This workflow follows the Google Sheets → HTTP Request 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": "Proj4 Governance Tool",
"nodes": [
{
"parameters": {},
"id": "node-manual-trigger",
"name": "Manual Trigger",
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
240,
300
]
},
{
"parameters": {
"operation": "read",
"documentId": {
"__rl": true,
"value": "YOUR_GOOGLE_SHEET_ID",
"mode": "id"
},
"sheetName": {
"__rl": true,
"value": "Questions",
"mode": "name"
},
"filtersUI": {},
"options": {}
},
"id": "node-read-questions",
"name": "Read Questions",
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4,
"position": [
460,
300
],
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "a1",
"name": "startTime",
"value": "={{ Date.now() }}",
"type": "number"
},
{
"id": "a2",
"name": "User ID",
"value": "={{ $json['User ID'] }}",
"type": "string"
},
{
"id": "a3",
"name": "Query",
"value": "={{ $json['Query'] }}",
"type": "string"
}
]
},
"options": {}
},
"id": "node-set-start-time",
"name": "Set Start Time",
"type": "n8n-nodes-base.set",
"typeVersion": 3,
"position": [
680,
300
]
},
{
"parameters": {
"method": "POST",
"url": "https://api.groq.com/openai/v1/chat/completions",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"contentType": "raw",
"rawContentType": "application/json",
"body": "={{ JSON.stringify({ model: 'qwen/qwen3-32b', messages: [{ role: 'user', content: 'Answer the following question in plain text only. Do not use markdown, bullet points, headers, bold, italic, or any formatting. Write in plain prose sentences only.\\n\\nQuestion: ' + $json['Query'] }], temperature: 0.7, max_tokens: 512, reasoning_effort: 'none' }) }}",
"options": {
"timeout": 30000,
"batching": {
"batch": {
"batchSize": 1,
"batchInterval": 4000
}
}
}
},
"id": "node-generate-response",
"name": "Generate Response",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
900,
300
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "const raw = ($json.choices[0].message.content || '').toString();\nlet text = raw;\ntext = text.replace(/<think>[\\s\\S]*?<\\/think>/gi, '');\ntext = text.replace(/\\\\n/g, ' ');\ntext = text.replace(/```[\\s\\S]*?```/g, '');\ntext = text.replace(/`([^`]+)`/g, '$1');\ntext = text.replace(/^#{1,6}\\s+/gm, '');\ntext = text.replace(/\\*{1,3}([^*\\n]+)\\*{1,3}/g, '$1');\ntext = text.replace(/_{1,3}([^_\\n]+)_{1,3}/g, '$1');\ntext = text.replace(/^[\\*\\-\\+]\\s+/gm, '');\ntext = text.replace(/^\\d+\\.\\s+/gm, '');\ntext = text.replace(/^[\\-\\*_]{3,}\\s*$/gm, '');\ntext = text.replace(/\\n{3,}/g, '\\n\\n');\ntext = text.trim();\nreturn {\n json: {\n cleanResponse: text,\n genUsage: $json.usage,\n userId: $('Set Start Time').item.json['User ID'],\n query: $('Set Start Time').item.json['Query'],\n startTime: $('Set Start Time').item.json.startTime\n }\n};"
},
"id": "node-strip-markdown",
"name": "Strip Markdown",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1120,
300
]
},
{
"parameters": {
"method": "POST",
"url": "https://api.groq.com/openai/v1/chat/completions",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"contentType": "raw",
"rawContentType": "application/json",
"body": "={{ JSON.stringify({ model: 'qwen/qwen3-32b', messages: [{ role: 'user', content: 'Classify the QUERY below for data governance. Return ONLY a raw JSON object with no markdown and no explanation.\\n\\nclassification field (one of): SENSITIVE, STANDARD, UNCERTAIN\\n- SENSITIVE: requests PII, financial data, strategic roadmap, credentials, legal advice, medical info, or individual-specific HR actions\\n- STANDARD: requests no sensitive information\\n- UNCERTAIN: ambiguous or spans multiple sensitive categories\\n\\ndomain field (one of): PII, FINANCIALS, STRATEGIC, CREDENTIALS, LEGAL, MEDICAL, HR, NAMED_INDIVIDUAL, NONE\\n\\nQuery: ' + $json.query }], temperature: 0, max_tokens: 200, reasoning_effort: 'none' }) }}",
