This workflow follows the Agent → Chat 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 →
{
"name": "Sweeppea v0.2.0 \u2014 Smart Registration (chat)",
"nodes": [
{
"parameters": {
"content": "## Smart Registration v2\n\nEvolves v1's dynamic-form pattern with v0.2.0 ops.\n\n**Flow**: Chat \u2192 Count \u2192 Get Form Fields \u2192 Build prompt (with form fields + current count) \u2192 AI Agent collects data \u2192 Switch \u2192 Transform \u2192 Create \u2192 Reply.\n\n**New in v2**: shows participant their position (\"you'll be #N+1\") thanks to `Participant: Count`.\n\nReplace `sweepstakesToken` in the two Sweeppea nodes with yours, and bind the OpenAI credential on the chat model.",
"height": 280,
"width": 460,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-400,
0
],
"id": "10000000-0000-0000-0000-000000000001",
"name": "Sticky: README"
},
{
"parameters": {
"public": true,
"options": {
"responseMode": "responseNodes"
}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.3,
"position": [
-400,
400
],
"id": "10000000-0000-0000-0000-000000000010",
"name": "When chat message received"
},
{
"parameters": {
"resource": "participant",
"operation": "count",
"sweepstakesToken": "512e77fa-3d11-4ebe-95ee-031d7ddfa593",
"countFilterType": "all"
},
"type": "n8n-nodes-sweeppea.sweeppea",
"typeVersion": 1,
"position": [
-180,
400
],
"id": "10000000-0000-0000-0000-000000000020",
"name": "Count Participants",
"credentials": {
"sweeppeaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"resource": "participant",
"operation": "getFormFields",
"sweepstakesToken": "512e77fa-3d11-4ebe-95ee-031d7ddfa593"
},
"type": "n8n-nodes-sweeppea.sweeppea",
"typeVersion": 1,
"position": [
40,
400
],
"id": "10000000-0000-0000-0000-000000000030",
"name": "Get Form Fields",
"credentials": {
"sweeppeaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "/* Build Dynamic System Prompt From Form Fields + Current Count */\n\nconst schemaResp = $input.first().json;\nconst data = schemaResp.Data;\nconst countResp = $('Count Participants').first().json;\nconst current = countResp?.Data?.Counts?.Total ?? 0;\nconst chatInput = $('When chat message received').first().json.chatInput;\nconst sessionId = $('When chat message received').first().json.sessionId;\n\nif (!data || !data.FormFields) {\n\tthrow new Error('Form fields not available \u2014 check the sweepstakesToken');\n}\n\n/* Slug Helper: 'First Name' \u2192 'First_Name' */\nconst toSlug = (n) => n.trim().replace(/\\s+/g, '_');\n\n/* Build Required/Optional Lists */\nconst required = data.FormFields.filter(f => f.Required);\nconst optional = data.FormFields.filter(f => !f.Required);\nconst describe = (f) => {\n\tconst ex = f.Placeholder ? ` \u2014 example: ${f.Placeholder}` : '';\n\tconst opts = (f.Options && f.Options.length) ? ` \u2014 pick one: ${f.Options.map(o => `${o.Id}=${o.Name}`).join(', ')}` : '';\n\treturn `- ${f.Name}${ex}${opts}`;\n};\n\n/* Build JSON Example Skeleton */\nconst skeleton = {};\ndata.FormFields.forEach(f => {\n\tconst slug = toSlug(f.Name);\n\tif (f.Type === 'email') skeleton[slug] = 'user@example.com';\n\telse if (f.Type === 'usphonenumber') skeleton[slug] = '5551234567';\n\telse if (f.Type === 'birthdate') skeleton[slug] = 'MM/DD/YYYY';\n\telse if (f.Type === 'number') skeleton[slug] = '0';\n\telse if (f.Type === 'list' && f.Options?.length) skeleton[slug] = String(f.Options[0].Id);\n\telse skeleton[slug] = '<value>';\n});\n\n/* Identify Key Fields For Mapping */\nconst emailField = data.FormFields.find(f => f.Type === 'email');\nconst phoneField = data.FormFields.find(f => f.Type === 'usphonenumber');\n\n/* Compose System Message */\nconst systemPrompt = `You are a friendly sweepstake registration assistant.