This workflow follows the Agent → Chainllm 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": "AI WhatsApp Assistant for Humanized Replies",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "7bbf1baf-4b61-4dd8-bfe1-be0ccc1bf64f",
"options": {}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
-80,
0
],
"id": "112cfd90-a043-4e81-92b4-6a0522331443",
"name": "Webhook"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "09f48a87-a7cf-42de-9294-4f9e68a2f27c",
"name": "content_type",
"value": "={{ $json.body.content_type }}",
"type": "string"
},
{
"id": "3dbdb649-b864-45af-a31b-5528d6c33cce",
"name": "content_text",
"value": "={{ $json.body.content }}",
"type": "string"
},
{
"id": "30a69cf4-fac8-40ab-b35a-c66b7a68f3d8",
"name": "status",
"value": "={{ $json.body.conversation.messages[0].status }}",
"type": "string"
},
{
"id": "ab626022-db93-4691-9e72-a219fedff2b6",
"name": "sender_type",
"value": "={{ $json.body.conversation.messages[0].sender_type }}",
"type": "string"
},
{
"id": "6bdea5ea-40c0-4c71-9115-cb2ce87d5b21",
"name": "cliente_name",
"value": "={{ $json.body.conversation.meta.sender.name }}",
"type": "string"
},
{
"id": "64a0946f-b3ab-402c-b1f6-5eda3ac4a21e",
"name": "identifier",
"value": "={{ $json.body.conversation.meta.sender.identifier }}",
"type": "string"
},
{
"id": "d07ca2db-7a83-4df9-8134-afec06cca28a",
"name": "message_type",
"value": "={{ $json.body.message_type }}",
"type": "string"
},
{
"id": "5860f566-6890-4e52-a76d-aff7572dd8cb",
"name": "source",
"value": "={{ $json.body.source_id }}",
"type": "string"
},
{
"id": "423d5c38-2c96-413c-9736-340246fbb25f",
"name": "",
"value": "",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
320,
0
],
"id": "3ef508e7-90c1-4217-9c6f-2f4cb8d6a48f",
"name": "setData"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.content_text }}",
"options": {
"systemMessage": "Voc\u00ea \u00e9 uma assistente pessoal, responda as d\u00favidas de forma clara, simples e objetiva."
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.9,
"position": [
1140,
0
],
"id": "7c12c870-dcd6-4064-b663-eb9b89b4ebc3",
"name": "AI Agent"
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {
"maxTokens": 300
}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
840,
260
],
"id": "07a44aa5-2158-4fad-a530-13ac96400ddb",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $json.identifier }}",
"contextWindowLength": 50
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
1140,
300
],
"id": "21844bb8-b258-4805-91df-a251f25f2dfa",
"name": "Simple Memory"
},
{
"parameters": {
"method": "POST",
"url": "https://evolution.ggnocode.com/message/sendText/eduarda-teste-1",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "number",
"value": "={{ $item(\"0\").$node[\"setData\"].json[\"identifier\"] }}"
},
{
"name": "text",
"value": "={{ $json.output }}"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1340,
-500
],
"id": "64d6aade-a200-466c-9ea4-ab943f3b6bdc",
"name": "HTTP Request19",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"onError": "continueRegularOutput"
},
{
"parameters": {
"promptType": "define",
"text": "=Whatsapp message to be splitted and formated: {{ $json.output }}",
"hasOutputParser": true,
"messages": {
"messageValues": [
{
