This workflow follows the Agent → HTTP Request 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 →
{
"id": "mOcaSIUAvpt3QjQ1",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "\ud83c\udf10 Confluence Page AI Powered Chatbot",
"tags": [],
"nodes": [
{
"id": "f4761e1a-6430-4b3d-97f9-b91743e02ea6",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
80,
-340
],
"parameters": {
"color": 7,
"width": 633,
"height": 974,
"content": "## Confluence\nhttps://developer.atlassian.com/cloud/confluence/basic-auth-for-rest-apis/\nhttps://id.atlassian.com/manage-profile/security/api-tokens\nhttps://developer.atlassian.com/cloud/confluence/rest/v2/intro/#about\n\nSupplying basic auth headers\nYou can construct and send basic auth headers yourself, including a base64-encoded string that contains your Atlassian account email and API token.\n\nTo use basic auth headers, perform the following steps:\n\nGenerate an API Token for your Atlassian Account: https://id.atlassian.com/manage/api-tokens\nBuild a string of the form your_email@domain.com:your_user_api_token.\nYou'll need to encode your authorization credentials to Base64 encoded. You can do this locally:\nLinux/Unix/MacOS:\n\nCopy\n```\necho -n your_email@domain.com:your_user_api_token | base64\n```\nWindows 7 and later, using Microsoft Powershell:\n\nCopy\n```\n$Text = \u2018your_email@domain.com:your_user_api_token\u2019\n$Bytes = [System.Text.Encoding]::UTF8.GetBytes($Text)\n$EncodedText = [Convert]::ToBase64String($Bytes)\n$EncodedText\n```\nSupply an Authorization header with content Basic followed by the encoded string. Example: Authorization: Basic eW91cl9lbWFpbEBkb21haW4uY29tOnlvdXJfdXNlcl9hcGlfdG9rZW4=\n\nCopy\n```\ncurl -D- \\\n -X GET \\\n -H \"Authorization: Basic <your_encoded_string>\" \\\n -H \"Content-Type: application/json\" \\\n \"https://<your-domain.atlassian.net>/wiki/rest/api/space\"\n```\n\nThe above cURL command will not work as shown. You need to replace <your_encoded_string> and <your-domain.atlassian.net> with your authorization credentials encoded string and instance information before running it in the terminal."
},
"typeVersion": 1
},
{
"id": "b2865684-687e-45a9-bb0c-e78df4dda72e",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
760,
-340
],
"parameters": {
"color": 5,
"width": 768.3946456283678,
"height": 381.59428876752247,
"content": "## Using Rest API to GET Confluence Page Body\nhttps://developer.atlassian.com/cloud/confluence/rest/v2/api-group-page/#api-pages-id-get\n\nRequest\nhttps://<your-wiki>.atlassian.net/wiki/api/v2/pages/{id}\nPath parameters\nid\ninteger\n\nRequired\nQuery parameters\n\nThe content format types to be returned in the body field of the response. \nIf available, the representation will be available under a response field of the same name under the body field.\n\nValid values: storage, atlas_doc_format, view, export_view, anonymous_export_view, styled_view, editor\n\n"
},
"typeVersion": 1
},
{
"id": "2fae2b02-b15f-4226-86c2-f4444f10965e",
"name": "Confluence Page Storage View",
"type": "n8n-nodes-base.httpRequest",
"position": [
900,
580
],
"parameters": {
"url": "=https://example.atlassian.net/wiki/api/v2/pages/{{ $json.id }}",
"options": {},
"sendQuery": true,
"sendHeaders": true,
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"queryParameters": {
"parameters": [
{
"name": "body-format",
"value": "storage"
}
]
},
"headerParameters": {
"parameters": [
{}
]
}
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "49c5c6f7-f879-4518-aeef-922154f47ea6",
"name": "HTML to Markdown",
"type": "n8n-nodes-base.markdown",
"position": [
1100,
580
],
"parameters": {
"html": "={{ $json.body.storage.value }}",
"options": {}
},
"typeVersion": 1
},
{
"id": "6ef64460-1406-43c9-9c5b-9d8ae3f51d31",
"name": "gpt-4o-mini",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1260,