\n\nThe sweepstake currently has ${current} participants. Tell the user they'll be #${current + 1} once registered.\n\nCollect this data ONE field at a time:\n\nRequired:\n${required.map(describe).join('\\n')}\n${optional.length ? `\\nOptional:\\n${optional.map(describe).join('\\n')}` : ''}\n\nWhen you have all required fields, respond with EXACTLY this JSON (no markdown, no extra text):\n\n${JSON.stringify({ action: 'create_participant', ...skeleton }, null, 2)}\n\nRules:\n- Use the field names exactly as shown (underscores).\n- For list fields, pass the option ID number.\n- Validate emails and phones (10 digits) before sending the final JSON.\n- Be warm, brief, and friendly.`;\n\nreturn {\n\tjson: {\n\t\tsystemPrompt,\n\t\tchatInput,\n\t\tsessionId,\n\t\temailFieldSlug: emailField ? toSlug(emailField.Name) : 'Email',\n\t\tphoneFieldSlug: phoneField ? toSlug(phoneField.Name) : 'Mobile_Number',\n\t\tcurrentParticipantCount: current\n\t}\n};"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
260,
400
],
"id": "10000000-0000-0000-0000-000000000040",
"name": "Build Dynamic Prompt"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.chatInput }}",
"options": {
"systemMessage": "={{ $json.systemPrompt }}"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 2.2,
"position": [
480,
400
],
"id": "10000000-0000-0000-0000-000000000050",
"name": "AI Agent"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
420,
620
],
"id": "10000000-0000-0000-0000-000000000060",
"name": "OpenAI Chat Model"
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('When chat message received').first().json.sessionId }}",
"contextWindowLength": 12
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
620,
620
],
"id": "10000000-0000-0000-0000-000000000070",
"name": "Simple Memory"
},
{
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"caseSensitive": true,
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"leftValue": "={{ $json.output }}",
"rightValue": "create_participant",
"operator": {
"type": "string",
"operation": "contains"
},
"id": "switch-cond-1"
}
],
"combinator": "and"
}
}
]
},
"options": {
"fallbackOutput": "extra"
}
},
"type": "n8n-nodes-base.switch",
"typeVersion": 3.3,
"position": [
780,
400
],
"id": "10000000-0000-0000-0000-000000000080",
"name": "Switch: ready to register?"
},
{
"parameters": {
"jsCode": "/* Transform AI Output JSON Into participant:create Input Shape */\n\nconst aiOutput = $input.first().json.output;\nconst promptData = $('Build Dynamic Prompt').first().json;\n\n/* LLMs Sometimes Add Narrative Around The JSON; Strip Markdown Fences */\n/* And Extract The Outermost {...} Block From Whatever The Model Wrote */\nlet raw = String(aiOutput).replace(/```json/g, '').replace(/```/g, '');\nconst firstBrace = raw.indexOf('{');\nconst lastBrace = raw.lastIndexOf('}');\n\nif (firstBrace === -1 || lastBrace === -1 || lastBrace < firstBrace) {\n\tthrow new Error('AI output did not contain a JSON object: ' + raw.slice(0, 200));\n}\n\nconst clean = raw.slice(firstBrace, lastBrace + 1).trim();\nconst parsed = JSON.parse(clean);\n\nif (parsed.action !== 'create_participant') {\n\treturn { json: {} };\n}\n\nconst { action, ...fields } = parsed;\n\nreturn {\n\tjson: {\n\t\tKeyEmail : fields[promptData.emailFieldSlug] || '',\n\t\tKeyPhoneNumber : fields[promptData.phoneFieldSlug] || '',\n\t\tBonusEntries : 0,\n\t\tFields : fields\n\t}\n};"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
980,
304
],
"id": "10000000-0000-0000-0000-000000000090",
"name": "Transform AI \u2192 API"
},
{
"parameters": {
"resource": "participant",
