This workflow follows the Agent → Agenttool 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": "Workflow Final",
"nodes": [
{
"parameters": {
"model": {
"__rl": true,
"value": "gpt-5-mini",
"mode": "list",
"cachedResultName": "gpt-5-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
-368,
288
],
"id": "48267bc0-a608-472d-909e-4923a6e15334",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('Webhook').item.json.headers[\"x-real-ip\"] }}"
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
-240,
288
],
"id": "8e6488a6-1c69-4de5-aabb-4f16feb78582",
"name": "Simple Memory"
},
{
"parameters": {
"authentication": "oAuth2",
"select": "channel",
"channelId": {
"__rl": true,
"value": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Channel', ``, 'string') }}",
"mode": "id"
},
"text": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Message_Text', ``, 'string') }}",
"otherOptions": {}
},
"type": "n8n-nodes-base.slackTool",
"typeVersion": 2.3,
"position": [
-112,
288
],
"id": "d1e6b001-aff3-4bde-b2e2-bd3047724ecb",
"name": "Send a message in Slack",
"credentials": {
"slackOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"url": "https://api.hackathon.souamigu.org.br/armador",
"options": {}
},
"type": "n8n-nodes-base.httpRequestTool",
"typeVersion": 4.2,
"position": [
16,
288
],
"id": "2df05e29-2640-4ff2-aeb8-79a0314002dc",
"name": "Armador"
},
{
"parameters": {
"url": "https://api.hackathon.souamigu.org.br/agencia-maritima",
"options": {}
},
"type": "n8n-nodes-base.httpRequestTool",
"typeVersion": 4.2,
"position": [
144,
288
],
"id": "e361c317-5d2b-4ae8-b86c-3e7f6bf02e39",
"name": "Agencia Mar\u00edtima"
},
{
"parameters": {
"url": "https://api.hackathon.souamigu.org.br/autoridade-portuaria",
"options": {}
},
"type": "n8n-nodes-base.httpRequestTool",
"typeVersion": 4.2,
"position": [
272,
288
],
"id": "3e5d197b-dc42-41bf-9d49-5b829e9d137b",
"name": "Autoridade Portu\u00e1ria"
},
{
"parameters": {
"url": "https://api.hackathon.souamigu.org.br/terminal-portuario",
"options": {}
},
"type": "n8n-nodes-base.httpRequestTool",
"typeVersion": 4.2,
"position": [
400,
288
],
"id": "c34addc6-ab29-4a12-8375-919b460e15e6",
"name": "Terminal Portu\u00e1rio"
},
{
"parameters": {
"url": "https://api.hackathon.souamigu.org.br/rebocadores",
"options": {}
},
"type": "n8n-nodes-base.httpRequestTool",
"typeVersion": 4.2,
"position": [
672,
496
],
"id": "2258c6c4-2783-4bb9-bbc8-2c4bd946f25c",
"name": "Rebocadores"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.body.question }}",
"options": {
"systemMessage": "Utilize apenas o Slack\n\nAcesse a API atraves do HTTP Request e envie os dados adquiridos no slack.\n\nVoc\u00ea deve encontrar o canal correto baseado no nome da API, deve ser um desses nomes: ag\u00eancia-mar\u00edtima, autoridade-portu\u00e1ria, movimenta\u00e7\u00e3o-armador, rebocadores ou terminal-portu\u00e1rio\n\nOlhe o statusOperacao e procure os dados do navio atrav\u00e9s da API da se\u00e7\u00e3o que ele se encontra, exemplo: \"statusOperacao\": \"descarga_em_andamento\" - terminal portu\u00e1rio, \"statusOperacao\": \"documentacao_pendente\" - ag\u00eancia mart\u00edtica, etc\n\nToda vez que redirecionar a pesquisa de dados para outro setor, fale no slack o identificador do navio e alerte que ele foi enviado a outro setor\n\nA se\u00e7\u00e3o de terminal portu\u00e1ria \u00e9 a \u00faltima se\u00e7\u00e3o, quando algum navio chega nessa se\u00e7\u00e3o, pode finalizar o processo, mandando um aviso no chat correto\n\nA ordem dos processos \u00e9 a seguinte: Movimenta\u00e7\u00e3o Armador, Autoridade Portu\u00e1ria, Ag\u00eancia Mar\u00edtima, Rebocadores e por fim Terminal Portu\u00e1rio\n\nCaso aconte\u00e7a algum problema ou inconsist\u00eancia nos dados em qualquer um dos setores, pare a execu\u00e7\u00e3o do processo e lance notifica\u00e7\u00e3oes aos canais corretos exigindo corre\u00e7\u00e3o\n\nAnalisando o statusOperacao voc\u00ea deve localizar o setor que o navio j\u00e1 se encontra e iniciar o processo por aquele setor\n\nMonte mensagens mais decoradas, com cores indicando sucesso ou fracasso, erros, etc.