Paul This workflow corresponds to n8n.io template #5012 — we link there as the canonical source.
This workflow follows the Agent → Execute Workflow 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "c4a7b5c1-f74e-4de0-9469-146a197c42f5",
"name": "When Executed by Another Workflow",
"type": "n8n-nodes-base.executeWorkflowTrigger",
"position": [
-1568,
368
],
"parameters": {
"inputSource": "passthrough"
},
"typeVersion": 1.1
},
{
"id": "1f37374e-3c5c-4dad-bfa0-5e948cfbd6e5",
"name": "Query agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-1328,
368
],
"parameters": {
"text": "={{ $json.query }}",
"options": {
"systemMessage": "# SQL Query Generator - Sub Agent Template\n\nYou are a PostgreSQL query generator. Convert user requests into SELECT queries for the database table.\n\n## CRITICAL: OUTPUT FORMAT\n- Output ONLY the SQL query\n- NO explanations, descriptions, or additional text\n- NO code blocks or formatting\n- Just the raw SQL query string\n\n## DATABASE SCHEMA:\n**[REPLACE WITH YOUR DATABASE SCHEMA]**\n```\n[TABLE_NAME] Table:\nid (bigint, Primary Key)\n[field_name] (data_type)\n[field_name] (data_type)\n...\n```\n\n## STRICT RULES:\n1. ONLY SELECT queries - NO INSERT/UPDATE/DELETE/DROP/ALTER\n2. Table name: \"[YOUR_TABLE_NAME]\" (use double quotes if needed)\n3. Column names with spaces: use double quotes (\"[column name]\")\n4. Boolean columns: use true/false (not 1/0)\n5. Text searches: use ILIKE for case-insensitive matching\n6. Always end query with semicolon\n\n## EXAMPLES:\n**[CUSTOMIZE THESE EXAMPLES FOR YOUR USE CASE]**\nUser: \"Show verified entries\" \nResponse: SELECT * FROM \"[YOUR_TABLE]\" WHERE [verified_field] = true;\n\nUser: \"Top 10 most popular\" \nResponse: SELECT * FROM \"[YOUR_TABLE]\" ORDER BY [popularity_field] DESC LIMIT 10;\n\nUser: \"Items containing [keyword]\"\nResponse: SELECT * FROM \"[YOUR_TABLE]\" WHERE [description_field] ILIKE '%[keyword]%';\n\nREMEMBER: Output ONLY the SQL query, nothing else."
},
"promptType": "define"
},
"typeVersion": 2
},
{
"id": "1019eeda-425f-4450-934e-0224c689a801",
"name": "Think",
"type": "@n8n/n8n-nodes-langchain.toolThink",
"position": [
-1136,
592
],
"parameters": {
"description": "Think if the ouputed query really matches the input message."
},
"typeVersion": 1
},
{
"id": "2219bc4a-cdf2-4297-9bd6-423d0f138319",
"name": "OpenRouter Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
-1344,
560
],
"parameters": {
"model": "anthropic/claude-3.5-sonnet",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "21a65536-abfd-4d19-94c9-9aa8d839db16",
"name": "Postgres Chat Memory",
"type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
"position": [
-288,
80
],
"parameters": {
"sessionKey": "C08SU8T0FJ8",
"sessionIdType": "customKey"
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "32cf9699-649c-4781-b27b-c68e7ff306a4",
"name": "OpenRouter Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
-448,
80
],
"parameters": {
"model": "anthropic/claude-3.5-sonnet",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "cacfb298-2ee6-4292-ade7-bb18436df301",
"name": "Think1",
"type": "@n8n/n8n-nodes-langchain.toolThink",
"position": [
-144,
80
],
"parameters": {},
"typeVersion": 1
},
{
"id": "6c979f9c-38df-4b8d-a7c2-be499bd37cd7",
"name": "Download File1",
"type": "n8n-nodes-base.telegram",
"position": [
-1040,
-288
],
"parameters": {
"fileId": "={{ $json.message.voice.file_id }}",
"resource": "file"
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "578c6f2d-d738-49d3-95f4-6de6a48c5754",