"operation": "create",
"sweepstakesToken": "512e77fa-3d11-4ebe-95ee-031d7ddfa593"
},
"type": "n8n-nodes-sweeppea.sweeppea",
"typeVersion": 1,
"position": [
1180,
304
],
"id": "10000000-0000-0000-0000-0000000000A0",
"name": "Register Participant",
"credentials": {
"sweeppeaApi": {
"name": "<your credential>"
}
},
"onError": "continueRegularOutput"
},
{
"parameters": {
"message": "={{\n $json.Response === false\n ? ($json.Message && $json.Message.toLowerCase().includes('duplicated')\n ? 'You have already entered this sweepstake \u2014 only one entry per person. \ud83c\udf89'\n : 'Sorry, registration failed: ' + ($json.Message || 'unknown error'))\n : 'You are in! \ud83c\udf8a You are participant #' + ($('Build Dynamic Prompt').first().json.currentParticipantCount + 1) + '. Good luck!'\n}}",
"waitUserReply": false,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.chat",
"typeVersion": 1,
"position": [
1400,
304
],
"id": "10000000-0000-0000-0000-0000000000B0",
"name": "Reply: registered"
},
{
"parameters": {
"message": "={{ $('AI Agent').first().json.output }}",
"waitUserReply": false,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.chat",
"typeVersion": 1,
"position": [
980,
496
],
"id": "10000000-0000-0000-0000-0000000000C0",
"name": "Reply: continue dialog"
}
],
"connections": {
"When chat message received": {
"main": [
[
{
"node": "Count Participants",
"type": "main",
"index": 0
}
]
]
},
"Count Participants": {
"main": [
[
{
"node": "Get Form Fields",
"type": "main",
"index": 0
}
]
]
},
"Get Form Fields": {
"main": [
[
{
"node": "Build Dynamic Prompt",
"type": "main",
"index": 0
}
]
]
},
"Build Dynamic Prompt": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Switch: ready to register?",
"type": "main",
"index": 0
}
]
]
},
"Switch: ready to register?": {
"main": [
[
{
"node": "Transform AI \u2192 API",
"type": "main",
"index": 0
}
],
[
{
"node": "Reply: continue dialog",
"type": "main",
"index": 0
}
]
]
},
"Transform AI \u2192 API": {
"main": [
[
{
"node": "Register Participant",
"type": "main",
"index": 0
}
]
]
},
"Register Participant": {
"main": [
[
{
"node": "Reply: registered",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
},
"meta": {
"templateCredsSetupCompleted": true
},
"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.
sweeppeaApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Sweeppea v0.2.0 — Smart Registration (chat). Uses chatTrigger, n8n-nodes-sweeppea, agent, lmChatOpenAi. Chat trigger; 13 nodes.
Source: https://github.com/Sweeppea-Development-Lab/sweeppea-n8n-nodes/blob/c4dbe5a70c9de86b27b1a226d1e2ab71f1ed64ee/examples/sweeppea-smart-registration-v2.json — 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.
Who is this workflow for? This workflow is designed for SEO analysts, content creators, marketing agencies, and developers who need to index a website and then interact with its content as if it were
Agent, OpenAI Chat, Memory Buffer Window +10
This Chatbot automates the process of discovering job openings and generating tailored job application emails.
Chat Trigger, OpenAI Chat, Mcp Client Tool +12
Job Application PredictLeads & ScrapeGraph AI. Uses chatTrigger, lmChatOpenAi, mcpClientTool, memoryBufferWindow. Chat trigger; 32 nodes.
Chat Trigger, OpenAI Chat, Mcp Client Tool +12
Job Application PredictLeads & ScrapeGraph AI. Uses chatTrigger, lmChatOpenAi, mcpClientTool, memoryBufferWindow. Chat trigger; 32 nodes.
Chat Trigger, OpenAI Chat, Mcp Client Tool +12
This workflow implements an advanced AI-powered system for generating, and executing Claude Skills stored on GitHub.
Chat Trigger, Memory Buffer Window, Mcp Client Tool +9