This workflow follows the Execute Workflow Trigger → 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": "Gmail-Triage",
"nodes": [
{
"parameters": {},
"id": "triage-trigger",
"name": "Workflow Input",
"type": "n8n-nodes-base.executeWorkflowTrigger",
"typeVersion": 1,
"position": [
240,
300
]
},
{
"parameters": {
"mode": "manual",
"duplicateItem": false,
"assignments": {
"assignments": [
{
"id": "classification_prompt",
"name": "classification_prompt",
"value": "=Classify this email. Return ONLY valid JSON, no other text.\nFrom: {{ $json.sender }}\nSubject: {{ $json.subject }}\nSnippet: {{ $json.snippet }}\nLabels: {{ $json.labels }}\n\nReturn exactly this JSON structure:\n{\"category\":\"<one of: urgent, informational, admin, finance, customer, personal, newsletter, meeting_related, follow_up_needed, low_priority, potential_spam>\",\"action\":\"<one of: ignore, label, archive, delete, draft, send, flag, log_to_sheet, link_to_calendar>\",\"entities\":[{\"type\":\"person|org|date|amount|url\",\"value\":\"...\"}],\"action_items\":[\"...\"],\"deadlines\":[\"YYYY-MM-DD: description\"],\"priority_score\":<1-10>,\"ai_summary\":\"one sentence summary\"}",
"type": "string"
},
{
"id": "message_id",
"name": "message_id",
"value": "={{ $json.message_id }}",
"type": "string"
},
{
"id": "thread_id",
"name": "thread_id",
"value": "={{ $json.thread_id }}",
"type": "string"
},
{
"id": "sender",
"name": "sender",
"value": "={{ $json.sender }}",
"type": "string"
},
{
"id": "subject",
"name": "subject",
"value": "={{ $json.subject }}",
"type": "string"
},
{
"id": "snippet",
"name": "snippet",
"value": "={{ $json.snippet }}",
"type": "string"
},
{
"id": "labels",
"name": "labels",
"value": "={{ $json.labels }}",
"type": "string"
},
{
"id": "correlation_id",
"name": "correlation_id",
"value": "={{ $json.correlation_id }}",
"type": "string"
}
]
},
"options": {}
},
"id": "build-prompt",
"name": "Build Classification Prompt",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
460,
300
]
},
{
"parameters": {
"method": "POST",
"url": "https://super-agent-production.up.railway.app/chat",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "X-Token",
"value": "={{ $env.SUPER_AGENT_PASSWORD }}"
},
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\"message\": \"{{ $json.classification_prompt }}\", \"session_id\": \"gmail-triage\"}",
"options": {
"timeout": 30000,
"response": {
"response": {
"responseFormat": "json"
}
}
}
},
"id": "call-ai",
"name": "Call Super Agent AI",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
680,
300
]
},
{
"parameters": {
"jsCode": "const raw = $input.first().json.response || $input.first().json.choices?.[0]?.message?.content || '';\nconst msgFields = $('Build Classification Prompt').first().json;\nlet parsed;\ntry {\n const jsonMatch = raw.match(/\\{[\\s\\S]*\\}/);\n parsed = JSON.parse(jsonMatch ? jsonMatch[0] : raw);\n} catch (e) {\n parsed = {\n category: 'informational',\n action: 'label',\n priority_score: 3,\n entities: [],\n action_items: [],\n deadlines: [],\n ai_summary: 'Classification failed - defaulting to informational'\n };\n}\n// Validate category\nconst validCategories = ['urgent','informational','admin','finance','customer','personal','newsletter','meeting_related','follow_up_needed','low_priority','potential_spam'];\nif (!validCategories.includes(parsed.category)) parsed.category = 'informational';\n// Validate action\nconst validActions = ['ignore','label','archive','delete','draft','send','flag','log_to_sheet','link_to_calendar'];\nif (!validActions.includes(parsed.action)) parsed.action = 'label';\n// Validate priority\nif (!parsed.priority_score || parsed.priority_score < 1 || parsed.priority_score > 10) parsed.priority_score = 3;\n\nreturn [{\n json: {\n ...parsed,\n message_id: msgFields.message_id,\n thread_id: msgFields.thread_id,\n sender: msgFields.sender,\n subject: msgFields.subject,\n correlation_id: msgFields.correlation_id,\n classified_at: new Date().toISOString()\n }\n}];"
