GiovanniSegar This workflow corresponds to n8n.io template #4694 — 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": "70bedb4b-6fe6-4cf0-86c5-e3c8e78fa256",
"name": "Ultimate Assistant1",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
480,
100
],
"parameters": {
"text": "={{ $json.body.message }}",
"options": {
"systemMessage": "=# Overview\nYou are the ultimate personal assistant. Your job is to figure out the right tool to use, if applicable to the user's prompt.\n\n## Rules\n{{ \"- \" + $json.rules.join(\"\\n- \") }}\n\n## Rule Database Schema: \nTable name: datos_agent_rules\n[\n {\n \"column_name\": \"id\",\n \"data_type\": \"bigint\",\n \"character_maximum_length\": null,\n \"is_nullable\": \"NO\",\n \"column_default\": null\n },\n {\n \"column_name\": \"created_at\",\n \"data_type\": \"timestamp with time zone\",\n \"character_maximum_length\": null,\n \"is_nullable\": \"NO\",\n \"column_default\": \"now()\"\n },\n {\n \"column_name\": \"rule_text\",\n \"data_type\": \"text\",\n \"character_maximum_length\": null,\n \"is_nullable\": \"YES\",\n \"column_default\": null\n },\n {\n \"column_name\": \"agent\",\n \"data_type\": \"text\",\n \"character_maximum_length\": null,\n \"is_nullable\": \"YES\",\n \"column_default\": null\n }\n]\n\n## Final Context:\n- Here is the current date/time: {{ $now.toISO() }}\n- UNIX timestamp for current date/time: {{ $now.toMillis() }}\n- The user's timezone is PST\n- The user's name is Giovanni Segar (or Gio for short)",
"returnIntermediateSteps": true
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "53fc82b4-81d2-4e4d-8bdb-fb253a513626",
"name": "Chat History1",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
540,
360
],
"parameters": {
"contextWindowLength": 10
},
"typeVersion": 1.3
},
{
"id": "a7108939-61f7-40f1-8c35-8ed7410fc45a",
"name": "Anthropic Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"position": [
360,
360
],
"parameters": {
"model": "=claude-sonnet-4-20250514",
"options": {
"temperature": 0.2
}
},
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "6765ccef-d5ad-4040-9378-67fe0019e7c7",
"name": "Get rules from database",
"type": "n8n-nodes-base.postgres",
"position": [
-180,
-20
],
"parameters": {
"query": "SELECT rule_text FROM datos_agent_rules WHERE agent = 'TestAgent';",
"options": {},
"operation": "executeQuery"
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 2.6
},
{
"id": "33e63152-923a-4b61-a9b1-71b8c43ba90d",
"name": "Merge",
"type": "n8n-nodes-base.merge",
"position": [
260,
100
],
"parameters": {
"mode": "combine",
"options": {},
"combineBy": "combineByPosition"
},
"typeVersion": 3.1
},
{
"id": "e0343829-da12-4ed7-a610-8353168a2562",
"name": "Aggregate",
"type": "n8n-nodes-base.aggregate",
"position": [
40,
-20
],
"parameters": {
"options": {},
"fieldsToAggregate": {
"fieldToAggregate": [
{
"renameField": true,
"outputFieldName": "rules",
"fieldToAggregate": "rule_text"
}
]
}
},
"typeVersion": 1
},
{
"id": "cae47efc-4063-412a-bdc4-366f1cdb5308",
"name": "Insert rule into database",
"type": "n8n-nodes-base.postgresTool",
"position": [
920,
340
],
"parameters": {
"table": {
"__rl": true,
"mode": "list",
"value": "datos_agent_rules",
"cachedResultName": "datos_agent_rules"
},
"schema": {
"__rl": true,
"mode": "list",
"value": "public"
},
"columns": {
"value": {
"agent": "TestAgent",
"rule_text": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('rule_text', `Write a simple reminder for the future based on the user's instructions. `, 'string') }}"
},
"schema": [
{
"id": "id",
"type": "number",
"display": true,
"removed": true,
"required": false,
"displayName": "id",
"defaultMatch": true,
"canBeUsedToMatch": true
},
{
"id": "created_at",
"type": "dateTime",
"display": true,
"removed": true,
"required": false,
"displayName": "created_at",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "rule_text",
"type": "string",
"display": true,
"required": false,
"displayName": "rule_text",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "agent",
"type": "string",
"display": true,
"required": false,
"displayName": "agent",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"descriptionType": "manual",
"toolDescription": "This should be used when the user corrects you in some way to add a rule that will be included in the future prompts. This can be specific to a certain client or can be a general rule for how to do things. Make sure to let the user know if you added a rule."