"options": {
"timeout": 30000,
"batching": {
"batch": {
"batchSize": 1,
"batchInterval": 4000
}
}
}
},
"id": "node-classify-query",
"name": "Classify Query",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1340,
160
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"method": "POST",
"url": "https://api.groq.com/openai/v1/chat/completions",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"contentType": "raw",
"rawContentType": "application/json",
"body": "={{ JSON.stringify({ model: 'qwen/qwen3-32b', messages: [{ role: 'user', content: 'Classify the RESPONSE below for data governance. Return ONLY a raw JSON object with no markdown and no explanation.\\n\\nclassification field (one of): SENSITIVE, STANDARD, UNCERTAIN\\n- SENSITIVE: contains PII, financial data, strategic roadmap, credentials, legal advice, medical info, or individual-specific HR actions\\n- STANDARD: contains no sensitive information\\n- UNCERTAIN: ambiguous, spans multiple sensitive categories, or cannot be confidently classified. UNCERTAIN is a valid output.\\n\\ndomain field (one of): PII, FINANCIALS, STRATEGIC, CREDENTIALS, LEGAL, MEDICAL, HR, NAMED_INDIVIDUAL, NONE\\n\\nResponse: ' + $json.cleanResponse }], temperature: 0, max_tokens: 200, reasoning_effort: 'none' }) }}",
"options": {
"timeout": 30000,
"batching": {
"batch": {
"batchSize": 1,
"batchInterval": 4000
}
}
}
},
"id": "node-classify-response",
"name": "Classify Response",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1340,
440
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "function parseClass(raw) {\n const text = (raw || '').toString().trim();\n let classification = 'UNCERTAIN';\n let domain = 'NONE';\n try {\n const s = text.indexOf('{');\n const e = text.lastIndexOf('}');\n if (s !== -1 && e > s) {\n const p = JSON.parse(text.substring(s, e + 1));\n if (p.classification) classification = p.classification;\n if (p.domain) domain = p.domain;\n }\n } catch (err) {\n const cm = text.match(/classification[^A-Z]*([A-Z_]+)/);\n const dm = text.match(/domain[^A-Z]*([A-Z_]+)/);\n if (cm) classification = cm[1];\n if (dm) domain = dm[1];\n }\n const vc = ['SENSITIVE', 'STANDARD', 'UNCERTAIN'];\n const vd = ['PII', 'FINANCIALS', 'STRATEGIC', 'CREDENTIALS', 'LEGAL', 'MEDICAL', 'HR', 'NAMED_INDIVIDUAL', 'NONE'];\n if (!vc.includes(classification)) classification = 'UNCERTAIN';\n if (!vd.includes(domain)) domain = 'NONE';\n return { classification, domain };\n}\nconst result = parseClass($json.choices[0].message.content);\nconst strip = $('Strip Markdown').item.json;\nreturn {\n json: {\n queryClass: result.classification,\n queryDomain: result.domain,\n queryTokensIn: ($json.usage || {}).prompt_tokens || 0,\n queryTokensOut: ($json.usage || {}).completion_tokens || 0,\n cleanResponse: strip.cleanResponse,\n genTokensIn: (strip.genUsage || {}).prompt_tokens || 0,\n genTokensOut: (strip.genUsage || {}).completion_tokens || 0,\n userId: strip.userId,\n query: strip.query,\n startTime: strip.startTime\n }\n};"
},
"id": "node-parse-query-result",
"name": "Parse Query Result",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1560,
160
]
