Guillaume Duvernay This workflow corresponds to n8n.io template #8351 — we link there as the canonical source.
This workflow follows the Chainllm → Form Trigger 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 →
{
"nodes": [
{
"id": "954ed22b-db88-4708-82f8-63beed6317de",
"name": "New article form",
"type": "n8n-nodes-base.formTrigger",
"position": [
-944,
-704
],
"parameters": {
"options": {},
"formTitle": "New article",
"formFields": {
"values": [
{
"fieldLabel": "Article title",
"placeholder": "10 ways to do Influencer Marketing in 2025",
"requiredField": true
},
{
"fieldLabel": "Article guidelines",
"placeholder": "Promote xyz and write in British English...",
"requiredField": true
}
]
},
"formDescription": "Fill in this form to trigger the generation of a new article."
},
"typeVersion": 2.3
},
{
"id": "4d44933f-1e99-46cf-919d-0942acb2ccb7",
"name": "Prepare form values",
"type": "n8n-nodes-base.set",
"position": [
-688,
-704
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "ec4734ed-654f-478a-ab90-91bfcee1e208",
"name": "Title",
"type": "string",
"value": "={{ $json['Article title'] }}"
},
{
"id": "c034402e-a7b9-4c91-aaed-f24a838c3d91",
"name": "Guidelines",
"type": "string",
"value": "={{ $json['Article guidelines'] }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "5553922c-69d4-4de7-8a07-a38c37238b50",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
-256,
-480
],
"parameters": {
"jsonSchemaExample": "[\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua, ut enim ad minim veniam?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur?\"\n }\n]"
},
"typeVersion": 1.2
},
{
"id": "2b5dee40-df1b-41cb-8691-bf43158ff50e",
"name": "GPT 5 mini",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-384,
-480
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5-mini",
"cachedResultName": "gpt-5-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "4e25660b-428e-416c-91a0-63cc04104196",
"name": "Split Out Questions",
"type": "n8n-nodes-base.splitOut",
"position": [
16,
-704
],
"parameters": {
"options": {},
"fieldToSplitOut": "output"
},
"typeVersion": 1
},
{
"id": "39c18e8e-5d8f-4f54-9b0c-009fa3f4b966",
"name": "Loop Over Questions",
"type": "n8n-nodes-base.splitInBatches",
"position": [
272,
-720
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "924c6121-8fd7-413b-9a77-9b77054dd481",
"name": "GPT 5 chat",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
864,
-1056
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5-chat-latest",
"cachedResultName": "gpt-5-chat-latest"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "a9f80b58-8767-49ce-a1b3-b310a39f40dc",
"name": "Article result",
"type": "n8n-nodes-base.set",
"position": [
1200,
-1280
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "d3b8c4bc-27d9-4d57-b8d6-3a40b84d7b7d",
"name": "Article",
"type": "string",
"value": "={{ $json.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "a0c64516-6639-4164-8271-600a35a7eda2",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
544,
-720
],
"parameters": {
"color": 7,
"width": 224,
"height": 352,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nConnect your linkup.so credentials (adding your API key in the header or using \"generic credentials\" that you've stored for Linkup)."