\n\nNo fim do processo mostre os dados do navio atualizados no canal de movimenta\u00e7\u00e3o armador"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 2.2,
"position": [
-48,
64
],
"id": "9e4b49b2-0775-4b0c-8cfe-b028592ccf8e",
"name": "AI Agent"
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('Webhook').item.json.headers[\"x-real-ip\"] }}"
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
544,
496
],
"id": "ec358c6f-a3ef-4ceb-b103-3de2036bef8e",
"name": "Simple Memory1"
},
{
"parameters": {
"model": {
"__rl": true,
"value": "gpt-5-mini",
"mode": "list",
"cachedResultName": "gpt-5-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
416,
496
],
"id": "2c1c9556-ddd6-406a-be53-0a5eb126b17f",
"name": "OpenAI Chat Model1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"toolDescription": "Agente que consulta os rebocadores ",
"text": "Encontre rebocadores dispon\u00edveis para o navio selecionado",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.agentTool",
"typeVersion": 2.2,
"position": [
528,
288
],
"id": "991b4e8e-c84c-40b3-820c-ac8c71d51c88",
"name": "Agente Rebocadores"
},
{
"parameters": {
"httpMethod": "POST",
"path": "Brainstorm",
"responseMode": "responseNode",
"options": {}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2.1,
"position": [
-464,
64
],
"id": "8d8c7c59-fc19-4225-b13e-64bf3c1a30f1",
"name": "Webhook"
},
{
"parameters": {
"html": "<!DOCTYPE html>\n<html lang=\"pt-br\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\">\n <title>Poseidon SYNC Chat</title>\n <style>\n @import url('https://fonts.googleapis.com/css2?family=Roboto:wght@400;500;700&display=swap');\n\n :root {\n --primary-color: #008080; /* Um tom de verde-azulado (teal) */\n --secondary-color: #004d4d;\n --assistant-bg: #f0f2f5;\n --user-bg: #008080;\n --text-light: #ffffff;\n --text-dark: #333333;\n --border-color: #e0e0e0;\n }\n\n body {\n font-family: 'Roboto', sans-serif;\n background-color: #e5e5e5;\n margin: 0;\n padding: 20px;\n display: flex;\n justify-content: center;\n align-items: center;\n height: 100vh;\n }\n\n #chat-container {\n width: 100%;\n max-width: 450px;\n height: 90vh;\n max-height: 700px;\n display: flex;\n flex-direction: column;\n background: var(--text-light);\n border-radius: 12px;\n box-shadow: 0 4px 12px rgba(0, 0, 0, 0.15);\n overflow: hidden;\n }\n\n #chat-header {\n background-color: var(--primary-color);\n color: var(--text-light);\n padding: 15px;\n text-align: center;\n box-shadow: 0 2px 4px rgba(0,0,0,0.1);\n }\n\n #chat-header h1 {\n margin: 0;\n font-size: 1.4em;\n font-weight: 700;\n }\n\n #chat-header p {\n margin: 0;\n font-size: 0.8em;\n opacity: 0.9;\n }\n\n #chat-messages {\n flex-grow: 1;\n padding: 20px;\n overflow-y: auto;\n display: flex;\n flex-direction: column;\n gap: 12px;\n }\n\n .message {\n padding: 10px 15px;\n border-radius: 18px;\n max-width: 80%;\n line-height: 1.5;\n word-wrap: break-word;\n }\n\n .assistant-message {\n background-color: var(--assistant-bg);\n color: var(--text-dark);\n align-self: flex-start;\n border-bottom-left-radius: 4px;\n }\n\n .user-message {\n background-color: var(--user-bg);\n color: var(--text-light);\n align-self: flex-end;\n border-bottom-right-radius: 4px;\n }\n \n .error-message {\n background-color: #ffebee;\n color: #c62828;\n align-self: flex-start;\n border-bottom-left-radius: 4px;\n }\n\n #chat-form {\n display: flex;\n padding: 15px;\n border-top: 1px solid var(--border-color);\n background: #fff;\n }\n\n #user-input {\n flex-grow: 1;\n border: 1px solid var(--border-color);\n border-radius: 20px;\n padding: 10px 15px;\n font-size: 1em;\n margin-right: 10px;\n outline: none;\n }\n \n #user-input:focus {\n border-color: var(--primary-color);\n }\n\n #send-button {\n background-color: var(--primary-color);\n color: white;\n border: none;\n border-radius: 20px;\n padding: 10px 20px;\n font-size: 1em;\n font-weight: 500;\n cursor: pointer;\n transition: background-color 0.2s;\n }\n\n #send-button:hover {\n background-color: var(--secondary-color);\n }\n </style>\n</head>\n<body>\n\n<div id=\"chat-container\">\n <div id=\"chat-header\">\n <h1>Poseidon SYNC</h1>\n <p>Assistente Virtual do Porto</p>\n </div>\n <div id=\"chat-messages\" aria-live=\"polite\">\n </div>\n <form id=\"chat-form\">\n <input type=\"text\" id=\"user-input\" placeholder=\"Digno sua pergunta...\" autocomplete=\"off\">\n <button type=\"submit\" id=\"send-button\">Enviar</button>\n </form>\n</div>\n\n<script>\n // URL do seu webhook n8n que processa a pergunta\n const N8N_WEBHOOK_URL = 'https://n8n.hackathon.souamigu.org.br/webhook/Brainstorm';\n\n const chatForm = document.getElementById('chat-form');\n const userInput = document.getElementById('user-input');\n const messagesContainer = document.getElementById('chat-messages');\n\n // Evento de envio do formul\u00e1rio\n chatForm.addEventListener('submit', async (event) => {\n event.preventDefault(); // Impede o recarregamento da p\u00e1gina\n\n const question = userInput.value.trim();\n if (!question) return;\n\n // 1. Adiciona a mensagem do usu\u00e1rio \u00e0 interface\n addMessage(question, 'user-message');\n userInput.value = ''; // Limpa o campo de entrada\n\n try {\n // 2. Envia a pergunta para o webhook n8n\n const response = await fetch(N8N_WEBHOOK_URL, {\n method: 'POST',\n headers: {\n 'Content-Type': 'application/json'\n },\n body: JSON.stringify({ pergunta: question })\n });\n\n if (!response.ok) {\n throw new Error(`Erro na API: ${response.statusText}`);\n }\n\n const data = await response.json();\n \n // 3. Recebe a resposta e adiciona \u00e0 interface\n // A resposta do seu webhook est\u00e1 em `data.output`\n // Substitu\u00edmos as quebras de linha (\\n) por tags <br> para formata\u00e7\u00e3o HTML\n const formattedResponse = data.output.replace(/\\\\n/g, '<br>');\n addMessage(formattedResponse, 'assistant-message');\n\n } catch (error) {\n console.error('Falha ao contatar o webhook:', error);\n const errorMessage = \"Houve um problema com o assistente. Tente novamente mais tarde.\";\n addMessage(errorMessage, 'error-message');\n }\n });\n\n /**\n * Fun\u00e7\u00e3o para adicionar uma nova mensagem ao container do chat.\n * @param {string} text - O conte\u00fado da mensagem (pode conter HTML).\n * @param {string} className - A classe CSS para estilizar a mensagem (user-message, assistant-message, error-message).\n */\n function addMessage(text, className) {\n const messageElement = document.createElement('div');\n messageElement.classList.add('message', className);\n messageElement.innerHTML = text; // Usamos innerHTML para renderizar tags como <br>\n messagesContainer.appendChild(messageElement);\n\n // Rola para a mensagem mais recente\n messagesContainer.scrollTop = messagesContainer.scrollHeight;\n }\n\n</script>\n\n</body>\n</html>"
},
"type": "n8n-nodes-base.html",
"typeVersion": 1.2,
"position": [
-448,
1040
],