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "function parseClass(raw) {\n const text = (raw || '').toString().trim();\n let classification = 'UNCERTAIN';\n let domain = 'NONE';\n try {\n const s = text.indexOf('{');\n const e = text.lastIndexOf('}');\n if (s !== -1 && e > s) {\n const p = JSON.parse(text.substring(s, e + 1));\n if (p.classification) classification = p.classification;\n if (p.domain) domain = p.domain;\n }\n } catch (err) {\n const cm = text.match(/classification[^A-Z]*([A-Z_]+)/);\n const dm = text.match(/domain[^A-Z]*([A-Z_]+)/);\n if (cm) classification = cm[1];\n if (dm) domain = dm[1];\n }\n const vc = ['SENSITIVE', 'STANDARD', 'UNCERTAIN'];\n const vd = ['PII', 'FINANCIALS', 'STRATEGIC', 'CREDENTIALS', 'LEGAL', 'MEDICAL', 'HR', 'NAMED_INDIVIDUAL', 'NONE'];\n if (!vc.includes(classification)) classification = 'UNCERTAIN';\n if (!vd.includes(domain)) domain = 'NONE';\n return { classification, domain };\n}\nconst result = parseClass($json.choices[0].message.content);\nreturn {\n json: {\n responseClass: result.classification,\n responseDomain: result.domain,\n responseTokensIn: ($json.usage || {}).prompt_tokens || 0,\n responseTokensOut: ($json.usage || {}).completion_tokens || 0\n }\n};"
},
"id": "node-parse-response-result",
"name": "Parse Response Result",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1560,
440
]
},
{
"parameters": {
"mode": "combine",
"combineBy": "combineByPosition",
"options": {}
},
"id": "node-merge",
"name": "Merge",
"type": "n8n-nodes-base.merge",
"typeVersion": 3,
"position": [
1780,
300
]
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "return {\n json: {\n 'Timestamp': new Date().toISOString(),\n 'User ID': $json.userId,\n 'query': $json.query,\n 'response': $json.cleanResponse,\n 'response class': $json.responseClass,\n 'response domain': $json.responseDomain,\n 'query class': $json.queryClass,\n 'query domain': $json.queryDomain,\n 'input tokens': ($json.genTokensIn || 0) + ($json.queryTokensIn || 0) + ($json.responseTokensIn || 0),\n 'output tokens': ($json.genTokensOut || 0) + ($json.queryTokensOut || 0) + ($json.responseTokensOut || 0),\n 'latency ms': Date.now() - $json.startTime,\n 'est cost': 0\n }\n};"
},
"id": "node-assemble-row",
"name": "Assemble Row",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
2000,
300
]
},
{
"parameters": {
"operation": "append",
"documentId": {
"__rl": true,
"value": "YOUR_GOOGLE_SHEET_ID",
"mode": "id"
},
"sheetName": {
"__rl": true,
"value": "Audit Log Claude",
"mode": "name"
},
"columns": {
"mappingMode": "autoMapInputData",
"value": {},
"matchingColumns": [],
"schema": []
},
"options": {
"cellFormat": "USER_ENTERED"
}
},
"id": "node-append-audit-log",
"name": "Append Audit Log",
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4,
"position": [
2220,
300
],
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "c1",
"leftValue": "={{ $json['response class'] }}",
"rightValue": "SENSITIVE",
"operator": {
"type": "string",
"operation": "equals"
}
},
{
"id": "c2",
"leftValue": "={{ $json['response class'] }}",
"rightValue": "UNCERTAIN",
"operator": {
"type": "string",
"operation": "equals"
}
},
{
"id": "c3",
"leftValue": "={{ $json['query class'] }}",
"rightValue": "SENSITIVE",
"operator": {
"type": "string",
"operation": "equals"
}
},
{
"id": "c4",
"leftValue": "={{ $json['query class'] }}",
"rightValue": "UNCERTAIN",
"operator": {
"type": "string",
"operation": "equals"
}
}
],
"combinator": "or"
},
"options": {}
},
"id": "node-route-to-review",
"name": "Route to Review",
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