},
"typeVersion": 1
},
{
"id": "04528097-0fdb-432d-9847-5741eef25624",
"name": "Aggregate research content",
"type": "n8n-nodes-base.aggregate",
"position": [
528,
-1072
],
"parameters": {
"options": {},
"aggregate": "aggregateAllItemData",
"destinationFieldName": "Content to leverage"
},
"typeVersion": 1
},
{
"id": "45d07062-280c-41f4-a6ec-f1d50ce3ac22",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1680,
-1008
],
"parameters": {
"width": 544,
"height": 752,
"content": "# AI Article Research & Writing Team\n\nThis workflow mimics a professional writing process to create high-quality, sourced articles. It doesn't just write; it plans, researches, and then drafts the content.\n\n## How it works\n1. **Plan:** An AI planner breaks your article topic into a series of sub-questions.\n2. **Research:** It uses **Linkup** to search the web for sourced insights on each sub-question.\n3. **Write:** A final AI writer composes the article based *only* on the sourced research, complete with hyperlinks.\n\n## How to use\n1. **Connect Linkup:** Add your Linkup API Key to the `Query Linkup for insights` node.\n2. **Connect AI Provider:** Connect your AI credentials to the two LLM nodes (we recommend a small model for planning and a large one for writing).\n3. **Run:** Use the form to enter a title and guidelines to generate your sourced article.\n\n\n\n*This template was created by Guillaume Duvernay*"
},
"typeVersion": 1
},
{
"id": "7fa303e2-3f58-4c34-b4ae-d7d17a4062b7",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
176,
-848
],
"parameters": {
"color": 6,
"width": 976,
"height": 608,
"content": "## Retrieving insights from the web for each sub-question"
},
"typeVersion": 1
},
{
"id": "59d256ae-0dee-4e9a-aeef-d674f97473bb",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
720,
-1440
],
"parameters": {
"color": 5,
"width": 368,
"height": 512,
"content": "## AI step writing the final article based on the insights and initial request"
},
"typeVersion": 1
},
{
"id": "61489602-8823-4dc7-87aa-16870a543dcc",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-528,
-848
],
"parameters": {
"color": 6,
"width": 480,
"height": 608,
"content": "## Breaking down the topic into sub-questions"
},
"typeVersion": 1
},
{
"id": "653763b7-3438-4085-8888-fb332a6d3cd2",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1024,
-832
],
"parameters": {
"color": 4,
"width": 272,
"height": 304,
"content": "## Fill in this form to request a new article"
},
"typeVersion": 1
},
{
"id": "148a3000-ed6b-42a9-9c18-d7595cc1b754",
"name": "Query Linkup for insights",
"type": "n8n-nodes-base.httpRequest",
"position": [
608,
-672
],
"parameters": {
"url": "https://api.linkup.so/v1/search",
"method": "POST",
"options": {},
"sendBody": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "q",
"value": "=Find 5 specific and meaningful insights about the topic:\n\n\"{{ $json.question }}\" \n\nthat would strengthen an article paragraph. Each insight should be a concrete finding, statistic, research result, or illustrative example (not just generic background), and should come from a robust source."
},
{
"name": "depth",
"value": "standard"
},
{
"name": "outputType",
"value": "structured"
},
{
"name": "structuredOutputSchema",
"value": "={\n \"type\": \"object\",\n \"properties\": {\n \"insights\": {\n \"description\": \"A list of 5 insights about the topic\",\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"insight\": {\n \"description\": \"A one-sentence key insight, finding, or example about the topic\",\n \"type\": \"string\"\n },\n \"url\": {\n \"description\": \"The URL of the source where the insight is from\",\n \"type\": \"string\"\n },\n \"title\": {\n \"description\": \"The title of the page containing the insight\",\n \"type\": \"string\"\n }\n },\n \"required\": [\"insight\", \"url\", \"title\"]\n }\n }\n }\n}"
},
{
"name": "fromDate",
"value": "={{ \n $now\n .minus($json['News from last x days'], 'days')\n .startOf('day')\n .toISO()\n}}"
},
{
"name": "includeImages",
"value": "false"
}
]
},
"genericAuthType": "httpBearerAuth"
},
"credentials": {
"httpBearerAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "1af07cce-2414-4cfb-9320-099fe697e9ae",
"name": "Format question and insights",
"type": "n8n-nodes-base.set",
"position": [
960,
-464
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "1e33a1f4-a1a2-4962-ac72-cc518d7ff043",
"name": "Question",
"type": "string",
"value": "={{ $('Loop Over Questions').item.json.question }}"
},
{
"id": "903bcf38-13dd-48fb-8eb3-83f7a232aa53",
"name": "Insights",
"type": "array",
"value": "={{ $json.insights }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "7d217bf4-1209-4e0c-bdf8-0c4dce7b7f82",
"name": "Generate research questions",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
-384,
-704
],
"parameters": {
"text": "=Content title: {{ $json.Title }}\n\nArticle guidelines: {{ $json.Guidelines }}\n\n",
"messages": {
"messageValues": [
{