760
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "b8f998da-34b2-40d4-9816-b7a3ca33a3d9",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.manualChatTrigger",
"position": [
820,
180
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "8fcfb987-3ea1-43cd-804f-dc2d629e558e",
"name": "Window Buffer Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
1400,
760
],
"parameters": {
"sessionKey": "={{ $('When chat message received').item.json.sessionId }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.2
},
{
"id": "53fe680c-af07-4712-b3cd-ae853f19cf8a",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
760,
420
],
"parameters": {
"color": 6,
"width": 1163,
"height": 515,
"content": "## Chatbot for Confluence Pages\n\n\n"
},
"typeVersion": 1
},
{
"id": "f37546a9-1b33-4276-9ea3-e461b53fe70a",
"name": "Chat Response",
"type": "n8n-nodes-base.set",
"position": [
1700,
680
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "636ec5bb-141c-491b-b827-bf6c3753a531",
"name": "output",
"type": "string",
"value": "={{ $json.output }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "c53f59bd-f0d9-4629-bf56-ca439ef9c7f5",
"name": "Globals",
"type": "n8n-nodes-base.set",
"position": [
1100,
180
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "74683edb-6368-4673-95f3-2885e30595cf",
"name": "page_id_tekla",
"type": "string",
"value": "688157"
},
{
"id": "3a8796d7-3426-4f4a-bddf-973720b59e9d",
"name": "page_id_n8n",
"type": "string",
"value": "491546"
},
{
"id": "42b27698-8d11-4fb0-a308-e256e0752f4d",
"name": "page_id_more_n8n",
"type": "string",
"value": "983041"
},
{
"id": "62572887-e17a-4957-9ab1-3546277f79ab",
"name": "page_id_tekla_clash_checking",
"type": "string",
"value": "753691"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "ee500c5b-9289-4636-8178-6235c0fe4080",
"name": "Search By ID",
"type": "n8n-nodes-base.httpRequest",
"position": [
1300,
180
],
"parameters": {
"url": "=https://example.atlassian.net/wiki/rest/api/search?limit=1&cql=id={{ $json.page_id_n8n }}",
"options": {},
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "934f0c57-6184-4c85-a0dc-097b3c470be4",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1020,
80
],
"parameters": {
"width": 872,
"height": 297,
"content": "## Confluence Search By ID"
},
"typeVersion": 1
},
{
"id": "c51b8421-962d-46a1-aaf5-1b170252b7da",
"name": "Page Schema",
"type": "n8n-nodes-base.set",
"position": [
1700,
180
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "3e8b49af-f3c6-4441-842f-9ce9a42c34b6",
"name": "content._links.webui",
"type": "string",
"value": "={{ $json.content._links.webui }}"
},
{
"id": "6fd53eb3-52b2-4f7b-92ca-89a26e05d52a",
"name": "content._links.self",
"type": "string",
"value": "={{ $json.content._links.self }}"
},
{
"id": "dfc89cbb-2f63-41ca-acfb-27b4d36d0418",
"name": "title",
"type": "string",
"value": "={{ $json.title }}"
},
{
"id": "0e15af12-8ae2-4337-a174-f3c3592bd0c6",
"name": "url",
"type": "string",
"value": "={{ $json.url }}"
},
{
"id": "6bbfa6eb-d6db-42c4-9ef6-81611fda0365",
"name": "excerpt",
"type": "string",
"value": "={{ $json.excerpt }}"
},
{
"id": "a5a26e42-af66-41a6-9406-7ccb86fb3386",
"name": "id",
"type": "string",
"value": "={{ $json.content.id }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "2c765cad-e488-44ad-98b6-6e0a2c575fd2",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1300,
580
],
"parameters": {
"text": "=Answer questions from user with the context provided. Only respond using the context. If you do not know the answer simply respond with \"I don't know.\"\n\nUser question: {{ $('When chat message received').item.json.chatInput }}\n\nContext: {{ $json.data }}",
"agent": "conversationalAgent",
"options": {},
"promptType": "define"
},
"typeVersion": 1.6
},
{
