AI Prompt Refiner Workflow

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": "Prompt Refiner",
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "refine-prompt",
        "responseMode": "responseNode",
        "options": {}
      },
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2.1,
      "position": [
        -576,
        -160
      ],
      "id": "webhook-node",
      "name": "Webhook"
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1.5,
      "position": [
        352,
        -160
      ],
      "id": "respond-webhook-node",
      "name": "Respond to Webhook",
      "notesInFlow": false,
      "alwaysOutputData": false
    },
    {
      "parameters": {
        "model": "deepseek/deepseek-r1-0528:free",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
      "typeVersion": 1,
      "position": [
        -288,
        64
      ],
      "id": "openrouter-classifier-model",
      "name": "OpenRouter Chat Model",
      "credentials": {
        "openRouterApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "={{$node[\"Webhook\"].json[\"body\"][\"prompt\"]}}\n",
        "messages": {
          "messageValues": [
            {
              "message": "You are a prompt classification engine.  Analyze the user's prompt and return STRICT JSON with: - intent: one of [coding, design, debugging, explanation, brainstorming] - domain: one of [frontend, backend, devops, uiux, data, general] - missing_context: array of missing but important details - ambiguities: array of unclear or vague parts  Rules: - Return JSON only - No markdown - No explanations"
            }
          ]
        },
        "batching": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "typeVersion": 1.7,
      "position": [
        -352,
        -160
      ],
      "id": "classifier-node",
      "name": "Classifier"
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "={{$node[\"Classifier\"].json[\"text\"]}}\n",
        "options": {
          "systemMessage": "You are a prompt refinement engine.\n\nRewrite the user's original prompt into a clear, complete, and high-quality prompt for an LLM.\n\nRules:\n- Keep the original intent\n- Make reasonable assumptions to fill in missing context (don't ask questions)\n- Resolve ambiguities with sensible defaults\n- Do NOT ask clarifying questions\n- Do NOT list options or alternatives\n- Output ONLY the improved prompt as plain text\n- No markdown, no bullet points, no explanations"
        }
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 3,
      "position": [
        0,
        -160
      ],
      "id": "refiner-node",
      "name": "Refiner"
    },
    {
      "parameters": {
        "model": "deepseek/deepseek-r1-0528:free",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
      "typeVersion": 1,
      "position": [
        80,
        64
      ],
      "id": "openrouter-refiner-model",
      "name": "OpenRouter Chat Model1",
      "credentials": {
        "openRouterApi": {
          "name": "<your credential>"
        }
      }
    }
  ],
  "connections": {
    "Webhook": {
      "main": [
        [
          {
            "node": "Classifier",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenRouter Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Classifier",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Classifier": {
      "main": [
        [
          {
            "node": "Refiner",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Refiner": {
      "main": [
        [
          {
            "node": "Respond to Webhook",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenRouter Chat Model1": {
      "ai_languageModel": [
        [
          {
            "node": "Refiner",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "meta": {
    "templateCredsSetupCompleted": false
  },
  "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.

• openRouterApi

About this workflow

Prompt Refiner. Uses lmChatOpenRouter, chainLlm, agent. Webhook trigger; 6 nodes.

Source: https://github.com/Hanfried-Nguegan/AI-Prompt-Refiner-Agent/blob/f8338f955f48cd25dbd996b95357b6dc1bdad0b1/n8n/refiner-workflow.json — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.