"message": "=You will receive a content title and an angle. Return 3\u20135 non-overlapping questions in JSON array format that cover everything needed to write excellent content as it breaks down the topic into sub-questions.\n\nGuidelines: \n- Start with simple, short broad questions for example to define the terms (e.g., What is X?, Why is X important?, How to do X?). \n- Then move into more specific, advanced, or analytical questions. \n- Ensure questions together form a complete coverage of the topic. \n\n## Output format:\n\nYou'll return the questions in such a JSON ARRAY:\n\n[\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua, ut enim ad minim veniam?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur?\"\n }\n]"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.5
},
{
"id": "083922d8-71ec-4f1f-9451-f5b18cbc0880",
"name": "Generate the AI output",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
784,
-1280
],
"parameters": {
"text": "=Article title:\n\n{{ $('Prepare form values').first().json.Title }}\n\nArticle guidelines:\n\n{{ $('Prepare form values').first().json.Guidelines }}\n\n\nInsighs to leverage:\n\nThis Q&Insights research provides high-quality insights, and sources for your content. Be sure to include source links in your output whenever a source was used.\n\n{{ JSON.stringify($json['Content to leverage'], null, 2) }}\n",
"messages": {
"messageValues": [
{
"message": "=# Role\n\nYour role is to write an article based on the request in the user message.\n\n# What the user message contains\n\nThe user message includes the article title, any guidelines to follow, and a comprehensive set of insights. These insights should be smoothly integrated within the article's content to fact-base it and ensure is qualitative through the leverage of multiple sources. \nInterate the source links smoothly as hyperlinks in the article.\n\n# How to write good articles\n\nYou excel at writing articles by making sure that they deliver value, are concise, seem like they are human-written, not using typical AI useless sentence formulations.\n\n# Your output format\n\nOutput only the full article.\n\n* Begin with a `# H1` title.\n* Use subheadings throughout the article."
}
]
},
"promptType": "define"
},
"typeVersion": 1.5
}
],
"connections": {
"GPT 5 chat": {
"ai_languageModel": [
[
{
"node": "Generate the AI output",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"GPT 5 mini": {
"ai_languageModel": [
[
{
"node": "Generate research questions",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"New article form": {
"main": [
[
{
"node": "Prepare form values",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Questions": {
"main": [
[
{
"node": "Aggregate research content",
"type": "main",
"index": 0
}
],
[
{
"node": "Query Linkup for insights",
"type": "main",
"index": 0
}
]
]
},
"Prepare form values": {
"main": [
[
{
"node": "Generate research questions",
"type": "main",
"index": 0
}
]
]
},
"Split Out Questions": {
"main": [
[
{
"node": "Loop Over Questions",
"type": "main",
"index": 0
}
]
]
},
"Generate the AI output": {
"main": [
[
{
"node": "Article result",
"type": "main",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Generate research questions",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Query Linkup for insights": {
"main": [
[
{
"node": "Format question and insights",
"type": "main",
"index": 0
}
]
]
},
"Aggregate research content": {
"main": [
[
{
"node": "Generate the AI output",
"type": "main",
"index": 0
}
]
]
},
"Generate research questions": {
"main": [
[
{
"node": "Split Out Questions",
"type": "main",
"index": 0
}
]
]
},
"Format question and insights": {
"main": [
[
{
"node": "Loop Over Questions",
"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.
httpBearerAuthopenAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Go beyond basic AI-generated text and create articles that are well-researched, comprehensive, and credible. This template automates an advanced content creation process that mimics a professional writing team: it plans, researches, and then writes.
Source: https://n8n.io/workflows/8351/ — 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 template attempts to replicate OpenAI's DeepResearch feature which, at time of writing, is only available to their pro subscribers.
Output Parser Structured, OpenAI Chat, Form Trigger +8
My workflow 53. Uses formTrigger, httpRequest, lmChatOpenAi, form. Event-driven trigger; 74 nodes.
Form Trigger, HTTP Request, OpenAI Chat +15
Episode 23: UGC with nanobanana. Uses lmChatOpenAi, lmChatOllama, lmChatDeepSeek, lmChatOpenRouter. Event-driven trigger; 74 nodes.
OpenAI Chat, Ollama Chat, Lm Chat Deep Seek +12
PixelSensei(ZH). Uses agent, outputParserStructured, formTrigger, lmChatOpenAi. Event-driven trigger; 55 nodes.
Agent, Output Parser Structured, Form Trigger +4
This workflow is perfect for: Agile development teams and project managers who need to quickly set up Jira projects Product managers who want to convert feature ideas into structured user stories and
Form Trigger, OpenAI Chat, Output Parser Structured +5