n**End of prompt**\n",
"returnIntermediateSteps": false
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "85b0230d-f7ce-43d1-b482-6468a25f1cc4",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
64
],
"parameters": {
"color": 7,
"width": 544,
"height": 288,
"content": "## AI Agent\nGuides users through the cost estimation form for fabrics and tiles and runs calculations.\n"
},
"typeVersion": 1
},
{
"id": "dcc5f3ad-3a88-4fed-9d15-3d798d8eb46a",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
64,
432
],
"parameters": {
"color": 7,
"width": 448,
"height": 256,
"content": "## Tools: Calculator & Gmail\nCalculator: performs numeric calculations. Gmail: sends quotes or escalations to support.\n"
},
"typeVersion": 1
},
{
"id": "660ec177-6b8f-4591-a9e2-8be6edc8eedd",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2624,
16
],
"parameters": {
"width": 416,
"height": 624,
"content": "## Cost Estimate Agent \u2014 Overview\n\n## How it works\n- Scans uploaded bills or receipts using OCR. \n- Extracts key details like items, quantities, and prices. \n- Calculates total cost and tax automatically. \n- Estimates prices for fabrics and tiles based on size, finish, and material. \n- Saves all parsed and computed data in Supabase. \n- even if no ocr data is present this chat agent guide users through forms, show product info, and suggest alternatives. \n- Core flow: **OCR \u2192 Parse / user query \u2192 Calculate \u2192 Store \u2192 Chat.**\n\n## Setup steps\n1. Add Google Drive (or other storage) and Supabase credentials. \n2. Connect OCR and parsing nodes to handle PDF / image uploads. \n3. Review material and processing cost tables in the calculator node; adjust values for your currency. \n4. Test by uploading a sample invoice or selecting a fabric / tile in chat mode. \n5. Verify results are written to the Supabase table, then enable the webhook or chat trigger for live use.\n"
},
"typeVersion": 1
},
{
"id": "d41425c9-72a5-47e6-b1d4-00ee48725736",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-224,
464
],
"parameters": {
"color": 7,
"height": 192,
"content": "### Memory \nStores short-term session context so the agent can recall prior user inputs "
},
"typeVersion": 1
},
{
"id": "caa00085-20b6-46f4-84b5-61e9da0e0423",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
-544,
464
],
"parameters": {
"color": 7,
"width": 272,
"height": 192,
"content": "## Mistral Model\nHandles conversation logic for the cost estimation agent. "
},
"typeVersion": 1
},
{
"id": "897a43ec-b434-41cd-aa4b-713bf05fa406",
"name": "Split Out",
"type": "n8n-nodes-base.splitOut",
"position": [
-1440,
96
],
"parameters": {
"options": {
"includeBinary": true,
"destinationFieldName": "data"
},
"fieldToSplitOut": "$binary"
},
"typeVersion": 1
},
{
"id": "0c8127b4-405d-452f-9874-e05e684d764d",
"name": "Merge",
"type": "n8n-nodes-base.merge",
"position": [
-176,
144
],
"parameters": {},
"typeVersion": 3.1
},
{
"id": "d6099fc1-790e-4bc1-8cb3-ebdc2ab488eb",
"name": "CHECK IF BINARY FILE IS PRESENT OR NOT",
"type": "n8n-nodes-base.if",
"position": [
-1664,
160
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "loose"
},
"combinator": "and",
"conditions": [
{
"id": "463448a5-b323-4682-8674-24bee0df163b",
"operator": {
"type": "array",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.files }}",
"rightValue": ""
}
]
},
"looseTypeValidation": true
},
"typeVersion": 2.2
},
{
"id": "fde26d6a-7a41-443e-9973-f0d2c68ffde3",
"name": "NORMALIZE binary file",
"type": "n8n-nodes-base.code",
"position": [
-1216,
96
],
"parameters": {
"jsCode": "return items.map(item => {\n const binaryKeys = Object.keys(item.binary || {});\n const firstKey = binaryKeys[0];\n\n if (!firstKey) {\n return item;\n }\n\n return {\n json: item.json,\n binary: {\n data: item.binary[firstKey]\n }\n };\n});\n"
},
"typeVersion": 2
},
{
"id": "bae39571-4a46-40a3-8a5e-f8fd977cf72d",
"name": "OCR (ANY OCR API )",
