Générateur et Optimisateur de Prompts pour Systèmes d'IA (n8n + OpenAI)

Intermédiaire

Ceci est uncontenant 8 nœuds.Utilise principalement des nœuds comme Agent, ChatTrigger, LmChatOpenAi, MemoryBufferWindow. Générateur et Optimisateur de Prompts pour Systèmes d'IA (n8n + OpenAI)

Prérequis
  • Clé API OpenAI

Catégorie

-
Aperçu du workflow
Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement
Exporter le workflow
Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow
{
  "meta": {
    "instanceId": "ad0113c344ee237399e44e9f11798b05baeb83a6196d514a9ae9d2ad71c3b5c9",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "8f16c045-53e2-4405-9053-7dd634d6e82f",
      "name": "Note adhésive33",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -2048,
        8448
      ],
      "parameters": {
        "width": 400,
        "height": 752,
        "content": "## ⚙️ Setup Instructions\n\n### 1️⃣ Set Up OpenAI Connection\n1. Go to [OpenAI Platform](https://platform.openai.com/api-keys)  \n2. Navigate to [OpenAI Billing](https://platform.openai.com/settings/organization/billing/overview)  \n3. Add funds to your billing account  \n4. Copy your API key into the **OpenAI credentials** in n8n  \n\n\n\n## 📬 Contact Information\nNeed help customizing this workflow or building similar automations?\n\n📧 [robert@ynteractive.com](mailto:robert@ynteractive.com)  \n🔗 [Robert Breen](https://www.linkedin.com/in/robert-breen-29429625/)  \n🌐 [ynteractive.com](https://ynteractive.com)\n"
      },
      "typeVersion": 1
    },
    {
      "id": "1faa8374-59e4-4371-a7ed-c17301b8aca7",
      "name": "Note adhésive34",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1616,
        8448
      ],
      "parameters": {
        "color": 7,
        "width": 1104,
        "height": 752,
        "content": "# 🛠️ AI System Prompt Generator & Optimizer (n8n + OpenAI)\n\nThis workflow acts as a **System Prompt Optimizer Agent**.  \nYou send it a draft prompt or goal, and it returns:  \n1. A rewritten **optimized system prompt** that is clear, specific, and actionable.  \n2. A recommendation for the **best OpenAI model** to use based on reasoning needs, complexity, and latency/cost tradeoffs.  \n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "39899c3c-ec7e-4598-873a-0172a79db705",
      "name": "OpenAI Modèle de Chat10",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -1040,
        9040
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-5",
          "cachedResultName": "gpt-5"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "4l6TDfLZVFS24g3X",
          "name": "OpenAi account 4"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "b325fa59-0b59-4535-a0a9-7f3be237044f",
      "name": "Note adhésive35",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1152,
        8864
      ],
      "parameters": {
        "color": 3,
        "width": 288,
        "height": 304,
        "content": "### 1️⃣ Set Up OpenAI Connection\n1. Go to [OpenAI Platform](https://platform.openai.com/api-keys)  \n2. Navigate to [OpenAI Billing](https://platform.openai.com/settings/organization/billing/overview)  \n3. Add funds to your billing account  \n4. Copy your API key into the **OpenAI credentials** in n8n  "
      },
      "typeVersion": 1
    },
    {
      "id": "fae4be3e-f184-490e-bd98-4108ac657d5f",
      "name": "Mémoire Simple2",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        -688,
        9024
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "12da8616-e4ac-4a4d-8e3b-0387a4c3748f",
      "name": "Générateur de Prompts IA",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        -976,
        8672
      ],
      "parameters": {
        "options": {
          "systemMessage": "You are a System Prompt Optimizer.  \nYour job is to take a user’s goal or draft prompt and return an optimized system prompt that is clear, specific, and actionable.  \n\n### Rules:\n- Always rewrite the input into a polished, professional **system prompt**.  \n- Ensure the system prompt includes explicit rules, roles, and constraints where useful.  \n- Make it concise but detailed enough to remove ambiguity.  \n- Recommend the **best OpenAI model** to use for this prompt, based on complexity, reasoning needs, and latency/cost tradeoffs.  \n"
        },
        "hasOutputParser": true
      },
      "typeVersion": 2.2
    },
    {
      "id": "77d09a63-9b3c-47cf-a7a4-de76d4a84a07",
      "name": "Note adhésive36",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1536,
        8736
      ],
      "parameters": {
        "color": 3,
        "width": 288,
        "height": 304,
        "content": "### example question\n\nI need a system prompt for an agent that summarizes meeting transcripts into 3 bullet points for executives.\n  "
      },
      "typeVersion": 1
    },
    {
      "id": "a5c3ebce-f05b-4985-96ef-b98b8db66a22",
      "name": "Message de Chat",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -1440,
        8880
      ],
      "webhookId": "ccaca032-7964-4a83-9417-91a223bc1485",
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.3
    }
  ],
  "pinData": {},
  "connections": {
    "a5c3ebce-f05b-4985-96ef-b98b8db66a22": {
      "main": [
        [
          {
            "node": "12da8616-e4ac-4a4d-8e3b-0387a4c3748f",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "fae4be3e-f184-490e-bd98-4108ac657d5f": {
      "ai_memory": [
        [
          {
            "node": "12da8616-e4ac-4a4d-8e3b-0387a4c3748f",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "12da8616-e4ac-4a4d-8e3b-0387a4c3748f": {
      "main": [
        []
      ]
    },
    "39899c3c-ec7e-4598-873a-0172a79db705": {
      "ai_languageModel": [
        [
          {
            "node": "12da8616-e4ac-4a4d-8e3b-0387a4c3748f",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    }
  }
}
Foire aux questions

Comment utiliser ce workflow ?

Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.

Dans quelles scénarios ce workflow est-il adapté ?

Intermédiaire

Est-ce payant ?

Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.

Informations sur le workflow
Niveau de difficulté
Intermédiaire
Nombre de nœuds8
Catégorie-
Types de nœuds5
Description de la difficulté

Adapté aux utilisateurs expérimentés, avec des workflows de complexité moyenne contenant 6-15 nœuds

Auteur
Robert Breen

Robert Breen

@rbreen

Professional services consultant with over 10 years of experience solving complex business problems across industries. I specialize in n8n and process automation—designing custom workflows that integrate tools like Google Calendar, Airtable, GPT, and internal systems. Whether you need to automate scheduling, sync data, or streamline operations, I build solutions that save time and drive results.

Liens externes
Voir sur n8n.io

Partager ce workflow

Catégories

Catégories: 34