"id": "a89508f9-fd88-4a9f-84da-a0ddef590e1b",
"name": "Send Telegram Message",
"type": "n8n-nodes-base.telegram",
"position": [
1700,
480
],
"parameters": {
"text": "={{ $json.output}}",
"chatId": "={{ $env.TELEGRAM_CHAT_ID }}",
"additionalFields": {
"parse_mode": "HTML",
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "dae8ae00-1552-4945-948e-2556dfdd8802",
"name": "Split Out",
"type": "n8n-nodes-base.splitOut",
"position": [
1500,
180
],
"parameters": {
"options": {},
"fieldToSplitOut": "results"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "d57c434b-ed09-484a-bcc4-d81681001a36",
"connections": {
"Globals": {
"main": [
[
{
"node": "Search By ID",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Chat Response",
"type": "main",
"index": 0
},
{
"node": "Send Telegram Message",
"type": "main",
"index": 0
}
]
]
},
"Split Out": {
"main": [
[
{
"node": "Page Schema",
"type": "main",
"index": 0
}
]
]
},
"Page Schema": {
"main": [
[
{
"node": "Confluence Page Storage View",
"type": "main",
"index": 0
}
]
]
},
"gpt-4o-mini": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Search By ID": {
"main": [
[
{
"node": "Split Out",
"type": "main",
"index": 0
}
]
]
},
"HTML to Markdown": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Window Buffer Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Globals",
"type": "main",
"index": 0
}
]
]
},
"Confluence Page Storage View": {
"main": [
[
{
"node": "HTML to Markdown",
"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.
httpHeaderAuthopenAiApitelegramApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow transforms your Confluence pages into an interactive AI-powered chatbot, allowing team members to query content conversationally without sifting through documents manually. It suits knowledge managers, support teams, or any group relying on Confluence for documentation, delivering instant, context-aware responses that boost productivity and reduce search time. The core step involves fetching the page via HTTP Request, converting its HTML to Markdown, and feeding it into an OpenAI model like GPT-4o-mini for generating tailored replies, all triggered by chat inputs from platforms such as Telegram.
Use this when you need a quick, always-on assistant for specific Confluence pages, such as FAQs or project wikis, especially in customer-facing or internal support scenarios. Avoid it for highly dynamic content that changes frequently, as updates require manual reconfiguration, or for broad company-wide searches spanning multiple pages. Common variations include swapping Telegram for Slack integration or expanding to multiple pages with conditional branching.
About this workflow
🌐 Confluence Page AI Powered Chatbot. Uses stickyNote, httpRequest, markdown, lmChatOpenAi. Chat trigger; 16 nodes.
Source: https://github.com/Zie619/n8n-workflows — 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 n8n workflow template enables users to interact with an AI-powered chatbot designed to retrieve, process, and analyze content from Confluence pages. By leveraging Confluence's REST API and an AI
This project is an automation workflow that generates a personalized resume and cover letter for each job listing. Generates an HTML resume from your data. Hosts it live on GitHub Pages. Converts it t
Digital marketers, content creators, social media managers, and businesses who want to use AI marketing automation for YouTube Shorts without spending hours on production. This AI workflow helps anyon
Inbox Guardian. Uses gmailTrigger, lmChatOpenAi, agent, textClassifier. Event-driven trigger; 66 nodes.
This workflow is for beauty salons who want consistent, high‑quality social media content without writing every post manually. It also suits agencies and automation builders who manage multiple beauty