"type": "n8n-nodes-base.httpRequest",
"position": [
-736,
-256
],
"parameters": {
"method": "POST",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"bodyParameters": {
"parameters": [
{
"name": "mode",
"value": "single"
},
{
"name": "output_type",
"value": "jsonl"
},
{
"name": "include_images",
"value": "false"
},
{
"name": "files",
"parameterType": "formBinaryData",
"inputDataFieldName": "data"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "5296f45c-fe21-4b06-adea-63bb93ece610",
"name": "STORE OCR OUTPUT",
"type": "n8n-nodes-base.supabase",
"position": [
-320,
80
],
"parameters": {
"tableId": "temp_table",
"fieldsUi": {
"fieldValues": [
{
"fieldId": "session_id",
"fieldValue": "={{ $('When chat message received').item.json.sessionId }}"
},
{
"fieldId": "file",
"fieldValue": "={{ $json.data[0].parseJson().blocks }}"
},
{
"fieldId": "file_name",
"fieldValue": "={{ $json.data[0].parseJson().source }}"
}
]
}
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "d580dab1-84ca-4e21-8d51-d451cd6851f8",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
-784,
-352
],
"parameters": {
"color": 7,
"width": 192,
"height": 272,
"content": "### use any ocr(mistral or own hosted ocr)"
},
"typeVersion": 1
},
{
"id": "a1e5e3cc-e235-48c8-be61-babcd43dadc9",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1280,
0
],
"parameters": {
"color": 7,
"width": 224,
"height": 272,
"content": "## normalize binary file name "
},
"typeVersion": 1
},
{
"id": "c6fac97d-7110-4cf7-911d-10a03fe4a2b4",
"name": "Sticky Note9",
"type": "n8n-nodes-base.stickyNote",
"position": [
-352,
-16
],
"parameters": {
"color": 7,
"width": 160,
"height": 288,
"content": "### store ocr output in supbase"
},
"typeVersion": 1
},
{
"id": "822d5178-03f4-4553-bf53-83eb05f26cd8",
"name": "Sticky Note10",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1728,
48
],
"parameters": {
"color": 7,
"height": 256,
"content": "## check if user query have binary file or not ?"
},
"typeVersion": 1
},
{
"id": "a577dfab-3f20-47bd-be7b-64c1cf0f85ec",
"name": "Supabase Get",
"type": "n8n-nodes-base.supabaseTool",
"position": [
720,
528
],
"parameters": {
"filters": {
"conditions": [
{
"keyName": "session_id",
"keyValue": "={{ $('When chat message received').item.json.sessionId }}",
"condition": "eq"
}
]
},
"tableId": "temp_table",
"operation": "getAll"
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "50fe88db-002a-49b6-a124-270a5e7d43ec",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
592,
432
],
"parameters": {
"color": 7,
"width": 272,
"height": 240,
"content": "## get ocr output from supbase"
},
"typeVersion": 1
},
{
"id": "15d4bfb8-d049-422c-8541-3bf7aaacedf7",
"name": "Mistral Upload",
"type": "n8n-nodes-base.httpRequest",
"position": [
-1008,
96
],
"parameters": {
"url": "https://api.mistral.ai/v1/files",
"method": "POST",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"authentication": "predefinedCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "purpose",
"value": "ocr"
},
{
"name": "file",
"parameterType": "formBinaryData",
"inputDataFieldName": "data"
}
]
},
"nodeCredentialType": "mistralCloudApi"
},
"credentials": {
"mistralCloudApi": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "9de46179-9b2d-4aca-8b4c-c3b8938e7646",
"name": "Mistral Signed URL",
"type": "n8n-nodes-base.httpRequest",
"position": [
-768,
96
],
"parameters": {
"url": "=https://api.mistral.ai/v1/files/{{ $json.id }}/url",
"options": {},
"sendQuery": true,
"sendHeaders": true,
"authentication": "predefinedCredentialType",
"queryParameters": {
"parameters": [
{
"name": "expiry",
"value": "24"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "Accept",
"value": "application/json"
}
]
},
"nodeCredentialType": "mistralCloudApi"
},
"credentials": {
"mistralCloudApi": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "49df803d-8805-483b-8598-a616c589edb2",
"name": "Mistral DOC OCR",