"id": "f85ad3c1-92e4-4a52-92bd-2f8b935536a5",
"name": "HTML"
},
{
"parameters": {
"path": "index",
"responseMode": "responseNode",
"options": {}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2.1,
"position": [
-672,
1040
],
"id": "0d287993-9f5d-4e5a-bd17-0cf492c22bc8",
"name": "Webhook1"
},
{
"parameters": {
"respondWith": "text",
"responseBody": "={{ $json.html }}",
"options": {}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.4,
"position": [
-224,
1040
],
"id": "fddd88c3-bca3-4603-86ef-876a6282233c",
"name": "Respond to Webhook1"
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ $item(\"0\").$node[\"AI Agent\"].json }}",
"options": {}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.4,
"position": [
320,
64
],
"id": "c5293b37-6341-469b-b784-1d869bc24def",
"name": "Respond to Webhook"
}
],
"connections": {
"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
}
]
]
},
"Send a message in Slack": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Armador": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Agencia Mar\u00edtima": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Autoridade Portu\u00e1ria": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Terminal Portu\u00e1rio": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Rebocadores": {
"ai_tool": [
[
{
"node": "Agente Rebocadores",
"type": "ai_tool",
"index": 0
}
]
]
},
"Simple Memory1": {
"ai_memory": [
[
{
"node": "Agente Rebocadores",
"type": "ai_memory",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "Agente Rebocadores",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Agente Rebocadores": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
},
"Webhook": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"HTML": {
"main": [
[
{
"node": "Respond to Webhook1",
"type": "main",
"index": 0
}
]
]
},
"Webhook1": {
"main": [
[
{
"node": "HTML",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "a0a103e6-65b0-47ed-baac-81cc575ad137",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "dDy3QuftJX1lKdr0",
"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.
openAiApislackOAuth2Api
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Workflow Final. Uses lmChatOpenAi, memoryBufferWindow, slackTool, httpRequestTool. Webhook trigger; 17 nodes.
Source: https://github.com/RodrigoVSraw/Porto-Hack-2025-Final/blob/097de488568f65a764f71317a0d10be3531d9248/Back-end/WorkflowFinal.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.
This workflow automates enterprise compliance governance using a multi-agent AI architecture. It targets compliance officers, legal teams, and risk managers who need continuous, jurisdiction-aware mon
Agent, OpenAI Chat, Memory Buffer Window +8
This workflow automates end-to-end legal contract review and compliance governance for legal teams, contract managers, and risk officers. It solves the problem of manually reviewing uploaded contracts
Agent, OpenAI Chat, Memory Buffer Window +5
This workflow automates ethics disclosure intake, investigation, risk routing, and escalation for compliance officers, legal teams, and ethics oversight boards. Disclosures arrive via webhook and are
Agent, OpenAI Chat, Memory Buffer Window +7
This workflow automates Identity and Access Management (IAM) event governance using an AI agent, targeting security operations teams, compliance officers, and IT governance teams managing cloud or ent
Agent, OpenAI Chat, Memory Buffer Window +7
This workflow transforms WhatsApp into a powerful personal AI using n8n + Green-API. Send text or voice messages — the assistant understands intent and handles daily tasks automatically. 💰 Expense & i
Tool Calculator, Google Sheets Tool, OpenAI Chat +10