2440,
300
]
},
{
"parameters": {
"operation": "append",
"documentId": {
"__rl": true,
"value": "YOUR_GOOGLE_SHEET_ID",
"mode": "id"
},
"sheetName": {
"__rl": true,
"value": "Review Claude",
"mode": "name"
},
"columns": {
"mappingMode": "autoMapInputData",
"value": {},
"matchingColumns": [],
"schema": []
},
"options": {
"cellFormat": "USER_ENTERED"
}
},
"id": "node-append-review",
"name": "Append Review",
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4,
"position": [
2660,
160
],
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"id": "node-no-op",
"name": "No Operation",
"type": "n8n-nodes-base.noOp",
"typeVersion": 1,
"position": [
2660,
440
]
}
],
"connections": {
"Manual Trigger": {
"main": [
[
{
"node": "Read Questions",
"type": "main",
"index": 0
}
]
]
},
"Read Questions": {
"main": [
[
{
"node": "Set Start Time",
"type": "main",
"index": 0
}
]
]
},
"Set Start Time": {
"main": [
[
{
"node": "Generate Response",
"type": "main",
"index": 0
}
]
]
},
"Generate Response": {
"main": [
[
{
"node": "Strip Markdown",
"type": "main",
"index": 0
}
]
]
},
"Strip Markdown": {
"main": [
[
{
"node": "Classify Query",
"type": "main",
"index": 0
},
{
"node": "Classify Response",
"type": "main",
"index": 0
}
]
]
},
"Classify Query": {
"main": [
[
{
"node": "Parse Query Result",
"type": "main",
"index": 0
}
]
]
},
"Classify Response": {
"main": [
[
{
"node": "Parse Response Result",
"type": "main",
"index": 0
}
]
]
},
"Parse Query Result": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"Parse Response Result": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"Merge": {
"main": [
[
{
"node": "Assemble Row",
"type": "main",
"index": 0
}
]
]
},
"Assemble Row": {
"main": [
[
{
"node": "Append Audit Log",
"type": "main",
"index": 0
}
]
]
},
"Append Audit Log": {
"main": [
[
{
"node": "Route to Review",
"type": "main",
"index": 0
}
]
]
},
"Route to Review": {
"main": [
[
{
"node": "Append Review",
"type": "main",
"index": 0
}
],
[
{
"node": "No Operation",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "REPLACE_WORKFLOW_ID",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "REPLACE_WORKFLOW_ID",
"tags": []
}
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.
googleSheetsOAuth2ApihttpHeaderAuth
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Proj4 Governance Tool. Uses googleSheets, httpRequest. Event-driven trigger; 15 nodes.
Source: https://github.com/MDunn83/AI-Portfolio/blob/main/workflows/P04-ai-governance/P04-ai-governance.json — 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.
TrackCollect_deeper. Uses googleSheets, httpRequest, @n-octo-n/n8n-nodes-json-database, itemLists. Event-driven trigger; 80 nodes.
Google Sheets, HTTP Request, @N Octo N/N8N Nodes Json Database +1
This template is ideal for solo store owners, eCommerce marketers, automation beginners, or anyone using Shopify and Gmail who wants to recover lost revenue without coding.
HTTP Request, Gmail, Twilio +3
PCN. Uses googleSheets, httpRequest, @n-octo-n/n8n-nodes-json-database, itemLists. Event-driven trigger; 60 nodes.
Google Sheets, HTTP Request, @N Octo N/N8N Nodes Json Database +3
The workflow automates the process of gathering extensive keyword data for a "Main Keyword." It starts by reading initial parameters from a Google Sheets template, creates a new dedicated Google Sheet
Google Sheets, Google Drive, HTTP Request
cdp_router. Uses gmailTrigger, telegramTrigger, googleSheets, httpRequest. Event-driven trigger; 53 nodes.
Gmail Trigger, Telegram Trigger, Google Sheets +4