Linkedin Auto-posting with Gpt-4o Content & Image Generation + Telegram Alerts

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 →

{
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "4a83a2f6-f6ab-4657-ab2a-c5594cc13aa7",
      "name": "make Linkedin post",
      "type": "n8n-nodes-base.linkedIn",
      "position": [
        432,
        -48
      ],
      "parameters": {
        "text": "={{ $('Generate Post Content').item.json.message.content.content }}",
        "person": "SKNqCfgpq4",
        "additionalFields": {
          "visibility": "PUBLIC"
        },
        "shareMediaCategory": "IMAGE"
      },
      "credentials": {
        "linkedInOAuth2Api": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "276f682f-15cb-4ecb-93f2-fb07f92603e7",
      "name": "sent the status",
      "type": "n8n-nodes-base.telegram",
      "position": [
        688,
        -48
      ],
      "parameters": {
        "text": "=LinkedIn Post Sent Successfully  \n\nTag - {{ $('Get a random Tag').item.json.value }}\n\nURL - https://www.linkedin.com/feed/update/{{ $json.urn }}\n\nPosted At - {{ DateTime.now() }}",
        "chatId": "123456789",
        "replyMarkup": "inlineKeyboard",
        "additionalFields": {
          "appendAttribution": false
        }
      },
      "credentials": {
        "telegramApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "65b044fc-8595-4d00-9bbc-6f67a39a8d05",
      "name": "When clicking \u2018Execute workflow\u2019",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -784,
        -48
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "1f6d49f5-4d49-4769-bd4a-2cdb5e28e125",
      "name": "Generate an image",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        192,
        -48
      ],
      "parameters": {
        "model": "gpt-image-1",
        "prompt": "={{ $json.message.content.prompt }}",
        "options": {},
        "resource": "image"
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.8
    },
    {
      "id": "1fbd87ae-52ac-48e0-95d1-833ffc885a8b",
      "name": "Get a random Tag",
      "type": "n8n-nodes-base.code",
      "position": [
        -560,
        -48
      ],
      "parameters": {
        "jsCode": "const devToTags = [\n  \"llm\",\n  \"ai\",\n  \"devops\",\n  \"cloudnative\",\n  \"observability\",\n  \"automation\",\n  \"opensource\",\n  \"cybersecurity\",\n  \"scalability\"\n];\n\nfunction getRandomValuesAsObjects(list, count) {\n  const randomValues = [];\n  for (let i = 0; i < count; i++) {\n    const randomIndex = Math.floor(Math.random() * list.length);\n    randomValues.push({ json: { value: list[randomIndex] } });\n  }\n  return randomValues;\n}\n\nreturn getRandomValuesAsObjects(devToTags, 1);\n"
      },
      "typeVersion": 2
    },
    {
      "id": "35d5303a-48a9-4b2b-945b-ca929e400553",
      "name": "Add Examples to set Writing Style",
      "type": "n8n-nodes-base.set",
      "position": [
        -352,
        -48
      ],
      "parameters": {
        "mode": "raw",
        "options": {},
        "jsonOutput": "{\n  \"posts\": [\n  \"Redis is open source YET AGAIN! But does it matter anymore? Here's the story: \u2022 2009: Redis launched as open-source (BSD license). \u2022 2018: Redis Labs introduced RSAL for modules like Redis Search, Graph etc. \u2022 2024: Redis switched to a commercial license, as cloud providers copied Redis code without contributing back. \u2022 2025: Redis is open source again with AGPL v3. But why? Big players like AWS, Google, and Oracle backed the Valkey fork\u2014a fully open-source Redis alternative now under the Linux Foundation. Check out Valkey\u2014\",\n  \"10x Faster Typescript COMPILER!!! Still there is an ongoing debate on why Microsoft didn't choose Rust or their own C# for this rewrite. Although, according to the team, Go was a better choice as it provided a similar structure and seamless transition. Had it been a ground-up rewrite and not a migration, Rust or C# would have been a better choice.\",\n  \"I recently started working on a Teams to Signal messenger bot after realizing that so many people outright hate using MS Teams, but since it's an industry standard, they cannot directly ditch it. My current goal is to support forwarding incoming text messages on Teams to a messenger like Signal. The second will be to give support for the reply mechanism from Signal and sync it to Teams. Coming to the technical stuff, I am thinking of using automation tools like Cypress or Playwright to do this. But it all boils down to the availability of public APIs of both messengers. I will try to document my progress here, as I might fail trying, like a lot of other times \ud83d\ude05 Let's see how it pans out. How would you approach this kind of problem?