Draft and Revise Technical Articles with Openrouter in a Content Pipeline

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 →

{
  "id": "zZjdwqm8PwzrLjeZ",
  "name": "Template 2: Content Pipeline - Writer Agent",
  "tags": [],
  "nodes": [
    {
      "id": "623914e2-8553-4307-92c9-b182a6d3e81f",
      "name": "When Executed by Parent",
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "position": [
        208,
        304
      ],
      "parameters": {
        "inputSource": "passthrough"
      },
      "typeVersion": 1.1
    },
    {
      "id": "8a7f9744-f4c2-4e95-9412-45a1b3b5b646",
      "name": "Writer Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        448,
        304
      ],
      "parameters": {
        "text": "=Brief:\n{{ $json.brief }}\n\nResearch notes (JSON):\n{{ JSON.stringify($json.research) }}\n\n{{ $json.feedbackNotes ? ('Previous draft:\\n' + ($json.previousDraft || '') + '\\n\\nReviewer feedback to address in this revision:\\n' + $json.feedbackNotes) : 'This is a fresh draft (no prior version).' }}",
        "options": {
          "systemMessage": "You are a technical writer for a content pipeline. Given research notes and a brief, produce a clear, direct article. If reviewer feedback is provided along with a previous draft, revise the draft to address the feedback while keeping what was already working. Otherwise, write a fresh draft from scratch.\n\nGuidelines:\n- Match the brief's tone and audience.\n- Lead with the strongest point.\n- Use research facts accurately. Do not invent sources.\n- No filler sentences, no hedging openers, no summary restatements of the brief.\n- Aim for 300 to 600 words unless the brief specifies otherwise.\n\nReturn ONLY valid JSON in this exact shape:\n{\n  \"draft\": \"the full article text as a single string with paragraph breaks as \\\\n\\\\n\",\n  \"wordCount\": 0,\n  \"revisionOf\": null or \"previous\"\n}"
        },
        "promptType": "define"
      },
      "typeVersion": 1.7
    },
    {
      "id": "f2c51dcd-81bc-41b6-9387-0e68a1d53e61",
      "name": "OpenRouter - Writer",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
      "position": [
        352,
        528
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openRouterApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "d38c6150-2527-492e-866d-c8f96d7c3ec3",
      "name": "Parse Writer Output",
      "type": "n8n-nodes-base.code",
      "position": [
        720,
        304
      ],
      "parameters": {
        "jsCode": "// Parse writer output, merge with trigger input, overwrite currentDraft\nconst raw = $input.first().json;\nconst triggerIn = $('When Executed by Parent').first().json;\nlet draftFields;\ntry {\n  const text = typeof raw.output === 'string' ? raw.output : JSON.stringify(raw.output);\n  const m = text.match(/\\{[\\s\\S]*\\}/);\n  const agentOut = JSON.parse(m ? m[0] : text);\n  if (!agentOut.draft) throw new Error('Missing draft');\n  draftFields = {\n    currentDraft: agentOut.draft,\n    draftWordCount: agentOut.wordCount || agentOut.draft.trim().split(/\\s+/).length,\n    revisionOf: agentOut.revisionOf || (triggerIn.feedbackNotes ? 'previous' : null)\n  };\n} catch(e) {\n  draftFields = {\n    currentDraft: '',\n    draftWordCount: 0,\n    revisionOf: null,\n    writerParseError: e.message\n  };\n}\n\nreturn {\n  json: {\n    ...triggerIn,\n    ...draftFields\n  }\n};"
      },
      "typeVersion": 2
    },
    {
      "id": "033b4ea2-4652-441a-a8c1-c9698f57478e",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -448,
        0
      ],
      "parameters": {
        "width": 620,
        "height": 820,
        "content": "## Writer Subworkflow (for Content Pipeline)\n\n### How it works\nStandalone subworkflow called by the Content Pipeline parent. Drafts or revises an article:\n1. **Execute Workflow Trigger** (Passthrough): Receives the full pipeline state (brief, research, previous draft, reviewer feedback, revisionCount).\n2. **Writer Agent** (AI): Produces a ~400-word draft. On revisions, uses the Reviewer's feedback to revise the previous draft rather than starting from scratch.\n3. **Parse + Merge**: Extracts the draft and word count, then returns `{...triggerInput, currentDraft, wordCount}` so state flows through.\n\n### Setup\n- Must be saved before the parent can reference it\n- Attach your **LLM credentials** to the Chat Model sub-node\n- Called by the parent on the first draft and every revision iteration\n\n### Customization\n- Use a stronger model here since this is the highest-leverage step in the pipeline\n- Adjust target word count in the system prompt\n- Add brand voice or style guidelines to the prompt\n\nThis template is a learning companion to the Production AI Playbook, a series that explores strategies, shares best practices, and provides practical examples for building reliable AI systems in n8n."
      },
      "typeVersion": 1
    }
  ],
  "active": true,
  "settings": {
    "binaryMode": "separate",
    "executionOrder": "v1"
  },
  "versionId": "806575c7-a1b4-4e8e-a679-fb73676c6b8a",
  "connections": {
    "Writer Agent": {
      "main": [
        [
          {
            "node": "Parse Writer Output",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenRouter - Writer": {
      "ai_languageModel": [
        [
          {
            "node": "Writer Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "When Executed by Parent": {
      "main": [
        [
          {
            "node": "Writer Agent",
            "type": "main",
            "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.

• openRouterApi

About this workflow

This subworkflow is triggered by a parent content pipeline, uses OpenRouter (via an AI Writer Agent) to draft or revise a technical article from a brief, research notes, and optional reviewer feedback, and returns the updated pipeline state with the current draft and word count.…

Source: https://n8n.io/workflows/15952/ — 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.