"type": "n8n-nodes-base.httpRequest",
"position": [
-560,
96
],
"parameters": {
"url": "https://api.mistral.ai/v1/ocr",
"method": "POST",
"options": {},
"jsonBody": "={\n \"model\": \"mistral-ocr-latest\",\n \"document\": {\n \"type\": \"document_url\",\n \"document_url\": \"{{ $json.url }}\"\n },\n \"include_image_base64\": true\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "mistralCloudApi"
},
"credentials": {
"mistralCloudApi": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "db0b917c-8843-4061-a88f-d3263ec1d4b0",
"name": "Sticky Note11",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1040,
-64
],
"parameters": {
"color": 7,
"width": 608,
"height": 320,
"content": "## MISTRAL OCR\n [OCR Guide](https://mistral.ai/news/mistral-ocr)\n1. UPLOAD FILE\n2. GET SIGNED URL\n3. GET EXTRACT DATA AFTER USING MISTRAL OCR"
},
"typeVersion": 1
}
],
"connections": {
"Merge": {
"main": [
[
{
"node": "ai agent cost estimate",
"type": "main",
"index": 0
}
]
]
},
"Split Out": {
"main": [
[
{
"node": "NORMALIZE binary file",
"type": "main",
"index": 0
}
]
]
},
"Calculator1": {
"ai_tool": [
[
{
"node": "ai agent cost estimate",
"type": "ai_tool",
"index": 0
}
]
]
},
"Supabase Get": {
"ai_tool": [
[
{
"node": "ai agent cost estimate",
"type": "ai_tool",
"index": 0
}
]
]
},
"Mistral Upload": {
"main": [
[
{
"node": "Mistral Signed URL",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory1": {
"ai_memory": [
[
{
"node": "ai agent cost estimate",
"type": "ai_memory",
"index": 0
}
]
]
},
"Mistral DOC OCR": {
"main": [
[
{
"node": "STORE OCR OUTPUT",
"type": "main",
"index": 0
}
]
]
},
"STORE OCR OUTPUT": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"Mistral Signed URL": {
"main": [
[
{
"node": "Mistral DOC OCR",
"type": "main",
"index": 0
}
]
]
},
"OCR (ANY OCR API )": {
"main": [
[]
]
},
"NORMALIZE binary file": {
"main": [
[
{
"node": "Mistral Upload",
"type": "main",
"index": 0
}
]
]
},
"Send a message in Gmail": {
"ai_tool": [
[
{
"node": "ai agent cost estimate",
"type": "ai_tool",
"index": 0
}
]
]
},
"Mistral Cloud Chat Model4": {
"ai_languageModel": [
[
{
"node": "ai agent cost estimate",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "CHECK IF BINARY FILE IS PRESENT OR NOT",
"type": "main",
"index": 0
}
]
]
},
"CHECK IF BINARY FILE IS PRESENT OR NOT": {
"main": [
[
{
"node": "Split Out",
"type": "main",
"index": 0
}
],
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
}
}
}
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.
gmailOAuth2mistralCloudApisupabaseApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow introduces a conversational AI Cost Estimation Chatbot with built-in OCR document analysis and interactive form guidance. It helps users and teams handle pricing, measurement, and product configuration for multiple categories such as fabrics and tiles — whether…
Source: https://n8n.io/workflows/10467/ — 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 is a lightweight n8n workflow that accepts chat input and uploaded receipts, runs OCR, stores parsed results in Supabase, and uses an AI agent to extract structured travel expense data and comput
Supabase Tool, Chat Trigger, Memory Buffer Window +5
This template attempts to create an AI-powered content assistant for WordPress sites using Mistral AI, enabling article recommendations, content summarization, and contextual Q&A capabilities.
Chat Trigger, Output Parser Structured, Agent +10
This workflow transforms WhatsApp into a powerful personal AI using n8n + Green-API. Send text or voice messages — the assistant understands intent and handles daily tasks automatically. 💰 Expense & i
Tool Calculator, Google Sheets Tool, OpenAI Chat +10
Enhance your data analysis by connecting an AI Agent to your dataset, using n8n tools.
Chat Trigger, Agent, OpenAI Chat +6
Code Filter. Uses chatTrigger, agent, lmChatOpenAi, toolCalculator. Chat trigger; 30 nodes.
Chat Trigger, Agent, OpenAI Chat +6