"name": "Transcribe1",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
-816,
-288
],
"parameters": {
"options": {},
"resource": "audio",
"operation": "transcribe"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.6
},
{
"id": "68b40dcf-46a0-47e8-9f63-ce020f08c4c6",
"name": "Telegram Trigger1",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-1488,
-176
],
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "e28131b3-4c13-4c5a-b6d1-e9be94970c9f",
"name": "Voice or Text",
"type": "n8n-nodes-base.switch",
"position": [
-1264,
-176
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "Voice",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "612fa3b1-0e08-47f3-9455-746568546ab6",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.voice.file_id }}",
"rightValue": ""
}
]
},
"renameOutput": true
},
{
"outputKey": "Text",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "8c844924-b2ed-48b0-935c-c66a8fd0c778",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.text }}",
"rightValue": ""
}
]
},
"renameOutput": true
}
]
},
"options": {}
},
"typeVersion": 3.2
},
{
"id": "b8d80841-beeb-43f9-a51b-3ea3683c4ba1",
"name": "Text",
"type": "n8n-nodes-base.set",
"position": [
-944,
-80
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "fe7ecc99-e1e8-4a5e-bdd6-6fce9757b234",
"name": "text",
"type": "string",
"value": "={{ $json.message.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "e5e1508a-ceb2-49fd-b3d2-ef87338a230b",
"name": "Merge",
"type": "n8n-nodes-base.merge",
"position": [
-608,
-176
],
"parameters": {},
"typeVersion": 3.1
},
{
"id": "be9cde2d-e131-406b-a061-49193941e159",
"name": "Main agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-320,
-176
],
"parameters": {
"text": "={{ $json.text }}",
"options": {
"systemMessage": "# Database Assistant - Main Agent\n\nYou are an intelligent database assistant that helps users find and explore information from a structured database. You work with a specialized SQL sub-agent to retrieve data efficiently.\n\n## DATABASE SCHEMA:\n**[REPLACE WITH YOUR DATABASE SCHEMA]**\n```\nExample format:\nid (bigint, Primary Key)\nname (text)\ndescription (text)\ncategory (text)\n...\n```\n\n## CRITICAL OPERATIONAL RULES:\n- **ALWAYS use LIMIT in queries** - Default: 10, Maximum: 50\n- **NEVER request unlimited data** - this breaks the system\n- Use ORDER BY with LIMIT for meaningful results\n- Apply specific filters and conditions to narrow results\n\n## COMMUNICATION WITH SQL SUB-AGENT:\nSend clear, natural language requests:\n- \"Show me the 10 most popular [YOUR_ITEMS] in [CATEGORY_FIELD]\"\n- \"Find 5 newest verified entries containing '[KEYWORD]'\"\n- \"Get top 15 [YOUR_ITEMS] by [ACTIVITY_METRIC]\"\n- \"Search for entries with [PRICE_FIELD] less than [AMOUNT], limit 20\"\n\n## RESPONSE GUIDELINES:\nPresent results in a user-friendly format:\n- Highlight key information ([NAME_FIELD], [DESCRIPTION_FIELD], metrics)\n- Include relevant metadata ([VERIFICATION_FIELD], [POPULARITY_FIELD], [CATEGORIES_FIELD])\n- Provide actionable insights\n- Suggest related searches or refinements\n\n## DATA INTERPRETATION:\n**[CUSTOMIZE THESE FIELD DESCRIPTIONS]**\n- **[POPULARITY_FIELD]**: [Description of what this metric means]\n- **[ACTIVITY_FIELD]**: [Description of recent activity indicator]\n- **[VERIFICATION_FIELD]**: [Description of quality/trust indicator]\n- **[CATEGORY_FIELD]**: [Description of classification system]\n- **[PRICE_FIELD]**: [Description of pricing (0 = free, etc.)]\n\nAlways respect system limits and focus on delivering relevant, targeted results."