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 2.6
},
{
"id": "edda3371-1237-405e-a76e-bda1e0253b80",
"name": "Execute query on rule database",
"type": "n8n-nodes-base.postgresTool",
"position": [
1100,
340
],
"parameters": {
"query": "{{ $fromAI('valid_postgres_sql_query', 'Write any valid SQL query for the Postgres rule database.', 'string') }}",
"options": {},
"operation": "executeQuery",
"descriptionType": "manual",
"toolDescription": "Use this to get rules and their IDs for modification, delete items, add multiple items, or any other operation not covered by the simple insert tool"
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 2.6
},
{
"id": "f5348ce3-3600-4dab-a784-6455fb9f53f2",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-460,
120
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "e154a1e8-0e6f-4e04-b97a-803ec33908ac",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1100,
360
],
"parameters": {
"width": 1000,
"height": 760,
"content": "## Video walkthrough\n\n@[youtube](OwIFK-r-NtQ)\nhttps://www.youtube.com/watch?v=OwIFK-r-NtQ\n\n## Summary of agent\nThis agent can write and rewrite its own rules, allowing you to mold its behavior. It receives rules from a database as system instructions and has tools to create, edit, or delete them. This is a great baseline for new agent builds.\n\n## How to start using it\n\n### Option 1: With a Postgres database (e.g., Supabase)\n1. **Supabase Schema:** Create a table (e.g., `agent_rules`) with the following columns:\n * `id`: `bigint` (Primary Key, auto-incrementing)\n * `created_at`: `timestamp with time zone` (Default: `now()`)\n * `rule_text`: `text`\n * `agent`: `text`\n2. **Workflow Updates:**\n * Update the **Postgres credentials** in the \"Get rules from database,\" \"Insert rule into database,\" and \"Execute query on rule database\" nodes.\n * Update the `agent` value (currently 'TestAgent') in the \"Get rules from database\" and \"Insert rule into database\" nodes if you want a different agent name.\n * Update the **Anthropic API credentials**.\n\n### Option 2: With Google Sheets\n1. **Google Sheet Setup:** Create a Google Sheet with columns for `rule_text` and `agent`.\n2. **Workflow Updates:**\n * Example Google Sheets nodes are included. You will need to:\n * Connect your **Google Sheets credentials**.\n * Select your Google Sheet (with `rule_text` and `agent` columns) in all relevant Google Sheets nodes.\n * Replace the existing Postgres nodes (\"Get rules from database\", \"Insert rule into database\", \"Execute query on rule database\") with the configured Google Sheets nodes.\n * Update the `agent` value (currently 'TestAgent') in the Google Sheets nodes if you want a different agent name.\n * Update the **Anthropic API credentials**.\n * **Agent Instructions:** Update the agent's system message and remove the database schema section as it is no longer relevant"
},
"typeVersion": 1
},
{
"id": "1adbc807-44ce-4c35-800f-5dc0092e0aad",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
60,
580
],
"parameters": {
"color": 4,
"width": 1240,
"height": 540,
"content": "## Prefer Google Sheets? Here are nodes to replace Postgres"
},
"typeVersion": 1
},
{
"id": "e6f9a9c7-a498-46b0-88ac-ef693288ec18",
"name": "Get rules from sheets",
"type": "n8n-nodes-base.googleSheets",
"position": [
140,
680
],
"parameters": {
"sheetName": {
"__rl": true,
"mode": "list",
"value": ""
},
"documentId": {
"__rl": true,
"mode": "list",
"value": ""
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.6