"message": "=Sua tarefa \u00e9 dividir a mensagem do usu\u00e1rio em partes compreens\u00edveis, naturais e humanizadas.\n\nReescreva ou quebre o texto em blocos pequenos e coesos, como se estivesse escrevendo uma conversa entre humanos.\n\nMantenha o tom informal, claro e emp\u00e1tico.\n\nEvite quebras mec\u00e2nicas ou rob\u00f3ticas.\n\nUse pontua\u00e7\u00e3o adequada para representar pausas naturais (v\u00edrgulas, retic\u00eancias, travess\u00f5es...).\n\nQuando necess\u00e1rio, adicione pequenas palavras de liga\u00e7\u00e3o que tornem o texto mais fluido, como \u201cent\u00e3o\u201d, \u201cbom\u201d, \u201colha\u201d, \u201cs\u00f3 pra te explicar\u201d, etc.\n\nNunca altere o sentido original da mensagem.\n\nPreserve g\u00edrias, emojis ou linguagem informal, se houver.\n\nExemplo de sa\u00edda esperada:\nMensagem original:\nOi, tudo bem? Preciso de ajuda com uma automa\u00e7\u00e3o no n8n. Estou tentando pegar dados de uma API mas est\u00e1 dando erro.\n\nMensagem transformada:\nOi, tudo certo?\n\nEnt\u00e3o, t\u00f4 precisando de uma m\u00e3o aqui com uma automa\u00e7\u00e3o no n8n.\n\nT\u00f4 tentando puxar dados de uma API... mas t\u00e1 rolando um erro.\n\nSempre se pergunte: \"Se eu estivesse explicando isso pra algu\u00e9m no WhatsApp, como eu falaria?\"\n\n### Jamais separe uma mensagem vazia.\n\n### Certifique-se de que a resposta siga exatamente essa estrutura abaixo, deixando somente entre '*' para negrito e nunca fugindo das demais regras de markdown do whatsapp:\n\t\t\t- *negrito* (substitua '**' por '*')\n\t\t\t- _it\u00e1lico_.(extremamente raro)\n - `link` (usar sempre em todos os links)\n\nTudo o que for link, pode colocar entre \"`\", ou seja, na seguinte formata\u00e7\u00e3o: `www.link.com.br`\n"
}
]
}
},
"id": "b5a162e2-9011-4490-81d9-f6cfa7a0eb48",
"name": "Parser Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.4,
"position": [
1620,
40
]
},
{
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n \"type\": \"object\",\n \"properties\": {\n \"messages\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\"messages\"]\n}"
},
"id": "97bda638-5c3f-4ca0-8712-36a7020985dd",
"name": "OutputParser1",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"typeVersion": 1.2,
"position": [
1840,
400
]
},
{
"parameters": {},
"id": "e4b96224-0506-4fad-9674-ed633e4ada7e",
"name": "no.op",
"type": "n8n-nodes-base.noOp",
"typeVersion": 1,
"position": [
2960,
460
]
},
{
"parameters": {
"options": {}
},
"id": "2532ce66-8177-48c5-8e44-af9201eb23a0",
"name": "Loop Over Items",
"type": "n8n-nodes-base.splitInBatches",
"typeVersion": 3,
"position": [
2240,
40
]
},
{
"parameters": {
"amount": 1.2
},
"id": "04449e4f-5f72-42bd-9023-b3eefe588e24",
"name": "1,2s1",
"type": "n8n-nodes-base.wait",
"typeVersion": 1.1,
"position": [
2780,
320
]
},
{
"parameters": {
"fieldToSplitOut": "output.messages",
"options": {
"destinationFieldName": "output"
}
},
"id": "134d4a90-35c1-4a2f-9fa3-ae33ac53c5b6",
"name": "Segmentos1",
"type": "n8n-nodes-base.splitOut",
"typeVersion": 1,
"position": [
2000,
40
]
},
{
"parameters": {
"model": "gpt-4o",
"options": {}
},
"id": "e0bbe618-c82c-43b3-921a-6d3f39eea97e",
"name": "OpenAI",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1,
"position": [
1600,
420
],
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "## RESSPOSTA CLIENTE",
"height": 1000,
"width": 1640,
"color": 6
},
"type": "n8n-nodes-base.stickyNote",
"position": [
1500,
-260
],
"typeVersion": 1,
"id": "c208f39f-cebf-49d0-9ce9-2d5db560780d",
"name": "Sticky Note6"
},
{
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"leftValue": "={{ $json.message_type }}",
"rightValue": "outgoing",
"operator": {
"type": "string",
"operation": "equals"
},
"id": "5f4fc838-5202-486e-90c7-9cb2d10208a2"
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "Mensagem Enviada"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "eb450fc1-b44d-48f4-bad7-7762e5747621",
"leftValue": "={{ $json.message_type }}",