},
"promptType": "define"
},
"typeVersion": 2
},
{
"id": "ec7a16f3-fd62-4952-a074-3c044de6e86f",
"name": "SEND MESSAGE",
"type": "n8n-nodes-base.telegram",
"position": [
128,
-176
],
"parameters": {
"text": "={{ $json.output }}",
"chatId": "(YOUR CHAT ID)",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "4dfb46ad-d110-40e6-9a87-3c247fc2d8d3",
"name": "CALL QUERY AGENT",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"position": [
-16,
80
],
"parameters": {
"workflowId": {
"__rl": true,
"mode": "list",
"value": "Iw7dOCXYbpfRJrlW",
"cachedResultName": "query agent"
},
"description": "Call this tool for sql querys in natural language",
"workflowInputs": {
"value": {},
"schema": [],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"typeVersion": 2.2
},
{
"id": "dd79a9fb-cf29-4266-a51d-114713e030c0",
"name": "ACCES DATABASE WITH DYNAMIC QUERYS",
"type": "n8n-nodes-base.postgres",
"position": [
-976,
368
],
"parameters": {
"query": "{{ $json.output }}",
"options": {
"largeNumbersOutput": "numbers",
"replaceEmptyStrings": true
},
"operation": "executeQuery"
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 2.6
},
{
"id": "a302abcd-e6a0-4150-bcd7-84c549c1dc94",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1600,
-544
],
"parameters": {
"color": 6,
"width": 1960,
"height": 800,
"content": "# MAIN AGENT"
},
"typeVersion": 1
},
{
"id": "cfcf980f-e037-4c6a-9dd3-7ba4359f6b44",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1600,
272
],
"parameters": {
"color": 4,
"width": 1220,
"height": 440,
"content": "# SUB AGENT"
},
"typeVersion": 1
},
{
"id": "4aaa94db-f919-44d4-9c0f-c703d3838e94",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2320,
-544
],
"parameters": {
"color": 2,
"width": 1780,
"height": 1760,
"content": "# Setup & Configuration Guide\n\n## \ud83d\udccb **Setup Checklist**\n```\n\u25a1 Install N8N workflow platform\n\u25a1 Set up PostgreSQL database\n\u25a1 Configure AI Agent nodes\n\u25a1 Test sub-workflow connection\n\u25a1 Validate query limits\n\u25a1 Deploy and monitor\n```\n\n---\n\n## \ud83d\udd27 **Database Configuration**\n```\n\ud83c\udfaf CRITICAL SETUP STEPS:\n1. Create your PostgreSQL table\n2. Replace [YOUR_TABLE_NAME] in templates\n3. Update database schema in both agents\n4. Set connection credentials in N8N\n5. Test database connectivity\n```\n\n---\n\n## \ud83e\udd16 **Main Agent Setup**\n```\n\ud83d\udccd WHAT TO REPLACE:\n\u2022 [YOUR_DATABASE_SCHEMA] \u2192 Your actual table structure\n\u2022 [YOUR_ITEMS] \u2192 What you're querying (products, users, etc.)\n\u2022 [CATEGORY_FIELD] \u2192 Your category column name\n\u2022 [POPULARITY_FIELD] \u2192 Your popularity metric column\n\u2022 [PRICE_FIELD] \u2192 Your price column name\n```\n\n---\n\n## \u2699\ufe0f **Sub-Agent Configuration**\n```\n\ud83d\udd04 TEMPLATE REPLACEMENTS:\n\u2022 [YOUR_TABLE_NAME] \u2192 Actual table name\n\u2022 [field_name] \u2192 Your column names\n\u2022 [verified_field] \u2192 Your verification column\n\u2022 [popularity_field] \u2192 Your popularity column\n\u2022 [description_field] \u2192 Your description column\n```\n\n---\n\n## \ud83d\udea8 **Critical System Limits**\n```\n\u26a0\ufe0f NEVER FORGET:\n\u2022 Default LIMIT: 10 results\n\u2022 Maximum LIMIT: 50 results\n\u2022 NO unlimited queries allowed\n\u2022 Always use ORDER BY with LIMIT\n\u2022 System will break without limits!\n```\n\n---\n\n## \ud83d\udd17 **Workflow Architecture**\n```\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 USER QUERY \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2502\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u25bc\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 MAIN AGENT \u2502 \u2190 Interprets user needs\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2502\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u25bc\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 SUB-AGENT \u2502 \u2190 Generates SQL query\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2502\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u25bc\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 DATABASE \u2502 \u2190 Executes query\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2502\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u25bc\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 FORMATTED \u2502 \u2190 Returns to user\n\u2502 RESPONSE \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n```"