\",\n    \"Do you know about the require cache in Node.js? Lets say you have a js module that you have imported in a js file using require statement. It is highly possible that after a few iterations to your module code, the changes wont reflect even after you have reloaded the api server/modules. This happens because there is a module cache that happens. You need to invalidate it in order for the new changes to reflect. More on this here -\",\n    \"How important is Out-of-Box experience for an open source contributor? Nowadays I have been working on creating a seamless out-of-box experience for the new contributors of Sparrow API Tool. A poor app setup experience or hard-to-understand README file can be a serious dealbreaker for the community. I am emphasizing on the following things to make the setup as smooth as possible: 1) Created and hosted Docker images for various microservices like api-service and auth-service on DockerHub. 2) Created an all-in-one docker-compose file to set up everything from database to queue service in one command. 3) Created a migration script that generates a test user on app start\u2014bypassing auth flow for instant contribution. 4) Documented multiple setup methods (Docker and non-Docker). 5) Pre-filled example .env files with required variables for copy-paste convenience. Let me know if you have suggestions to improve this further\u2014I\u2019m open to feedback!\"\n]\n}\n",
        "includeOtherFields": true
      },
      "typeVersion": 3.4,
      "alwaysOutputData": false
    },
    {
      "id": "7eaf45b6-e58f-41f5-83e6-ed168f039301",
      "name": "Generate Post Content",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        -160,
        -48
      ],
      "parameters": {
        "modelId": {
          "__rl": true,
          "mode": "id",
          "value": "gpt-4o"
        },
        "options": {},
        "messages": {
          "values": [
            {
              "role": "system",
              "content": "=Role: You are my LinkedIn content assistant. Your job is to write perfectly formatted LinkedIn posts that align with my brand voice, tone, and style (based on provided examples). Each post must revolve around a single keyword/tag and avoid unsupported formatting.\n\nCritical Formatting Rules:\n\nDont use bold, italics or bullets.\n\nWhenever you want to add points, use emojis or simple \"- \" before the start of each pointer \n\nDont use big hyphens that AI usually uses while generating content. Instead use comma(,)\n\nStructure:\n\nAn Engaging Hook\n\nPersonal POV (first-person: \"I\u2019ve seen\u2026\")\n\nInsights (trends/tools/case studies)\n\nClear spacing + new line wherever needed\n\nCTA/question (\"What\u2019s your take?\")\n\nRelavant 4-5 treding hashtags\n\nTrends: \nTie to recent news, tools, or debates (no generic advice).\n\nImage Prompt Rules:\nSuggest an AI image prompt related to the post. Based on the post context, it can be:\n- App interface or UX concept\n- Visual metaphor (e.g. \u201cscaling servers as rocket engines\u201d)\n- Stack or architecture illustration\n- Abstract concept visuals (e.g. speed, chaos, control, balance)\n- Tech-product mockups or feature highlights\n- Flowcharts, only suggest if explaining a process, framework, or system\n\nResponse Format (Strictly JSON):\n```json\n{\n  \"content\": \"<LinkedIn-ready post with proper formatting and no markdown symbols>\",\n  \"prompt\": \"<AI image generation prompt \u2013 relevant, visual, descriptive>\"\n}"
            },
            {
              "role": "system",
              "content": "=Examples of my past writings. Use them to align the new post with my brand voice, tone, and style,\n\n{{ $json.posts.join(\"\\n\\n\") }}"
            },
            {
              "content": "=Use this tag to write a new article for Linkedin that follows my brand voice, style of writing, and tone. \nTag: {{ $json.value }}"
            }
          ]
        },
        "jsonOutput": true
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.8
    }
  ],
  "connections": {
    "Get a random Tag": {
      "main": [
        [
          {
            "node": "Add Examples to set Writing Style",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Generate an image": {
      "main": [
        [
          {
            "node": "make Linkedin post",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "make Linkedin post": {
      "main": [
        [
          {
            "node": "sent the status",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Generate Post Content": {
      "main": [
        [
          {
            "node": "Generate an image",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Add Examples to set Writing Style": {
      "main": [
        [
          {
            "node": "Generate Post Content",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking \u2018Execute workflow\u2019": {
      "main": [
        [
          {
            "node": "Get a random Tag",
            "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.

• linkedInOAuth2Api
• openAiApi
• telegramApi

About this workflow

This n8n workflow automates the process of generating and publishing LinkedIn posts that align with your personal brand tone and trending tech topics. It uses OpenAI to create engaging content and matching visuals, posts it directly to LinkedIn, and sends a confirmation via…

Source: https://n8n.io/workflows/7009/ — 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.