"rightValue": "incoming",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "Mensagem Recebida"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.switch",
"typeVersion": 3.2,
"position": [
560,
0
],
"id": "7c3088b6-15d0-47c9-9395-cbb61fc96cc2",
"name": "Switch"
},
{
"parameters": {},
"type": "n8n-nodes-base.noOp",
"typeVersion": 1,
"position": [
780,
-220
],
"id": "384525fb-fdbd-4e8b-bcff-611b192d164d",
"name": "No Operation, do nothing"
},
{
"parameters": {
"method": "POST",
"url": "https://evolution.ggnocode.com/message/sendText/eduarda-teste-1",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "number",
"value": "={{ $item(\"0\").$node[\"setData\"].json[\"identifier\"] }}"
},
{
"name": "text",
"value": "={{ $json.output }}"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
2600,
240
],
"id": "8e424b53-bc1b-41c8-9962-56ada20a48c1",
"name": "HTTP Request",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"onError": "continueRegularOutput"
}
],
"connections": {
"Webhook": {
"main": [
[
{
"node": "setData",
"type": "main",
"index": 0
}
]
]
},
"setData": {
"main": [
[
{
"node": "Switch",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Parser Chain",
"type": "main",
"index": 0
}
]
]
},
"Parser Chain": {
"main": [
[
{
"node": "Segmentos1",
"type": "main",
"index": 0
}
]
]
},
"OutputParser1": {
"ai_outputParser": [
[
{
"node": "Parser Chain",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"no.op": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Items": {
"main": [
[],
[
{
"node": "HTTP Request",
"type": "main",
"index": 0
}
]
]
},
"1,2s1": {
"main": [
[
{
"node": "no.op",
"type": "main",
"index": 0
}
]
]
},
"Segmentos1": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"OpenAI": {
"ai_languageModel": [
[
{
"node": "Parser Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Switch": {
"main": [
[
{
"node": "No Operation, do nothing",
"type": "main",
"index": 0
}
],
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"HTTP Request": {
"main": [
[
{
"node": "1,2s1",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "39e1d324-8c4d-47f7-8c42-ee5bd105755d",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "rv4OUQnms2JYf3cb",
"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.
httpHeaderAuthopenAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
AI WhatsApp Assistant for Humanized Replies. Uses agent, lmChatOpenAi, memoryBufferWindow, httpRequest. Webhook trigger; 17 nodes.
Source: https://github.com/mesquitapetro-crypto/n8n-mcp-knowledge-base/blob/a6cc08e57184733dc87a55f53d291650cc52e9bc/workflows/ai-whatsapp-assistant-for-humanized-replies.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.
Tindi article. Uses httpRequest, lmChatOpenAi, chainLlm, outputParserStructured. Webhook trigger; 44 nodes.
HTTP Request, OpenAI Chat, Chain Llm +3
leads. Uses supabase, gmail, formTrigger, httpRequest. Webhook trigger; 62 nodes.
Supabase, Gmail, Form Trigger +13
🧠 Gwen – The AI Voice Marketing Agent Gwen is your intelligent voice-powered marketing assistant built in n8n. She combines the power of OpenAI, ElevenLabs, and automation workflows to handle content
Tool Workflow, Memory Buffer Window, Agent +10
Tired of grinding out YouTube content? This n8n workflow turns AI into your personal video factory—creating engaging, faceless shorts on autopilot. Perfect for creators, marketers, or side-hustlers lo
HTTP Request, Google Drive, Google Sheets +6
Public-facing professionals (developer advocates, founders, marketers, content creators) who get bombarded with LinkedIn messages that aren't actually for them - support requests when you're in market
Slack, HTTP Request, Agent +4