},
{
"id": "728c29e0-bd0f-4237-823b-1ca01de880ef",
"name": "Add rule to sheet",
"type": "n8n-nodes-base.googleSheetsTool",
"position": [
400,
700
],
"parameters": {
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": ""
},
"documentId": {
"__rl": true,
"mode": "list",
"value": ""
},
"descriptionType": "manual",
"toolDescription": "Use this to add rules to the google sheet"
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.6
},
{
"id": "41c75ff2-cbab-4ec7-b5ff-858d5abbecb4",
"name": "Update rule in sheet",
"type": "n8n-nodes-base.googleSheetsTool",
"position": [
580,
700
],
"parameters": {
"operation": "update",
"sheetName": {
"__rl": true,
"mode": "list",
"value": ""
},
"documentId": {
"__rl": true,
"mode": "list",
"value": ""
},
"descriptionType": "manual",
"toolDescription": "Use this to update an existing rule in the sheet"
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.6
},
{
"id": "6fd802ea-84ae-49bd-8e56-f966509a21e8",
"name": "Delete rule in sheet",
"type": "n8n-nodes-base.googleSheetsTool",
"position": [
720,
700
],
"parameters": {
"operation": "delete",
"sheetName": {
"__rl": true,
"mode": "list",
"value": ""
},
"documentId": {
"__rl": true,
"mode": "list",
"value": ""
},
"descriptionType": "manual",
"toolDescription": "Use this to delete an existing rule in the sheet"
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.6
}
],
"connections": {
"Merge": {
"main": [
[
{
"node": "Ultimate Assistant1",
"type": "main",
"index": 0
}
]
]
},
"Aggregate": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"Chat History1": {
"ai_memory": [
[
{
"node": "Ultimate Assistant1",
"type": "ai_memory",
"index": 0
}
]
]
},
"Anthropic Chat Model": {
"ai_languageModel": [
[
{
"node": "Ultimate Assistant1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Get rules from database": {
"main": [
[
{
"node": "Aggregate",
"type": "main",
"index": 0
}
]
]
},
"Insert rule into database": {
"ai_tool": [
[
{
"node": "Ultimate Assistant1",
"type": "ai_tool",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
},
{
"node": "Get rules from database",
"type": "main",
"index": 0
}
]
]
},
"Execute query on rule database": {
"ai_tool": [
[
{
"node": "Ultimate Assistant1",
"type": "ai_tool",
"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.
anthropicApigoogleSheetsOAuth2Apipostgres
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
https://www.youtube.com/watch?v=OwIFK-r-NtQ
Source: https://n8n.io/workflows/4694/ — 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.
Who is this workflow for? This workflow is designed for SEO analysts, content creators, marketing agencies, and developers who need to index a website and then interact with its content as if it were
Agent, OpenAI Chat, Memory Buffer Window +10
Send an AI a few details about your "Dream Customer" in normal english, then have it search the web and give you a "Dream 100" - 100 ideal prospects to connect with in your industry.
Agent, OpenRouter Chat, Chat Trigger +7
Chat with a multi-agent system to write a blog. The orchestrator advances through research, headlines, hooks, outline, intro, draft, and final polish–one phase per reply—outputting options and asking
Agent, Tool Workflow, Memory Buffer Window +9
Think Tool. Uses stickyNote, agent, googleCalendarTool, memoryBufferWindow. Chat trigger; 28 nodes.
Agent, Google Calendar Tool, Memory Buffer Window +8
This template turns your PostgreSQL database into an AI-powered analytics assistant.
Chat Trigger, Postgres, Agent +5