},
"id": "parse-response",
"name": "Parse AI Response",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
900,
300
]
},
{
"parameters": {
"operation": "executeQuery",
"query": "INSERT INTO gmail_processing_state (message_id, category, action, priority_score, ai_summary, ai_model_used, classified_at) VALUES ($1, $2, $3, $4, $5, 'super_agent', NOW()) ON CONFLICT (message_id) DO UPDATE SET category = $2, action = $3, priority_score = $4, ai_summary = $5, classified_at = NOW()",
"options": {
"queryParameters": "={{ $json.message_id }},={{ $json.category }},={{ $json.action }},={{ $json.priority_score }},={{ $json.ai_summary }}"
}
},
"id": "store-classification",
"name": "Store Classification",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.5,
"position": [
1120,
300
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "const entities = $input.first().json.entities || [];\nconst messageId = $input.first().json.message_id;\nif (entities.length === 0) return [{ json: { message_id: messageId, entities_stored: 0 } }];\nreturn entities.map(e => ({\n json: {\n message_id: messageId,\n entity_type: e.type || 'unknown',\n entity_value: e.value || '',\n confidence: e.confidence || 0.5\n }\n}));"
},
"id": "store-entities",
"name": "Store Entities",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1340,
200
]
},
{
"parameters": {
"operation": "executeQuery",
"query": "INSERT INTO extracted_entities (message_id, entity_type, entity_value, confidence) VALUES ($1, $2, $3, $4) ON CONFLICT DO NOTHING",
"options": {
"queryParameters": "={{ $json.message_id }},={{ $json.entity_type }},={{ $json.entity_value }},={{ $json.confidence }}"
}
},
"id": "insert-entities",
"name": "Insert Entities",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.5,
"position": [
1560,
200
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"onError": "continueRegularOutput"
},
{
"parameters": {
"jsCode": "const items = $input.first().json.action_items || [];\nconst deadlines = $input.first().json.deadlines || [];\nconst messageId = $input.first().json.message_id;\nconst priority = $input.first().json.priority_score || 5;\nif (items.length === 0) return [{ json: { message_id: messageId, action_items_stored: 0 } }];\nreturn items.map((item, i) => {\n let deadline = null;\n if (deadlines[i]) {\n const match = deadlines[i].match(/(\\d{4}-\\d{2}-\\d{2})/);\n if (match) deadline = match[1];\n }\n return { json: { message_id: messageId, description: item, deadline, priority } };\n});"
},
"id": "store-actions",
"name": "Store Action Items",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1340,
400
]
},
{
"parameters": {
"operation": "executeQuery",
"query": "INSERT INTO action_items (message_id, description, deadline, priority, status) VALUES ($1, $2, $3::date, $4, 'open')",
"options": {
"queryParameters": "={{ $json.message_id }},={{ $json.description }},={{ $json.deadline }},={{ $json.priority }}"
}
},
"id": "insert-action-items",
"name": "Insert Action Items",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.5,
"position": [
1560,
400
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"onError": "continueRegularOutput"
},
{
"parameters": {
"mode": "manual",
"duplicateItem": false,
"assignments": {
"assignments": [
{
"id": "message_id",
"name": "message_id",
"value": "={{ $json.message_id }}",
"type": "string"
},
{