},
"typeVersion": 1
},
{
"id": "e223ef72-1654-4368-8832-963e485a600b",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-304,
320
],
"parameters": {
"color": 3,
"width": 576,
"height": 560,
"content": "## Need a tailor-made workflow? Tell me about your business and get a free proposal:\n\n**[Start here \u2192 Custom Automation Form](https://taskmorphr.com/contact)**\n\n---\n## \ud83d\udcc8 Cost-Savings Snapshot \nCurious what automation could save you? \nRun the 60-second calculator:\n\n**[ROI / Cost Comparison](https://taskmorphr.com/cost-comparison)**\n\n---\n### \u2709\ufe0f Reach me directly \n`paul@taskmorphr.com`"
},
"typeVersion": 1
},
{
"id": "49e2aa95-5fa3-4576-bb06-c9b8b7bba111",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
16,
720
],
"parameters": {
"color": 3,
"width": 224,
"height": 128,
"content": "### \ud83d\udee0\ufe0f Build it yourself \nBrowse every ready-made workflow: \n[Full Template Pack \u2014 coming soon](https://n8n.io/creators/diagopl/)\n"
},
"typeVersion": 1
}
],
"connections": {
"Text": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"Merge": {
"main": [
[
{
"node": "Main agent",
"type": "main",
"index": 0
}
]
]
},
"Think": {
"ai_tool": [
[
{
"node": "Query agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Think1": {
"ai_tool": [
[
{
"node": "Main agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Main agent": {
"main": [
[
{
"node": "SEND MESSAGE",
"type": "main",
"index": 0
}
]
]
},
"Query agent": {
"main": [
[
{
"node": "ACCES DATABASE WITH DYNAMIC QUERYS",
"type": "main",
"index": 0
}
]
]
},
"Transcribe1": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"Voice or Text": {
"main": [
[
{
"node": "Download File1",
"type": "main",
"index": 0
}
],
[
{
"node": "Text",
"type": "main",
"index": 0
}
]
]
},
"Download File1": {
"main": [
[
{
"node": "Transcribe1",
"type": "main",
"index": 0
}
]
]
},
"CALL QUERY AGENT": {
"ai_tool": [
[
{
"node": "Main agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Telegram Trigger1": {
"main": [
[
{
"node": "Voice or Text",
"type": "main",
"index": 0
}
]
]
},
"Postgres Chat Memory": {
"ai_memory": [
[
{
"node": "Main agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"OpenRouter Chat Model": {
"ai_languageModel": [
[
{
"node": "Query agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenRouter Chat Model1": {
"ai_languageModel": [
[
{
"node": "Main agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When Executed by Another Workflow": {
"main": [
[
{
"node": "Query agent",
"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.
openAiApiopenRouterApipostgrestelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
AI Database Assistant with Smart Query's & PostgreSQL Integration
Source: https://n8n.io/workflows/5012/ — 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.
Turn your Telegram into a personal Bloomberg terminal. Ask any question about any stock — get institutional-grade analysis back in seconds. TwelveData Pro Analyst is a complete, ready-to-import n8n wo
Telegram, Telegram Trigger, Agent +6
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
Output Parser Structured, Telegram, N8N Nodes Tesseractjs +14
Multi Agent System Benefits. Uses gmailTool, lmChatOpenAi, agent, googleCalendarTool. Event-driven trigger; 46 nodes.
Gmail Tool, OpenAI Chat, Agent +12
AI marketing Team Agent. Uses toolWorkflow, telegram, memoryBufferWindow, openAi. Event-driven trigger; 46 nodes.
Tool Workflow, Telegram, Memory Buffer Window +10
This workflow is for users who want to turn Telegram into a personal AI-powered assistant capable of handling everyday tasks through natural language. It's ideal for solo founders, operators, or profe
Memory Buffer Window, Tool Workflow, Tool Think +9