"id": "thread_id",
"name": "thread_id",
"value": "={{ $json.thread_id }}",
"type": "string"
},
{
"id": "sender",
"name": "sender",
"value": "={{ $json.sender }}",
"type": "string"
},
{
"id": "subject",
"name": "subject",
"value": "={{ $json.subject }}",
"type": "string"
},
{
"id": "category",
"name": "category",
"value": "={{ $json.category }}",
"type": "string"
},
{
"id": "action",
"name": "action",
"value": "={{ $json.action }}",
"type": "string"
},
{
"id": "priority_score",
"name": "priority_score",
"value": "={{ $json.priority_score }}",
"type": "number"
},
{
"id": "ai_summary",
"name": "ai_summary",
"value": "={{ $json.ai_summary }}",
"type": "string"
},
{
"id": "entities",
"name": "entities",
"value": "={{ $json.entities }}",
"type": "object"
},
{
"id": "action_items",
"name": "action_items",
"value": "={{ $json.action_items }}",
"type": "object"
},
{
"id": "deadlines",
"name": "deadlines",
"value": "={{ $json.deadlines }}",
"type": "object"
},
{
"id": "correlation_id",
"name": "correlation_id",
"value": "={{ $json.correlation_id }}",
"type": "string"
}
]
},
"options": {}
},
"id": "output-result",
"name": "Output Result",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
1780,
300
]
}
],
"connections": {
"Workflow Input": {
"main": [
[
{
"node": "Build Classification Prompt",
"type": "main",
"index": 0
}
]
]
},
"Build Classification Prompt": {
"main": [
[
{
"node": "Call Super Agent AI",
"type": "main",
"index": 0
}
]
]
},
"Call Super Agent AI": {
"main": [
[
{
"node": "Parse AI Response",
"type": "main",
"index": 0
}
]
]
},
"Parse AI Response": {
"main": [
[
{
"node": "Store Classification",
"type": "main",
"index": 0
}
]
]
},
"Store Classification": {
"main": [
[
{
"node": "Store Entities",
"type": "main",
"index": 0
}
]
]
},
"Store Entities": {
"main": [
[
{
"node": "Insert Entities",
"type": "main",
"index": 0
}
]
]
},
"Insert Entities": {
"main": [
[
{
"node": "Store Action Items",
"type": "main",
"index": 0
}
]
]
},
"Store Action Items": {
"main": [
[
{
"node": "Insert Action Items",
"type": "main",
"index": 0
}
]
]
},
"Insert Action Items": {
"main": [
[
{
"node": "Output Result",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1",
"saveManualExecutions": true,
"saveExecutionProgress": true
},
"meta": {
"templateCredsSetupCompleted": false,
"description": "Gmail Triage sub-workflow: classifies emails using Super Agent AI, extracts entities and action items, stores results in PostgreSQL."
},
"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.
postgres
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Gmail-Triage. Uses executeWorkflowTrigger, httpRequest, postgres. Event-driven trigger; 10 nodes.
Source: https://github.com/gelson12/super-agent/blob/aeb812f679f48777a12790d2ecba7d4e351c2838/n8n/gmail_triage.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.
6_Multi-Agent_4vaEvzlaMrgovhNz. Uses postgres, httpRequest, lmChatOpenAi, outputParserStructured. Event-driven trigger; 54 nodes.
Postgres, HTTP Request, OpenAI Chat +4
Jigsaw API key for image processing, I use this as a gatekeeper/second pair of eyes. LINK to their website https://jigsawstack.com/ SECOND A postgress DATABASE (I use Supabase) LlamaCloud for the pars
HTTP Request, Postgres, Stop And Error +2
Bridge_Finance_BOT. Uses telegramTrigger, postgres, httpRequest. Event-driven trigger; 23 nodes.
Telegram Trigger, Postgres, HTTP Request
bridge_pm_bot. Uses telegramTrigger, postgres, httpRequest. Event-driven trigger; 23 nodes.
Telegram Trigger, Postgres, HTTP Request
[2/2] KNN classifier (lands dataset). Uses httpRequest, stickyNote, executeWorkflowTrigger. Event-driven trigger; 18 nodes.
HTTP Request, Execute Workflow Trigger